fix: boilerplate reduction 70

* feat: boilerplate reduction 66

* fix bucket name

.cloud-build/cleanup/cleanup.py

@@ -1,5 +1,14 @@
 from typing import List
 from ratemate import RateLimit
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--dry_run",
+                    type=bool,
+                    default=False)
+args = parser.parse_args()
+
+
 from resource_cleanup_manager import (
     DatasetResourceCleanupManager,
     ModelResourceCleanupManager,
@@ -7,6 +16,14 @@ from resource_cleanup_manager import (
     ResourceCleanupManager,
     MatchingEngineIndexEndpointResourceCleanupManager,
     MatchingEngineIndexResourceCleanupManager,
+    FeatureStoreCleanupManager,
+    PipelineJobCleanupManager,
+    TrainingJobCleanupManager,
+    HyperparameterTuningCleanupManager,
+    BatchPredictionJobCleanupManager,
+    ExperimentCleanupManager,
+    BucketCleanupManager,
+    ArtifactRegistryCleanupManager
 )
 
 rate_limit = RateLimit(max_count=25, per=60, greedy=False)
@@ -23,7 +40,6 @@ def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: boo
             try:
                 if not manager.is_deletable(resource):
                     continue
-
                 if is_dry_run:
                     resource_name = manager.resource_name(resource)
                     print(f"Will delete '{type_name}': {resource_name}")
@@ -36,9 +52,7 @@ def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: boo
         print("")
 
 
-is_dry_run = False
-
-if is_dry_run:
+if args.dry_run:
     print("Starting cleanup in dry run mode...")
 
 # List of all cleanup managers
@@ -48,6 +62,14 @@ managers: List[ResourceCleanupManager] = [
     ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
     MatchingEngineIndexEndpointResourceCleanupManager(),
     MatchingEngineIndexResourceCleanupManager(),
+    FeatureStoreCleanupManager(),
+    PipelineJobCleanupManager(),
+    TrainingJobCleanupManager(),
+    HyperparameterTuningCleanupManager(),
+    BatchPredictionJobCleanupManager(),
+    ExperimentCleanupManager(), # Experiment missing _resource_noun
+    BucketCleanupManager(),
+    ArtifactRegistryCleanupManager()
 ]
 
-run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)
+run_cleanup_managers(managers=managers, is_dry_run=args.dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -1,8 +1,18 @@
+'''
+READ FIRST BEFORE MAKING CHANGES
+-  Create a convention for resources created from vertex-ai-samples GH. We already have one IIRC
+- Only delete those objects as part of our clean-up script.
+- Don't run any tests on python-docs-samples-tests project, especially ones that affect resources created outside of our purview
+- Add --dry-run option to the clean-up script. This option will just output the list of resources the script will delete instead of actually deleting the resources.
+- Have a larger conversation in DEE before touching any resources that were not created as part of vertex-ai-samples
+'''
+import os
 import abc
 from typing import Any, Type
 
 from google.cloud import aiplatform
 from google.cloud.aiplatform import base
+from google.cloud import storage
 from proto.datetime_helpers import DatetimeWithNanoseconds
 
 # If a resource was updated within this number of seconds, do not delete.
@@ -69,7 +79,7 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
     def delete(self, resource):
         resource.delete()
 
-    def get_seconds_since_modification(self, resource: Any) -> bool:
+    def get_seconds_since_modification(self, resource: Any) -> float:
         update_time = resource.update_time
         current_time = DatetimeWithNanoseconds.now(tz=update_time.tzinfo)
         return (current_time - update_time).total_seconds()
@@ -97,13 +107,10 @@ class EndpointResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Endpoint
 
     def delete(self, resource):
-        # TODO: Remove this once https://github.com/googleapis/python-aiplatform/issues/1441 is fixed
-        resource._sync_gca_resource()
         for deployed_model_id in [
             models.id for models in resource._gca_resource.deployed_models
         ]:
             resource._undeploy(deployed_model_id=deployed_model_id)
-
         resource.delete(force=True)
 
 
@@ -117,3 +124,125 @@ class MatchingEngineIndexResourceCleanupManager(VertexAIResourceCleanupManager):
 
 class MatchingEngineIndexEndpointResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.MatchingEngineIndexEndpoint
+
+    def delete(self, resource):
+        resource.undeploy_all()
+        resource.delete(force=True)
+
+class FeatureStoreCleanupManager(VertexAIResourceCleanupManager):
+    vertex_ai_resource = aiplatform.Featurestore
+
+    def resource_name(self, resource: Any) -> str:
+        return resource.name
+
+class PipelineJobCleanupManager(VertexAIResourceCleanupManager):
+    vertex_ai_resource = aiplatform.PipelineJob
+
+class TrainingJobCleanupManager(VertexAIResourceCleanupManager):
+    vertex_ai_resource = aiplatform.training_jobs._CustomTrainingJob
+
+    job_types = [
+            aiplatform.AutoMLImageTrainingJob,
+            aiplatform.AutoMLTextTrainingJob,
+            aiplatform.AutoMLTabularTrainingJob,
+            aiplatform.AutoMLVideoTrainingJob,
+            aiplatform.AutoMLForecastingTrainingJob,
+            aiplatform.CustomJob,
+            aiplatform.CustomTrainingJob,
+            aiplatform.CustomContainerTrainingJob,
+            aiplatform.CustomPythonPackageTrainingJob
+    ]
+
+    def list(self) -> Any:
+        return [
+            job
+            for job_type in self.job_types
+            for job in job_type.list()
+        ]
+
+class HyperparameterTuningCleanupManager(VertexAIResourceCleanupManager):
+    vertex_ai_resource = aiplatform.HyperparameterTuningJob
+
+
+class BatchPredictionJobCleanupManager(VertexAIResourceCleanupManager):
+    vertex_ai_resource = aiplatform.BatchPredictionJob
+
+class ExperimentCleanupManager(VertexAIResourceCleanupManager):
+    vertex_ai_resource = aiplatform.Experiment
+
+    @property
+    def type_name(self) -> str:
+        return "Experiment"
+
+    def resource_name(self, resource: Any) -> str:
+        return resource.name
+
+    def get_seconds_since_modification(self, resource: Any) -> float:
+        update_time = resource._metadata_context.update_time
+        current_time = DatetimeWithNanoseconds.now()
+        return float(current_time.timestamp() - update_time.timestamp())
+
+class BucketCleanupManager(ResourceCleanupManager):
+    vertex_ai_resource = storage.bucket.Bucket
+
+    def list(self) -> Any:
+        storage_client = storage.Client()
+        return list(storage_client.list_buckets())
+
+    def delete(self, resource):
+        try:
+            resource.delete(force=True)
+        except Exception as e:
+            print(e)
+
+    @property
+    def type_name(self) -> str:
+        return "Bucket"
+
+    def get_seconds_since_modification(self, resource: Any) -> float:
+        # Bucket has no last_update property, only time created
+        created_time = resource.time_created
+        current_time = DatetimeWithNanoseconds.now()
+        return float(current_time.timestamp() - created_time.timestamp())
+
+    def resource_name(self, resource: Any) -> str:
+        return resource.name
+
+    def is_deletable(self, resource: Any) -> bool:
+        time_difference = self.get_seconds_since_modification(resource)
+
+        if not self.resource_name(resource).startswith('your-bucket-name'):
+            print(f"Skipping '{resource}' not a Vertex AI notebook bucket")
+            return False
+
+        # Check that it wasn't created too recently, to prevent race conditions
+        if time_difference <= RESOURCE_UPDATE_BUFFER_IN_SECONDS:
+            print(
+                f"Skipping '{resource}' due to update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
+            )
+            return False
+        return True
+
+class ArtifactRegistryCleanupManager(ResourceCleanupManager):
+    vertex_ai_resource = "Artifact Registry"
+
+    def list(self) -> Any:
+        return ["my-private-repo"]
+
+    def delete(self, resource):
+        os.system(f"! gcloud artifacts repositories delete {resource} --location=us-central1")
+
+    @property
+    def type_name(self) -> str:
+        return "ArtifactRepository"
+
+    def resource_name(self, resource: Any) -> str:
+        return resource
+
+    # delete repository regardless of age
+    def get_seconds_since_modification(self, resource: Any) -> float:
+        return RESOURCE_UPDATE_BUFFER_IN_SECONDS + 1
+    
+    def is_deleteable(self, resource: Any) -> bool:
+        return True
+

.cloud-build/execute_changed_notebooks_cli.py

@@ -17,6 +17,7 @@
 
 import argparse
 import pathlib
+import os
 
 import execute_changed_notebooks_helper
 
@@ -39,6 +40,19 @@ parser.add_argument(
     help="The path to the file that has newline-limited folders of notebooks that should be tested.",
     required=True,
 )
+parser.add_argument(
+    "--test_percent",
+    type=int,
+    help="The percent of notebooks to be tested (between 1 and 100).",
+    required=False,
+    default=100,
+)
+parser.add_argument(
+    "--build_id",
+    type=str,
+    help="The build id (which may be a Cloud Build job specific or user explicit.",
+    required=True
+)
 parser.add_argument(
     "--base_branch",
     help="The base git branch to diff against to find changed files.",
@@ -107,24 +121,52 @@ parser.add_argument(
     default=True,
     help="Should run notebooks in parallel.",
 )
+parser.add_argument(
+    "--dry_run",
+    type=str2bool,
+    default=False,
+    help="Dry run for testing - no execution",
+)
 
 args = parser.parse_args()
 
-notebooks = execute_changed_notebooks_helper.get_changed_notebooks(
+changed_notebooks = execute_changed_notebooks_helper.get_changed_notebooks(
     test_paths_file=args.test_paths_file,
     base_branch=args.base_branch,
 )
 
-execute_changed_notebooks_helper.process_and_execute_notebooks(
-    notebooks=notebooks,
-    container_uri=args.container_uri,
-    staging_bucket=args.staging_bucket,
-    artifacts_bucket=args.artifacts_bucket,
-    should_parallelize=args.should_parallelize,
-    timeout=args.timeout,
-    variable_project_id=args.variable_project_id,
-    variable_region=args.variable_region,
-    variable_service_account=args.variable_service_account,
-    variable_vpc_network=args.variable_vpc_network,
-    private_pool_id=args.private_pool_id,
+
+results_bucket = f"{args.artifacts_bucket}"
+# artifacts_bucket may get set by trigger to a full gs:// folder path
+if results_bucket.startswith("gs://"):
+    results_bucket = results_bucket[5:]
+results_bucket = results_bucket.split('/')[0]
+results_file = f"build_results/{args.build_id}.json"
+
+if args.test_percent == 100:
+    notebooks = changed_notebooks
+    accumulative_results = {}
+else:
+    accumulative_results = execute_changed_notebooks_helper.load_results(results_bucket, results_file)
+
+    notebooks = [changed_notebook for changed_notebook in changed_notebooks if execute_changed_notebooks_helper.select_notebook(changed_notebook, accumulative_results, args.test_percent)]
+
+if args.dry_run:
+    print("Dry run ...\n")
+    for notebook in notebooks:
+        print(f"Would execute: {notebook}")
+else:
+    execute_changed_notebooks_helper.process_and_execute_notebooks(
+        notebooks=notebooks,
+        container_uri=args.container_uri,
+        staging_bucket=args.staging_bucket,
+        artifacts_bucket=args.artifacts_bucket,
+        results_file=results_file,
+        should_parallelize=args.should_parallelize,
+        timeout=args.timeout,
+        variable_project_id=args.variable_project_id,
+        variable_region=args.variable_region,
+        variable_service_account=args.variable_service_account,
+        variable_vpc_network=args.variable_vpc_network,
+        private_pool_id=args.private_pool_id
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -21,11 +21,15 @@ import json
 import git
 import operator
 import os
+import io
+import json
 import pathlib
 import re
 import subprocess
+import random
+from google.cloud import storage
 import utils
-from typing import List, Optional
+from typing import List, Optional, Dict, Any
 from utils import util
 
 import execute_notebook_helper
@@ -40,6 +44,9 @@ from utils import NotebookProcessors, util
 WORKER_TIMEOUT_BUFFER_IN_SECONDS: int = 60 * 60
 PYTHON_VERSION = "3.9"  # Set default python version
 
+# rolling time window for accumulating build results for selecting notebooks
+MAX_RESULTS_AGE_SECONDS: int = (60 * 60) * 24 * 60  # 60 days
+
 
 def format_timedelta(delta: datetime.timedelta) -> str:
     """Formats a timedelta duration to [N days] %H:%M:%S format"""
@@ -65,7 +72,9 @@ def format_timedelta(delta: datetime.timedelta) -> str:
 @dataclasses.dataclass
 class NotebookExecutionResult:
     name: str
+    path: str
     duration: datetime.timedelta
+    start_time: datetime.datetime
     is_pass: bool
     log_url: str
     output_uri: str
@@ -81,6 +90,75 @@ class NotebookExecutionResult:
             return None
 
 
+def load_results(results_bucket: str,
+                 results_file: str) -> Dict[str, Any]:
+    '''
+    Load accumulated notebook test results
+    '''
+
+    print("Loading existing accumulative results ...")
+    accumulative_results = {}
+    try:
+        client = storage.Client()
+        bucket = client.bucket(results_bucket)
+
+        build_results_dir = os.path.dirname(results_file)
+        blobs = client.list_blobs(results_bucket, prefix=build_results_dir)
+        for blob in blobs:
+            time_created = blob.time_created.replace(tzinfo=None)
+            if (datetime.datetime.now().replace(tzinfo=None) - time_created).total_seconds() > MAX_RESULTS_AGE_SECONDS:
+                continue
+
+            content = util.download_blob_into_memory(results_bucket, blob.name, download_as_text=True)
+
+            try:
+                build_results = json.loads(content)
+            except:
+                continue  # skip corrupted build results files
+            for notebook in build_results:
+                if notebook in accumulative_results:
+                    accumulative_results[notebook]['passed'] += build_results[notebook]['passed']
+                    accumulative_results[notebook]['failed'] += build_results[notebook]['failed']
+                else:
+                    accumulative_results[notebook] = build_results[notebook]
+
+        print(accumulative_results)
+    except Exception as e:
+        print(e)
+
+    # If there are no accumulative results, an empty dict is returned
+    return accumulative_results
+
+def select_notebook(changed_notebook: str,
+                    accumulative_results: Dict[str, Any],
+                    test_percent: int) -> bool:
+    '''
+    Algorithm to randomly select a notebook, but weight the propbability of selected based on past failures
+    '''
+
+    if changed_notebook in accumulative_results:
+        pass_count = accumulative_results[changed_notebook]['passed']
+        fail_count = accumulative_results[changed_notebook]['failed']
+    else:
+        pass_count = 1
+        fail_count = 0
+
+    inferred_failure_rate = fail_count / (pass_count + fail_count)
+
+    # If failure rate is high, the chance of testing should be higher
+    should_test_due_to_failure = random.uniform(0, 1) <= inferred_failure_rate
+
+    # Additionally, only test a percentage of these
+    should_test_due_to_random_subset = random.uniform(0, 1) <= (test_percent / 100)
+
+    if should_test_due_to_failure or should_test_due_to_random_subset:
+        print(f"Selected: {changed_notebook}, {should_test_due_to_failure}, {should_test_due_to_random_subset}")
+        return True
+    else:
+        print(f"Not Selected: {changed_notebook}, pass {pass_count}, fail {fail_count}")
+        return False
+
+
 def _process_notebook(
     notebook_path: str,
     variable_project_id: str,
@@ -156,7 +234,7 @@ def _create_tag(filepath: str) -> str:
     return tag
 
 
-rate_limit = RateLimit(max_count=50, per=60, greedy=True)
+rate_limit = RateLimit(max_count=10, per=60, greedy=True)
 
 
 def process_and_execute_notebook(
@@ -191,7 +269,9 @@ def process_and_execute_notebook(
 
     result = NotebookExecutionResult(
         name=tag,
+        path=notebook,
         duration=datetime.timedelta(seconds=0),
+        start_time=datetime.datetime.now(),
         is_pass=False,
         output_uri=notebook_output_uri,
         log_url="",
@@ -201,7 +281,6 @@ def process_and_execute_notebook(
     )
 
     # TODO: Handle cases where multiple notebooks have the same name
-    time_start = datetime.datetime.now()
     operation = None
     try:
         # Get the python version for running the notebook if specified
@@ -247,9 +326,10 @@ def process_and_execute_notebook(
         # Block and wait for the result
         operation_result = operation.result(timeout=timeout_in_seconds)
 
-        result.duration = datetime.datetime.now() - time_start
+        result.duration = datetime.datetime.now() - result.start_time
         result.is_pass = True
         print(f"{notebook} PASSED in {format_timedelta(result.duration)}.")
+
     except Exception as error:
         result.error_message = str(error)
 
@@ -268,7 +348,7 @@ def process_and_execute_notebook(
             except Exception as error:
                 result.error_message = str(error)
 
-        result.duration = datetime.datetime.now() - time_start
+        result.duration = datetime.datetime.now() - result.start_time
         result.is_pass = False
 
         print(
@@ -336,12 +416,44 @@ def get_changed_notebooks(
 
     return notebooks
 
+def _save_results(results: List[NotebookExecutionResult],
+                  artifacts_bucket: str,
+                  results_file: str):
+
+    artifacts_bucket = artifacts_bucket.replace("gs://", "").split('/')[0]
+
+    print("Updating build results ...")
+    build_results = {}
+    for result in results:
+        if result.is_pass:
+            pass_count = 1
+            fail_count = 0
+        else:
+            pass_count = 0
+            fail_count = 1
+        build_results[result.path] = {
+                'duration': result.duration.total_seconds(),
+                'start_time': str(result.start_time),
+                'passed': pass_count,
+                'failed': fail_count
+        }
+        print(f"adding {result.path}")
+
+    print("Saving accumulative results ...")
+    content = json.dumps(build_results)
+
+    client = storage.Client()
+    bucket = client.get_bucket(artifacts_bucket)
+    bucket.blob(str(results_file)).upload_from_string(content, 'text/json')
+
+
 
 def process_and_execute_notebooks(
     notebooks: List[str],
     container_uri: str,
     staging_bucket: str,
     artifacts_bucket: str,
+    results_file: str,
     should_parallelize: bool,
     timeout: int,
     variable_project_id: str,
@@ -369,6 +481,8 @@ def process_and_execute_notebooks(
             Required. The GCS staging bucket to write source code to.
         artifacts_bucket (str):
             Required. The GCS staging bucket to write executed notebooks to.
+        results_file (str):
+            Required: The path to the artifacts bucket to save results 
         variable_project_id (str):
             Required. The value for PROJECT_ID to inject into notebooks.
         variable_region (str):
@@ -471,7 +585,7 @@ def process_and_execute_notebooks(
             print("=" * 100)
 
             build_id = results_sorted[0].build_id
-            logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
+            logs_bucket_name = (results_sorted[0].logs_bucket).replace("gs://", "")
             log_file_name = f"log-{build_id}.txt"
 
             log_contents = util.download_blob_into_memory(
@@ -489,6 +603,10 @@ def process_and_execute_notebooks(
             else:
                 print(log_contents)
 
+        _save_results(results_sorted, 
+                      artifacts_bucket, 
+                      results_file)
+
         print("\n=== END RESULTS===\n")
 
         total_notebook_duration = functools.reduce(

.cloud-build/notebook-execution-test-cloudbuild.yaml

@@ -36,7 +36,7 @@ steps:
     - -c
     - |
       . workspace/env/bin/activate &&
-      python3 .cloud-build/execute_changed_notebooks_cli.py --test_paths_file "${_TEST_PATHS_FILE}" --base_branch "${_FORCED_BASE_BRANCH}" --container_uri ${_PYTHON_IMAGE} --staging_bucket ${_GCS_STAGING_BUCKET}  --artifacts_bucket ${_GCS_STAGING_BUCKET}/executed_notebooks/PR_${_PR_NUMBER}/BUILD_${BUILD_ID} --variable_project_id ${PROJECT_ID} --variable_region ${_GCP_REGION} --variable_service_account ${_GCP_SERVICE_ACCOUNT} --variable_vpc_network "${_GPC_VPC_NETWORK_NAME}" `if [ ! -z "${_PRIVATE_POOL_NAME}" ]; then echo "--private_pool_id ${_PRIVATE_POOL_NAME}"; fi`
+      python3 .cloud-build/execute_changed_notebooks_cli.py --test_paths_file "${_TEST_PATHS_FILE}" --base_branch "${_FORCED_BASE_BRANCH}" --container_uri ${_PYTHON_IMAGE} --staging_bucket ${_GCS_STAGING_BUCKET}  --artifacts_bucket ${_GCS_STAGING_BUCKET}/executed_notebooks/PR_${_PR_NUMBER}/BUILD_${BUILD_ID} --variable_project_id ${PROJECT_ID} --variable_region ${_GCP_REGION} --variable_service_account ${_GCP_SERVICE_ACCOUNT} --variable_vpc_network "${_GPC_VPC_NETWORK_NAME}" `if [ ! -z "${_PRIVATE_POOL_NAME}" ]; then echo "--private_pool_id ${_PRIVATE_POOL_NAME}"; fi` --build_id ${BUILD_ID} --test_percent=${_TEST_PERCENT}
     env:
     - 'IS_TESTING=1'
 timeout: 86400s

.cloud-build/requirements.txt

@@ -3,12 +3,15 @@ numpy
 jupyter
 nbconvert
 papermill
-pandas
 matplotlib
 tabulate
 google-cloud-aiplatform
 google-cloud-storage
 google-cloud-build
+google-cloud-storage
 ratemate
 GitPython
-google-api-core==2.10
+tqdm
+fsspec
+pandas
+

.cloud-build/test_failing.txt

@@ -0,0 +1,40 @@
+notebooks/official/training/pytorch_gcs_data_training.ipynb
+notebooks/official/custom/custom_training_tensorboard_profiler.ipynb
+notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb
+notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb
+notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb
+notebooks/official/tabnet/tabnet_vertex_tutorial.ipynb
+notebooks/official/tabnet/get_started_with_tabnet.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb
+notebooks/official/pipelines/multicontender_vs_champion_deployment_method.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.ipynb
+notebooks/official/pipelines/rapid_prototyping_bqml_automl.ipynb
+notebooks/official/pipelines/challenger_vs_blessed_deployment_method.ipynb
+notebooks/official/matching_engine/sdk_matching_engine_create_stack_overflow_embeddings.ipynb
+notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb
+notebooks/official/matching_engine/sdk_matching_engine_create_text_to_image_embeddings.ipynb
+notebooks/official/explainable_ai/sdk_custom_image_classification_online_explain.ipynb
+notebooks/official/explainable_ai/xai_image_classification_feature_attributions.ipynb
+notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb
+notebooks/official/tabular_workflows/tabnet_on_vertex_pipelines.ipynb
+notebooks/official/model_registry/get_started_with_model_registry.ipynb
+notebooks/official/model_registry/bqml_vertexai_model_registry.ipynb
+notebooks/official/sdk/SDK_Custom_Training_Python_Package_Managed_Text_Dataset_Tensorflow_Serving_Container.ipynb
+notebooks/official/model_monitoring/batch_prediction_model_monitoring.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_setup.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_custom.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_custom_tf_serving.ipynb
+notebooks/official/model_monitoring/model_monitoring.ipynb
+notebooks/official/tensorboard/tensorboard_profiler_custom_training_with_prebuilt_container.ipynb
+notebooks/official/tensorboard/tensorboard_hyperparameter_tuning_with_hparams.ipynb
+notebooks/official/tensorboard/tensorboard_profiler_custom_training.ipynb
+notebooks/official/model_evaluation/custom_tabular_regression_model_evaluation.ipynb
+notebooks/official/model_evaluation/custom_tabular_classification_model_evaluation.ipynb
+notebooks/official/model_evaluation/automl_video_classification_model_evaluation.ipynb
+notebooks/official/experiments/comparing_local_trained_models.ipynb
+notebooks/official/automl/automl_image_classification_online_online_prediction.ipynb
+notebooks/official/automl/automl-text-classification.ipynb
+notebooks/official/automl/sdk_automl_video_object_tracking_batch.ipynb
+notebooks/official/feature_store/sdk-feature-store-pandas.ipynb
+notebooks/official/prediction/custom_batch_prediction_feature_filter.ipynb
+notebooks/official/prediction/pytorch_image_classification_with_prebuilt_serving_containers.ipynb

.cloud-build/test_passing.txt

@@ -0,0 +1,80 @@
+notebooks/official/training/hyperparameter_tuning_tensorflow.ipynb
+notebooks/official/training/get_started_with_vertex_distributed_training.ipynb
+notebooks/official/training/hyperparameter_tuning_xgboost.ipynb
+notebooks/official/training/multi_node_ddp_gloo_vertex_training_with_custom_container.ipynb
+notebooks/official/training/distributed_hyperparameter_tuning.ipynb
+notebooks/official/training/pytorch-text-sentiment-classification-custom-train-deploy.ipynb
+notebooks/official/training/xgboost_data_parallel_training_on_cpu_using_dask.ipynb
+notebooks/official/training/multi_node_ddp_nccl_vertex_training_with_custom_container.ipynb
+notebooks/official/bigquery_ml/get_started_with_bqml_training.ipynb
+notebooks/official/bigquery_ml/bqml-online-prediction.ipynb
+notebooks/official/custom/custom_training_container_and_model_registry.ipynb
+notebooks/official/custom/sdk-custom-image-classification-online.ipynb
+notebooks/official/custom/sdk-custom-image-classification-batch.ipynb
+notebooks/official/custom/SDK_FBProphet_Forecasting_Online.ipynb
+notebooks/official/custom/get_started_vertex_training_xgboost.ipynb
+notebooks/official/custom/get_started_with_vertex_endpoint_and_shared_vm.ipynb
+notebooks/official/custom/SDK_Custom_Container_Prediction.ipynb
+notebooks/official/reduction_server/pytorch_distributed_training_reduction_server.ipynb
+notebooks/official/tabnet/ai-explanations-tabnet-algorithm.ipynb
+notebooks/official/vizier/get_started_vertex_vizier.ipynb
+notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb
+notebooks/official/pipelines/get_started_with_hpt_pipeline_components.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb
+notebooks/official/pipelines/custom_tabular_train_batch_pred_bq_pipeline.ipynb
+notebooks/official/pipelines/metrics_viz_run_compare_kfp.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_model_upload_predict_evaluate.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_model_train_upload_deploy.ipynb
+notebooks/official/pipelines/get_started_with_machine_management.ipynb
+notebooks/official/pipelines/custom_model_training_and_batch_prediction.ipynb
+notebooks/official/pipelines/control_flow_kfp.ipynb
+notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_bqml_text.ipynb
+notebooks/official/pipelines/pipelines_intro_kfp.ipynb
+notebooks/official/pipelines/automl_tabular_classification_beans.ipynb
+notebooks/official/pipelines/google_cloud_pipeline_components_dataproc_tabular.ipynb
+notebooks/official/explainable_ai/sdk_automl_tabular_classification_online_explain.ipynb
+notebooks/official/explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb
+notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb
+notebooks/official/explainable_ai/sdk_custom_tabular_regression_online_explain_get_metadata.ipynb
+notebooks/official/explainable_ai/sdk_custom_tabular_regression_batch_explain.ipynb
+notebooks/official/tabular_workflows/prophet_on_vertex_pipelines.ipynb
+notebooks/official/tabular_workflows/wide_and_deep_on_vertex_pipelines.ipynb
+notebooks/official/sdk/SDK_AutoML_Video_Classification.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_automl.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_automl_image_batch.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_automl_image_online.ipynb
+notebooks/official/model_monitoring/get_started_with_model_monitoring_xgboost.ipynb
+notebooks/official/tensorboard/tensorboard_custom_training_with_custom_container.ipynb
+notebooks/official/tensorboard/tensorboard_custom_training_with_prebuilt_container.ipynb
+notebooks/official/tensorboard/tensorboard_vertex_ai_pipelines_integration.ipynb
+notebooks/official/model_evaluation/automl_text_classification_model_evaluation.ipynb
+notebooks/official/model_evaluation/get_started_with_custom_model_evaluation_import.ipynb
+notebooks/official/model_evaluation/automl_tabular_classification_model_evaluation.ipynb
+notebooks/official/model_evaluation/automl_tabular_regression_model_evaluation.ipynb
+notebooks/official/experiments/get_started_with_vertex_experiments.ipynb
+notebooks/official/experiments/comparing_pipeline_runs.ipynb
+notebooks/official/experiments/get_started_with_vertex_experiments_autologging.ipynb
+notebooks/official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb
+notebooks/official/experiments/delete_outdated_tensorboard_experiments.ipynb
+notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb
+notebooks/official/automl/sdk_automl_text_sentiment_analysis_online.ipynb
+notebooks/official/automl/sdk_automl_text_entity_extraction_online.ipynb
+notebooks/official/automl/sdk_automl_forecasting_hierarchical_batch.ipynb
+notebooks/official/automl/automl_text_entity_extraction_batch_prediction.ipynb
+notebooks/official/automl/automl_image_classification_batch_prediction.ipynb
+notebooks/official/automl/automl_text_sentiment_analysis_batch_prediction.ipynb
+notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb
+notebooks/official/automl/get_started_automl_training.ipynb
+notebooks/official/automl/automl-tabular-classification.ipynb
+notebooks/official/automl/automl_image_object_detection_export_edge.ipynb
+notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb
+notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb
+notebooks/official/automl/sdk_automl_video_classification_batch.ipynb
+notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb
+notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb
+notebooks/official/automl/automl_image_object_detection_online_prediction.ipynb
+notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb
+notebooks/official/datasets/get_started_bq_datasets.ipynb
+notebooks/official/datasets/get_started_with_data_labeling.ipynb
+notebooks/official/feature_store/feature_store_streaming_ingestion_sdk.ipynb

.cloud-build/tests/flaky.py

@@ -0,0 +1,46 @@
+# grep PASSED tests.txt | cut -c 10-100 >passed.txt
+
+import os
+
+repo_dir = '/home/jupyter/vertex-ai-samples/'
+repo_dir_len = len(repo_dir)
+official_dir = repo_dir + 'notebooks/official'
+
+entries = os.scandir(official_dir)
+folders = []
+for entry in entries:
+    if entry.is_dir():
+        folders.append(entry.path)
+
+# Passing
+with open('passed.txt', 'r') as pass_file:
+    notebook_names = pass_file.readlines()
+        
+notebooks = []
+for folder in folders:
+    entries = os.scandir(folder)
+    for entry in entries:
+        for notebook in notebook_names:
+            if entry.name == notebook.rstrip():
+                notebooks.append(entry.path[repo_dir_len:])
+                
+with open('passing_tests.txt', 'w') as f:
+    for notebook in notebooks:
+        f.write(notebook + '\n')
+        
+        
+# Failing
+with open('failed.txt', 'r') as fail_file:
+    notebook_names = fail_file.readlines()
+        
+notebooks = []
+for folder in folders:
+    entries = os.scandir(folder)
+    for entry in entries:
+        for notebook in notebook_names:
+            if entry.name == notebook.rstrip():
+                notebooks.append(entry.path[repo_dir_len:])
+                
+with open('failing_tests.txt', 'w') as f:
+    for notebook in notebooks:
+        f.write(notebook + '\n')

.cloud-build/tests/select_notebooks_test.py

@@ -0,0 +1,33 @@
+import sys
+
+from execute_changed_notebooks_helper import (load_results, select_notebook)
+
+
+def test_load_results():
+    bucket: str = "cloud-build-notebooks-presubmit"
+    bucket_file: str = "build_results"
+
+    accum = load_results(bucket, bucket_file)
+
+    print(accum)
+
+    assert len(accum) > 0
+
+def test_select_notebook():
+    bucket: str = "cloud-build-notebooks-presubmit"
+    bucket_file: str = "build_results"
+
+    accum = load_results(bucket, bucket_file)
+
+    n_select = 0
+    n_notselect = 0
+    for notebook in accum:
+        if select_notebook(notebook, accum, 50):
+            n_select += 1
+        else:
+            n_notselect += 1
+
+    print(f"SELECTED {n_select}, NOT SELECTED {n_notselect}")
+
+    assert n_select > 0
+    assert n_notselect > 0

.cloud-build/utils/build_results_viewer.py

@@ -0,0 +1,22 @@
+'''
+Viewer for the weekly regression testing of the official notebooks
+
+Cloud Storage location: gs://cloud-build-notebooks-presubmit/build_results/
+'''
+import argparse
+import json
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--file', dest='file',
+                    default='build.json', type=str, help='build results file')
+import json
+
+with open('build.json', 'r') as f:
+    results = json.load(f)
+
+for item in results.items():
+    if item[1]['passed']:
+        print(f"{item[0]},PASSED")
+    else:
+        print(f"{item[0]},FAILED")

.github/workflows/linter/requirements.txt

@@ -2,9 +2,9 @@ git+https://github.com/tensorflow/docs
 ipython
 jupyter
 nbconvert
-black==22.10.0
-pyupgrade==2.38.4
-isort==5.10.1
-flake8==4.0.1
-nbqa==1.5.3
+black==23.3.0
+pyupgrade==3.4.0
+isort==5.12.0
+flake8==6.0.0
+nbqa==1.7.0
 

CONTRIBUTING.md

@@ -44,12 +44,10 @@ Finally, run this code block to check for errors. Each step will attempt to
 automatically fix any issues. If the fixes can't be performed automatically,
 then you will need to manually address them before submitting your PR.
 
+Note: For official, only submit one notebook per PR.
+
 ```shell
-nbqa black "$notebook"
-nbqa pyupgrade "$notebook"
-nbqa isort "$notebook"
-nbqa flake8 "$notebook" --extend-ignore=W391,E501,F821,E402,F404,W503,E203,E722,W293,W291
-python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
+docker run -v ${PWD}:/setup/app gcr.io/cloud-devrel-public-resources/notebook_linter:latest your_notebook
 ```
 
 ## Code Reviews

community-content/CODEOWNERS

@@ -9,3 +9,4 @@
 /Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines @Ark-kun
 /pipeline_components @Ark-kun
 /pipeline_components/image_ml_model_training @lakeyk
+/prediction_featurestore_integration @googleapis/vertex-prediction-team

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/trainer/requirements.txt

@@ -1,3 +1,3 @@
-torch==1.8.1
+torch==1.13.1
 torchvision==0.9.1
 tensorboard==2.5.0

community-content/pytorch_image_classification_single_gpu_with_vertex_sdk_and_torchserve/trainer/requirements.txt

@@ -1,3 +1,3 @@
-torch==1.8.1
+torch==1.13.1
 torchvision==0.9.1
 tensorboard==2.5.0

community-content/pytorch_pre_built_images_deployment/pytorch-text-classification-vertex-ai-deploy.ipynb

@@ -31,17 +31,7 @@
       "source": [
         "# Deploying a PyTorch Text Classification Model on [Vertex AI](https://cloud.google.com/vertex-ai)\n",
         "\n",
-        "**This is an Experimental release**, covered by the Pre-GA Offerings Terms of your Google Cloud Platform [Terms of Service](https://cloud.google.com/terms).\n",
-        "\n",
-        "Experiments are focused on validating a prototype and are not guaranteed to be released. They are not intended for production use or covered by any SLA, support obligation, or deprecation policy and might be subject to backward-incompatible changes.\n",
-        "\n",
-        "**Kindly drop us a note before you run any scale tests.**\n",
-        "\n",
-        "**Do not hesitate to contact vertexai-prediction-preview-feedback@google.com if you have any questions or run into any issues.**\n",
-        "\n",
-        "The usage of the product is free during the Experimental release period: you will still incur charges for other GCP products usage, such as storage.\n",
-        "\n",
-        "The projects need to be added to the allowlist in order to deploy PyTorch models using Vertex AI Prediction pre-built PyTorch images. If you are interested in the feature, please send an email to vertexai-prediction-preview-feedback@google.com to provide your project numbers OR project ids."
+        "**Kindly reach out to Vertex AI before you run any scale tests or you have any questions.**\n"
       ]
     },
     {

notebooks/community/CODEOWNERS

@@ -33,6 +33,7 @@
 /notebooks/community/cohere/cohere_embedding_with_matching_engine.ipynb @stewart-co
 /notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb @fhirschmann
 /notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb @fhirschmann
+/notebooks/community/ml_ops/stage3/get_started_with_dataflow_flex_template_component.ipynb @wintwoo
 /notebooks/community/vertex-ai-samples/notebooks/community/model_registry/vertex_ai_model_registry_bqml_custom_model_versioning.ipynb @inardini
 /notebooks/community/vertex-ai-samples/notebooks/community/model_registry/vertex_ai_model_registry_automl_model_versioning.ipynb @inardini
 /notebooks/community/vizier/conversions_vertex_vizier_and_open_source_vizier.ipynb @halio-g
@@ -40,4 +41,24 @@
 /notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_anomaly_detection.ipynb @inardini
 /notebooks/community/pipelines/google_cloud_pipeline_components_cloud_natural_language_pipeline.ipynb @Narwhalprime
 /notebooks/community/pipelines/google_cloud_pipeline_components_ready_to_go_text_classification_pipeline.ipynb @Narwhalprime
-
+/notebooks/community/feature_store/get_started_vertex_feature_store.ipynb @junkourata
+/notebooks/community/model_garden/model_garden_huggingface_local_inference.ipynb @dstnluong-google
+/notebooks/community/model_garden/model_garden_tfvision_image_classification.ipynb @genquan9
+/notebooks/community/model_garden/model_garden_tfvision_image_object_detection.ipynb @genquan9
+/notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb @genquan9
+/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_blip_image_captioning.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_blip_vqa.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_vilt_vqa.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_vit_gpt2_image_captioning.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_clip.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_owlvit.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_layoutml_document_qa.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_blip2.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_detectron2.ipynb @lavraicse
+/notebooks/community/generative_ai/text_embedding_api_semantic_search_with_scann.ipynb @henrytansetiawan
+/notebooks/community/bigquery_ml_inference/bq_ml_with_vision_translation_nlp.ipynb @deaconsmith
+/notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb @genquan9

notebooks/community/bigquery_ml/README.md

@@ -0,0 +1,19 @@
+
+[Unstructured data analytics with BigQuery ML and Vertex AI pre-trained models](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/bigquery_ml/bq_ml_with_vision_translation_nlp.ipynb)
+
+```
+Learn how to analyze unstructured data within BigQuery using BigQuery's inference engine. You will use BigQuery ML to connect to three pretrained Vertex AI APIs - Vision API, Translation API and Natural Language Processing API.
+
+The steps performed include:
+
+- Define pre-trained models for Vision AI, Translation AI and NLP AI in BigQuery ML
+- Call the Vision API (`ML.ANNOTATE_IMAGE`) to detect text in images stored in Cloud Storage
+  You will need to create an object table in BigQuery to do this
+- Call the Translation API (`ML.TRANSLATE`) to detect the language of text, and translate non-English movie titles to English
+- Call the Natural Language API (`ML.UNDERSTAND_TEXT`) to run sentiment analysis over movie reviews stored in BigQuery
+
+```
+
+   Check out the [blog for this notebook](https://cloud.google.com/blog/products/data-analytics/how-simplify-unstructured-data-analytics-using-bigquery-ml-and-vertex-ai).
+   Learn more about [BigQuery ML inference engine](https://cloud.google.com/bigquery/docs/reference/standard-sql/inference-overview).
+

notebooks/community/generative_ai/text_embedding_api_semantic_search_with_scann.ipynb

@@ -0,0 +1,373 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "KSP1duKDeaDR",
+      "metadata": {
+        "id": "KSP1duKDeaDR"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "67b2c5cc-8fc6-4082-9052-69fa0377d770",
+      "metadata": {
+        "id": "67b2c5cc-8fc6-4082-9052-69fa0377d770"
+      },
+      "source": [
+        "# Semantic Search using Embeddings\n",
+        "\n",
+        "Semantic search is a type of search that uses the meaning of words and phrases to find relevant results.\n",
+        "\n",
+        "In this tutorial, we will demonstrate how to do semantic search with embeddings generated from the news text and using [Google ScaNN: Efficient Vector Similarity Search](https://ai.googleblog.com/2020/07/announcing-scann-efficient-vector.html) to retrieve the most relevant news semantically.\n",
+        "\n",
+        "## Pre-requisites:\n",
+        "- Vertex LLM SDK\n",
+        "- ScaNN [github](https://github.com/google-research/google-research/tree/master/scann)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "FyyMdUeAJIVv",
+      "metadata": {
+        "id": "FyyMdUeAJIVv"
+      },
+      "source": [
+        "## Install Vertex LLM SDK\n",
+        "\n",
+        "DISCLAIMER: Text Embedding API is now in Experimental Preview. This release focuses on validating model prototypes and these models are not guaranteed to be released. Use of Text Embedding API is governed by the Google Cloud Terms of Service, the Pre-GA Offerings Terms of the GCP Service Specific Terms. The Acceptance Use Policy, and the Generative AI Prohibited Use Policy. Vertex Text Embedding API’s features may be unstable, change in backward-incompatible ways, and are not guaranteed to be released. There are no SLAs provided and no technical support obligations. GCP’s Cloud Data Processing Addendum does not apply to Pre-GA Offerings and customers should not use Text Embedding API to process personal data or other data subject to legal or regulatory compliance requirements. See description of launch stage for details.\n",
+        "\n",
+        "The information in this documentation is provided to the customer on an “as is” and “with all faults” basis without any warranty of any kind, either express or implied. Google does not warrant or guarantee the correctness, accuracy or reliability of the information in here. In no event will Google or its affiliates or licensors be liable for any damage or harm to customers from customer’s use of these materials."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "h6KaE3XRJdxc",
+      "metadata": {
+        "id": "h6KaE3XRJdxc"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "snBUuUamoJPz",
+      "metadata": {
+        "id": "snBUuUamoJPz"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install google-cloud-aiplatform>=1.25 \"shapely<2.0.0\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "zgVQcE0ewO8W",
+      "metadata": {
+        "id": "zgVQcE0ewO8W"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"cloud-nl-llm-embedding\"  # @param {type:\"string\"}\n",
+        "LOCATION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "import vertexai\n",
+        "\n",
+        "vertexai.init(project=PROJECT_ID, location=LOCATION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "4xFzXmPbY7FC",
+      "metadata": {
+        "id": "4xFzXmPbY7FC"
+      },
+      "source": [
+        "**Attention**: you would need to restart runtime so that the right package is installed."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "xnfG88OPZI18",
+      "metadata": {
+        "id": "xnfG88OPZI18"
+      },
+      "source": [
+        "## Import TextEmbeddingModel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "1e6e1b98-a632-44a2-afb8-fc212018ef4f",
+      "metadata": {
+        "id": "1e6e1b98-a632-44a2-afb8-fc212018ef4f"
+      },
+      "outputs": [],
+      "source": [
+        "from vertexai.preview.language_models import TextEmbeddingModel\n",
+        "\n",
+        "model = TextEmbeddingModel.from_pretrained(\"textembedding-gecko@001\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "1suA-1HuaGj6",
+      "metadata": {
+        "id": "1suA-1HuaGj6"
+      },
+      "source": [
+        "## Install ScaNN Package"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "770255d3-54dd-48c8-bbdd-fbc0be41f085",
+      "metadata": {
+        "id": "770255d3-54dd-48c8-bbdd-fbc0be41f085"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install scann"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "dae340cb-0583-4e7e-a562-6817ee4d7f6d",
+      "metadata": {
+        "id": "dae340cb-0583-4e7e-a562-6817ee4d7f6d"
+      },
+      "source": [
+        "## Imports packages"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "412d00f1-08db-4880-8ced-52a9583757b8",
+      "metadata": {
+        "id": "412d00f1-08db-4880-8ced-52a9583757b8"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "import time\n",
+        "\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import scann"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f50f22f3-ec85-463e-b6fe-5c8e6b80b07b",
+      "metadata": {
+        "id": "f50f22f3-ec85-463e-b6fe-5c8e6b80b07b"
+      },
+      "source": [
+        "## Create Embedding Dataset.\n",
+        "\n",
+        "The dataset is solely to demonstrate the use of the Text Embedding API with a vector database. It is not intended to be used for any other purpose, such as evaluating models. The dataset is small and does not represent a comprehensive sample of all possible text."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "2OUg-Qf8iFta",
+      "metadata": {
+        "id": "2OUg-Qf8iFta"
+      },
+      "outputs": [],
+      "source": [
+        "!gsutil cp gs://cloud-samples-data/vertex-ai/dataset-management/datasets/bert_finetuning/wide_and_deep_trainer_container_tests_input.jsonl ."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "BNPapKXviHlE",
+      "metadata": {
+        "id": "BNPapKXviHlE"
+      },
+      "outputs": [],
+      "source": [
+        "records = []\n",
+        "with open(\"wide_and_deep_trainer_container_tests_input.jsonl\") as f:\n",
+        "    for line in f:\n",
+        "        record = json.loads(line)\n",
+        "        records.append(record)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "Z1Y9Bx2miJba",
+      "metadata": {
+        "id": "Z1Y9Bx2miJba"
+      },
+      "outputs": [],
+      "source": [
+        "# Peek at the data.\n",
+        "df = pd.DataFrame(records)\n",
+        "df.head(50)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "1v7zUwoWiPl-",
+      "metadata": {
+        "id": "1v7zUwoWiPl-"
+      },
+      "outputs": [],
+      "source": [
+        "def get_embedding(text):\n",
+        "    get_embedding.counter += 1\n",
+        "    try:\n",
+        "        if get_embedding.counter % 100 == 0:\n",
+        "            time.sleep(3)\n",
+        "        return model.get_embeddings([text])[0].values\n",
+        "    except:\n",
+        "        return []\n",
+        "\n",
+        "\n",
+        "get_embedding.counter = 0\n",
+        "\n",
+        "# This may take several minutes to complete.\n",
+        "df[\"embedding\"] = df[\"textContent\"].apply(lambda x: get_embedding(x))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ba4f49b6-65e1-49ea-988b-c4e195219deb",
+      "metadata": {
+        "id": "ba4f49b6-65e1-49ea-988b-c4e195219deb"
+      },
+      "source": [
+        "## Create an Index"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "245bc8cd-038b-484a-acb2-3a705d4cc4cf",
+      "metadata": {
+        "id": "245bc8cd-038b-484a-acb2-3a705d4cc4cf"
+      },
+      "outputs": [],
+      "source": [
+        "record_count = len(records)\n",
+        "dataset = np.empty((record_count, 768))\n",
+        "for i in range(record_count):\n",
+        "    dataset[i] = df.embedding[i]\n",
+        "\n",
+        "normalized_dataset = dataset / np.linalg.norm(dataset, axis=1)[:, np.newaxis]\n",
+        "# configure ScaNN as a tree - asymmetric hash hybrid with reordering\n",
+        "# anisotropic quantization as described in the paper; see README\n",
+        "\n",
+        "# use scann.scann_ops.build() to instead create a TensorFlow-compatible searcher\n",
+        "searcher = (\n",
+        "    scann.scann_ops_pybind.builder(normalized_dataset, 10, \"dot_product\")\n",
+        "    .tree(\n",
+        "        num_leaves=record_count,\n",
+        "        num_leaves_to_search=record_count,\n",
+        "        training_sample_size=record_count,\n",
+        "    )\n",
+        "    .score_ah(2, anisotropic_quantization_threshold=0.2)\n",
+        "    .reorder(100)\n",
+        "    .build()\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "9f1689eb-c27c-4566-afc7-7fbc55552aad",
+      "metadata": {
+        "id": "9f1689eb-c27c-4566-afc7-7fbc55552aad"
+      },
+      "source": [
+        "## Queries the Index"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "494079df-d8f6-4a6a-b26b-0b0477791adc",
+      "metadata": {
+        "id": "494079df-d8f6-4a6a-b26b-0b0477791adc"
+      },
+      "outputs": [],
+      "source": [
+        "def search(query):\n",
+        "    start = time.time()\n",
+        "    query = model.get_embeddings([query])[0].values\n",
+        "    neighbors, distances = searcher.search(query, final_num_neighbors=3)\n",
+        "    end = time.time()\n",
+        "\n",
+        "    for id, dist in zip(neighbors, distances):\n",
+        "        print(f\"[docid:{id}] [{dist}] -- {df.textContent[int(id)][:125]}...\")\n",
+        "    print(\"Latency (ms):\", 1000 * (end - start))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "50497681-6112-4147-a13e-afedb72b54f5",
+      "metadata": {
+        "id": "50497681-6112-4147-a13e-afedb72b54f5"
+      },
+      "outputs": [],
+      "source": [
+        "search(\"tell me about shark or animal\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "c814f835-3e2a-4366-a334-ccc636f00b83",
+      "metadata": {
+        "id": "c814f835-3e2a-4366-a334-ccc636f00b83"
+      },
+      "outputs": [],
+      "source": [
+        "search(\"tell me about an important moment or event in your life\")"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "text_embedding_api_semantic_search_with_scann.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/matching_engine/matching_engine_for_indexing.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2023 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -24,6 +24,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "JAPoU8Sm5E6e"
@@ -32,20 +33,28 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/matching_engine/matching_engine_for_indexing.ipynb\">\n",
-        "      Run in Google Cloud Notebooks\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/matching_engine/matching_engine_for_indexing.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\">\n",
+        "      Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/matching_engine/matching_engine_for_indexing.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/matching_engine/matching_engine_for_indexing.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/matching_engine/matching_engine_for_indexing.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>                                                                                               \n",
         "</table>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "tvgnzT1CKxrO"
@@ -53,25 +62,49 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This example demonstrates how to use the GCP ANN Service. It is a high scale, low latency solution, to find similar vectors (or more specifically \"embeddings\") for a large corpus. Moreover, it is a fully managed offering, further reducing operational overhead. It is built upon [Approximate Nearest Neighbor (ANN) technology](https://ai.googleblog.com/2020/07/announcing-scann-efficient-vector.html) developed by Google Research.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the [GloVe dataset](https://nlp.stanford.edu/projects/glove/).\n",
-        "\n",
+        "This example demonstrates how to use Vertex AI Matching Engine. It is a high scale, low latency solution, to find similar vectors (or more specifically \"embeddings\") for a large corpus. Moreover, it is a fully managed offering, further reducing operational overhead. It is built upon [Approximate Nearest Neighbor (ANN) technology](https://ai.googleblog.com/2020/07/announcing-scann-efficient-vector.html) developed by Google Research."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "56e5f9699c6c"
+      },
+      "source": [
         "### Objective\n",
         "\n",
         "In this notebook, you will learn how to create Approximate Nearest Neighbor (ANN) Index, query against indexes, and validate the performance of the index. \n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "* Create ANN Index and Brute Force Index\n",
+        "* Create a Vertex AI Matching Engine Index and Brute Force Index\n",
         "* Create an IndexEndpoint with VPC Network\n",
-        "* Deploy ANN Index and Brute Force Index\n",
-        "* Perform online query\n",
-        "* Compute recall\n",
-        "\n",
+        "* Deploy a Vertex AI Matching Engine Index and Brute Force Index\n",
+        "* Perform online queries\n",
+        "* Submit batch queries\n",
+        "* Compute recall metric"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0aaef374550b"
+      },
+      "source": [
+        "### Dataset\n",
         "\n",
+        "The dataset used for this tutorial is the [GloVe dataset](https://nlp.stanford.edu/projects/glove/)."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5e2eba58ad71"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -87,6 +120,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "S5zc4kbEiYCm"
@@ -94,79 +128,47 @@
       "source": [
         "## Before you begin\n",
         "\n",
-        "* **Prepare a VPC network**.  To reduce any network overhead that might lead to unnecessary increase in overhead latency, it is best to call the ANN endpoints from your VPC via a direct [VPC Peering](https://cloud.google.com/vertex-ai/docs/general/vpc-peering) connection. The following section describes how to setup a VPC Peering connection if you don't have one. This is a one-time initial setup task. You can also reuse existing VPC network and skip this section.\n",
-        "* **WARNING:** The match service gRPC API (to create online queries against your deployed index) has to be executed in a Google Cloud Notebook instance that is created with the following requirements:\n",
-        "  * **In the same region as where your ANN service is deployed** (for example, if you set `REGION = \"us-central1\"` as same as the tutorial, the notebook instance has to be in `us-central1`).\n",
-        "  * **Make sure you select the VPC network you created for ANN service** (instead of using the \"default\" one). That is, you will have to create the VPC network below and then create a new notebook instance that uses that VPC.  \n",
-        "  * If you run it in the colab or a Google Cloud Notebook instance in a different VPC network or region, the gRPC API will fail to peer the network (InactiveRPCError)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "lW2LneA5mmmP"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"<your_project_id>\"  # @param {type:\"string\"}\n",
-        "NETWORK_NAME = \"ucaip-haystack-vpc-network\"  # @param {type:\"string\"}\n",
-        "PEERING_RANGE_NAME = \"ucaip-haystack-range\"\n",
+        "### Set up your Google Cloud project\n",
         "\n",
-        "# Create a VPC network\n",
-        "! gcloud compute networks create {NETWORK_NAME} --bgp-routing-mode=regional --subnet-mode=auto --project={PROJECT_ID}\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "# Add necessary firewall rules\n",
-        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-icmp --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow icmp\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-internal --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow all --source-ranges 10.128.0.0/9\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-rdp --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow tcp:3389\n",
+        "3. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
         "\n",
-        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-ssh --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow tcp:22\n",
-        "\n",
-        "# Reserve IP range\n",
-        "! gcloud compute addresses create {PEERING_RANGE_NAME} --global --prefix-length=16 --network={NETWORK_NAME} --purpose=VPC_PEERING --project={PROJECT_ID} --description=\"peering range for uCAIP Haystack.\"\n",
-        "\n",
-        "# Set up peering with service networking\n",
-        "! gcloud services vpc-peerings connect --service=servicenetworking.googleapis.com --network={NETWORK_NAME} --ranges={PEERING_RANGE_NAME} --project={PROJECT_ID}"
+        "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk)."
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "d3uj8x73nDX_"
-      },
-      "source": [
-        "* Authentication: `$ gcloud auth login` rerun this in Google Cloud Notebook terminal when you are logged out and need the credential again."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "i7EUnXsZhAGF"
+        "id": "4700b0e39c5d"
       },
       "source": [
         "### Installation\n",
         "\n",
-        "Download and install the latest (preview) version of the Vertex SDK for Python."
+        "Download and install the latest version of the Vertex AI SDK for Python."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "wyy5Lbnzg5fi"
+        "id": "014470c6a8de"
       },
       "outputs": [],
       "source": [
-        "! pip install -U git+https://github.com/googleapis/python-aiplatform.git@main-test --user"
+        "! pip install -U git+https://github.com/googleapis/python-aiplatform.git@main --user"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "irSMQn6gZ19l"
+        "id": "cf00462144f7"
       },
       "source": [
         "Install the `h5py` to prepare sample dataset, and the `grpcio-tools` for querying against the index. "
@@ -176,11 +178,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "-h5sqwOEZ5Yq"
+        "id": "3f3e45e5a1d1"
       },
       "outputs": [],
       "source": [
-        "! pip install -U grpcio-tools --user\n",
+        "! pip install protobuf==3.20.*\n",
+        "! pip install -U google-api-python-client==1.8.0 --user\n",
+        "! pip install -U grpcio-tools==1.47.0 --user\n",
+        "! pip install -U grpcio==1.47.0 --user\n",
+        "! pip install -U grpcio-status==1.47.0 --user\n",
         "! pip install -U h5py --user"
       ]
     },
@@ -199,7 +205,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "EzrelQZ22IZj"
+        "id": "aa1d87bdc90b"
       },
       "outputs": [],
       "source": [
@@ -215,79 +221,216 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "BF1j6f9HApxa"
+        "id": "249da91c1011"
       },
       "source": [
-        "### Set up your Google Cloud project\n",
+        "### Set your project ID\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager).\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API and Compute Engine API, and Service Networking API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,servicenetworking.googleapis.com).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "oM1iC_MfAts1"
+        "id": "10e0d2ee8c45"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
         "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output=!gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "qJYoRfYng0XZ"
+        "id": "3fbfae3ff12a"
       },
       "source": [
-        "Otherwise, set your project ID here."
+        "### Set the region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations).\n",
+        "* **WARNING:** \n",
+        "    *  **Make sure to [choose a region where Vertex AI services are available](https://cloud.google.com/vertex-ai/docs/general/locations#available_regions).**\n",
+        "    *  **If you use Vertex Workbench, the Notebook instance needs to be in the same region where your Vertex AI Matching Engine is deployed.** (for example, if you set `REGION = \"us-central1\"` as same as the tutorial, the notebook instance has to be in `us-central1`)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "riG_qUokg0XZ"
+        "id": "71c3fd82024e"
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"<your_project_id>\"  # @param {type:\"string\"}"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}\n",
+        "\n",
+        "# Set the regions\n",
+        "! gcloud config set ai_platform/region {REGION}"
       ]
     },
     {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "60c5a0f69ad8"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d118c95af93f"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3035286fcdda"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "455882ec0f11"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5097f3233d53"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2b88e46ac2c8"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fcdbb8929927"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7c6eef70dfdb"
+      },
+      "source": [
+        "### Prepare a VPC network\n",
+        "\n",
+        "To reduce any network overhead that might lead to unnecessary increase in overhead latency, it is best to call the Vertex AI Matching Engine endpoints from your VPC via a direct [VPC Peering](https://cloud.google.com/vertex-ai/docs/general/vpc-peering) connection. The following section describes how to setup a VPC Peering connection if you don't have one. This is a one-time initial setup task. You can also reuse existing VPC network and skip this section.\n",
+        "\n",
+        "* **WARNING:** The match service gRPC API (to create online queries against your deployed index) has to be executed in a Google Cloud Notebook instance that is created with the following requirements:\n",
+        "    * **Make sure you select the VPC network you created for Vertex AI Matching Engine service** (instead of using the \"default\" one). That is, you will have to create the VPC network below and then create a new notebook instance that uses that VPC.  \n",
+        "    * If you run it in the colab or a Google Cloud Notebook instance in a different VPC network or region, the gRPC API will fail to peer the network (InactiveRPCError)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ab38a8cc634c"
+      },
+      "outputs": [],
+      "source": [
+        "NETWORK_NAME = \"ucaip-haystack-vpc-network\"  # @param {type:\"string\"}\n",
+        "PEERING_RANGE_NAME = \"ucaip-haystack-range\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ec6bf3199835"
+      },
+      "outputs": [],
+      "source": [
+        "# Create a VPC network\n",
+        "! gcloud compute networks create {NETWORK_NAME} --bgp-routing-mode=regional --subnet-mode=auto --project={PROJECT_ID}\n",
+        "\n",
+        "# Add necessary firewall rules\n",
+        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-icmp --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow icmp\n",
+        "\n",
+        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-internal --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow all --source-ranges 10.128.0.0/9\n",
+        "\n",
+        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-rdp --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow tcp:3389\n",
+        "\n",
+        "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-ssh --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow tcp:22\n",
+        "\n",
+        "# Reserve IP range\n",
+        "! gcloud compute addresses create {PEERING_RANGE_NAME} --global --prefix-length=16 --network={NETWORK_NAME} --purpose=VPC_PEERING --project={PROJECT_ID} --description=\"peering range for uCAIP Haystack.\""
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ddbace09fe81"
+      },
+      "source": [
+        "Create the VPC Peering. If you are running this from Vertex AI Workbench it is possible you might need your notebook's instance service or user account to have the Service Networking Admin Role"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d329aa3c54d3"
+      },
+      "outputs": [],
+      "source": [
+        "# Set up peering with service networking\n",
+        "! gcloud services vpc-peerings connect --service=servicenetworking.googleapis.com --network={NETWORK_NAME} --ranges={PEERING_RANGE_NAME} --project={PROJECT_ID}"
+      ]
+    },
+    {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "zgPO1eR3CYjk"
@@ -297,13 +440,11 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets. Set the name of your Cloud Storage bucket below. It must be unique across all\n",
         "Cloud Storage buckets.\n",
         "\n",
-        "You may also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook. Make sure to [choose a region where Vertex AI services are\n",
-        "available](https://cloud.google.com/vertex-ai/docs/general/locations#available_regions). You may\n",
-        "not use a Multi-Regional Storage bucket for training with Vertex AI."
+        "* **WARNING:** \n",
+        "    * **You may not use a Multi-Regional Storage bucket for training with Vertex AI.**"
       ]
     },
     {
@@ -314,8 +455,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"us-central1\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"gs://[your-bucket-name-unique]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -328,10 +468,14 @@
       "source": [
         "from datetime import datetime\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
+        "UUID = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
         "\n",
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if (\n",
+        "    BUCKET_NAME == \"\"\n",
+        "    or BUCKET_NAME is None\n",
+        "    or BUCKET_NAME == \"gs://[your-bucket-name-unique]\"\n",
+        "):\n",
+        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + UUID"
       ]
     },
     {
@@ -351,7 +495,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_NAME"
       ]
     },
     {
@@ -416,10 +560,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"\n",
         "ENDPOINT = \"{}-aiplatform.googleapis.com\".format(REGION)\n",
-        "NETWORK_NAME = \"ucaip-haystack-vpc-network\"  # @param {type:\"string\"}\n",
-        "\n",
         "\n",
         "AUTH_TOKEN = !gcloud auth print-access-token\n",
         "PROJECT_NUMBER = !gcloud projects list --filter=\"PROJECT_ID:'{PROJECT_ID}'\" --format='value(PROJECT_NUMBER)'\n",
@@ -429,10 +570,7 @@
         "\n",
         "print(\"ENDPOINT: {}\".format(ENDPOINT))\n",
         "print(\"PROJECT_ID: {}\".format(PROJECT_ID))\n",
-        "print(\"REGION: {}\".format(REGION))\n",
-        "\n",
-        "!gcloud config set project {PROJECT_ID}\n",
-        "!gcloud config set ai_platform/region {REGION}"
+        "print(\"REGION: {}\".format(REGION))"
       ]
     },
     {
@@ -523,12 +661,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "QuVl8DrWG8NS"
       },
       "source": [
-        "Upload the training data to GCS."
+        "Upload the training data to Google Cloud Storage"
       ]
     },
     {
@@ -539,9 +678,9 @@
       },
       "outputs": [],
       "source": [
-        "# NOTE: Everything in this GCS DIR will be DELETED before uploading the data.\n",
+        "# NOTE: Everything in this Google Cloud Storage directory will be DELETED before uploading the data\n",
         "\n",
-        "! gsutil rm -rf {BUCKET_NAME}/*"
+        "! gsutil rm -raf {BUCKET_NAME}/** 2> /dev/null || true"
       ]
     },
     {
@@ -567,21 +706,23 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "mglUPwHpJH98"
       },
       "source": [
-        "## Create Indexes\n"
+        "## Create the indexes\n"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "qhIBCQ7dDSbW"
       },
       "source": [
-        "### Create ANN Index (for Production Usage)"
+        "### Create Vertex AI Matching Engine index (for production usage)"
       ]
     },
     {
@@ -597,6 +738,16 @@
         ")"
       ]
     },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "14e1ed031d66"
+      },
+      "source": [
+        "Set constants"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -611,14 +762,15 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "svLYiDf0OD2G"
       },
       "source": [
-        "Create the ANN index configuration:\n",
+        "#### Create the Vertex AI Matching Engine index configuration\n",
         "\n",
-        "Please read the documentation to understand the various configuration parameters that can be used to tune the index\n"
+        "Please read the [documentation](https://cloud.google.com/vertex-ai/docs/matching-engine/configuring-indexes) to understand the various configuration parameters that can be used to tune the index"
       ]
     },
     {
@@ -656,9 +808,9 @@
         "    }\n",
         ")\n",
         "\n",
-        "ann_index = {\n",
+        "matching_engine_index = {\n",
         "    \"display_name\": DISPLAY_NAME,\n",
-        "    \"description\": \"Glove 100 ANN index\",\n",
+        "    \"description\": \"Glove 100 Vertex AI Matching Engine Index\",\n",
         "    \"metadata\": struct_pb2.Value(struct_value=metadata),\n",
         "}"
       ]
@@ -671,7 +823,9 @@
       },
       "outputs": [],
       "source": [
-        "ann_index = index_client.create_index(parent=PARENT, index=ann_index)"
+        "matching_engine_index = index_client.create_index(\n",
+        "    parent=PARENT, index=matching_engine_index\n",
+        ")"
       ]
     },
     {
@@ -686,7 +840,7 @@
         "# This will take ~45 min.\n",
         "\n",
         "while True:\n",
-        "    if ann_index.done():\n",
+        "    if matching_engine_index.done():\n",
         "        break\n",
         "    print(\"Poll the operation to create index...\")\n",
         "    time.sleep(60)"
@@ -700,17 +854,18 @@
       },
       "outputs": [],
       "source": [
-        "INDEX_RESOURCE_NAME = ann_index.result().name\n",
+        "INDEX_RESOURCE_NAME = matching_engine_index.result().name\n",
         "INDEX_RESOURCE_NAME"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "kSsqZuyoA1SG"
       },
       "source": [
-        "### Create Brute Force Index (for Ground Truth)\n",
+        "### Create brute force index (for ground truth)\n",
         "\n",
         "The brute force index uses a naive brute force method to find the nearest neighbors. This method is not fast or efficient. Hence brute force indices are not recommended for production usage. They are to be used to find the \"ground truth\" set of neighbors, so that the \"ground truth\" set can be used to measure recall of the indices being tuned for production usage. To ensure an apples to apples comparison, the `distanceMeasureType` and `featureNormType`, `dimensions` of the brute force index should match those of the production indices being tuned.\n",
         "\n",
@@ -725,8 +880,6 @@
       },
       "outputs": [],
       "source": [
-        "from google.protobuf import *\n",
-        "\n",
         "algorithmConfig = struct_pb2.Struct(\n",
         "    fields={\"bruteForceConfig\": struct_pb2.Value(struct_value=struct_pb2.Struct())}\n",
         ")\n",
@@ -796,12 +949,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "mglUPwHpJH98"
       },
       "source": [
-        "## Update Indexes\n",
+        "## Update the indexes\n",
         "\n",
         "Create incremental data file.\n"
       ]
@@ -863,10 +1017,10 @@
         "    }\n",
         ")\n",
         "\n",
-        "ann_index = {\n",
+        "matching_engine_index = {\n",
         "    \"name\": INDEX_RESOURCE_NAME,\n",
         "    \"display_name\": DISPLAY_NAME,\n",
-        "    \"description\": \"Glove 100 ANN index\",\n",
+        "    \"description\": \"Glove 100 Vertex AI Matching Engine Index\",\n",
         "    \"metadata\": struct_pb2.Value(struct_value=metadata),\n",
         "}"
       ]
@@ -879,7 +1033,7 @@
       },
       "outputs": [],
       "source": [
-        "ann_index = index_client.update_index(index=ann_index)"
+        "matching_engine_index = index_client.update_index(index=matching_engine_index)"
       ]
     },
     {
@@ -894,7 +1048,7 @@
         "# This will take ~45 min.\n",
         "\n",
         "while True:\n",
-        "    if ann_index.done():\n",
+        "    if matching_engine_index.done():\n",
         "        break\n",
         "    print(\"Poll the operation to update index...\")\n",
         "    time.sleep(60)"
@@ -908,17 +1062,18 @@
       },
       "outputs": [],
       "source": [
-        "INDEX_RESOURCE_NAME = ann_index.result().name\n",
+        "INDEX_RESOURCE_NAME = matching_engine_index.result().name\n",
         "INDEX_RESOURCE_NAME"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "qV2xjAnDDObD"
       },
       "source": [
-        "## Create an IndexEndpoint with VPC Network"
+        "## Create an index endpoint with VPC network"
       ]
     },
     {
@@ -997,21 +1152,23 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "np2cgVuuIe9k"
       },
       "source": [
-        "## Deploy Indexes"
+        "## Deploy the indexes"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "8Ew1UgcIIiJG"
       },
       "source": [
-        "### Deploy ANN Index"
+        "### Deploy a Vertex AI Matching Engine index"
       ]
     },
     {
@@ -1022,7 +1179,7 @@
       },
       "outputs": [],
       "source": [
-        "DEPLOYED_INDEX_ID = \"ann_glove_deployed\""
+        "DEPLOYED_INDEX_ID = \"matching_engine_glove_deployed\""
       ]
     },
     {
@@ -1033,13 +1190,23 @@
       },
       "outputs": [],
       "source": [
-        "deploy_ann_index = {\n",
+        "deploy_matching_engine_index = {\n",
         "    \"id\": DEPLOYED_INDEX_ID,\n",
         "    \"display_name\": DEPLOYED_INDEX_ID,\n",
         "    \"index\": INDEX_RESOURCE_NAME,\n",
         "}"
       ]
     },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cb6d956d7419"
+      },
+      "source": [
+        "If errors occur with the next command wait some minutes for the index endpoint to be created and retry."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1049,7 +1216,7 @@
       "outputs": [],
       "source": [
         "r = index_endpoint_client.deploy_index(\n",
-        "    index_endpoint=INDEX_ENDPOINT_NAME, deployed_index=deploy_ann_index\n",
+        "    index_endpoint=INDEX_ENDPOINT_NAME, deployed_index=deploy_matching_engine_index\n",
         ")"
       ]
     },
@@ -1082,12 +1249,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "RNZnXmO5AhDO"
       },
       "source": [
-        "### Deploy Brute Force Index"
+        "### Deploy brute force index"
       ]
     },
     {
@@ -1158,12 +1326,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6LCGvBNvBd8D"
       },
       "source": [
-        "## Create Online Queries\n",
+        "## Create online queries\n",
         "\n",
         "After you built your indexes, you may query against the deployed index through the online querying gRPC API (Match service) within the virtual machine instances from the same region (for example 'us-central1' in this tutorial).  \n",
         "\n",
@@ -1178,7 +1347,15 @@
         "\n",
         "* Compile the protocal buffer (see below)\n",
         "* Obtain the index endpoint\n",
-        "* Use a code-generated stub to make the call, passing the parameter values"
+        "* Use a code-generated stub to make the call, passing the parameter values\n",
+        "\n",
+        "### Troubleshooting connectivity issues\n",
+        "\n",
+        "In case you have connectivity errors please perform the following:\n",
+        "\n",
+        "* Verify that the index endpoint, index, and VPC are all in the same Google Cloud project\n",
+        "* Verify that the index endpoint, index, and VPC are all in the same region and it is a valid (e.g. us-central1)\n",
+        "* Verify the Network does not have a firewall rule which denies all egress connections. Else, disable this rule or overwrite it with another rule that allows connection to the index endpoint IP"
       ]
     },
     {
@@ -1351,12 +1528,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "8wXTSgz1Bl0x"
       },
       "source": [
-        "Obtain the Private Endpoint: "
+        "Obtain the private endpoint: "
       ]
     },
     {
@@ -1521,12 +1699,13 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "_mNwdU9_B_Ez"
       },
       "source": [
-        "### Batch Query\n",
+        "## Submit a batch query\n",
         "\n",
         "You can run multiple queries in a single RPC call using the BatchMatch API:"
       ]
@@ -1764,18 +1943,20 @@
         "]\n",
         "\n",
         "batch_request = match_service_pb2.BatchMatchRequest()\n",
-        "batch_request_ann = match_service_pb2.BatchMatchRequest.BatchMatchRequestPerIndex()\n",
+        "batch_request_matching_engine = (\n",
+        "    match_service_pb2.BatchMatchRequest.BatchMatchRequestPerIndex()\n",
+        ")\n",
         "batch_request_brute_force = (\n",
         "    match_service_pb2.BatchMatchRequest.BatchMatchRequestPerIndex()\n",
         ")\n",
-        "batch_request_ann.deployed_index_id = DEPLOYED_INDEX_ID\n",
+        "batch_request_matching_engine.deployed_index_id = DEPLOYED_INDEX_ID\n",
         "batch_request_brute_force.deployed_index_id = DEPLOYED_BRUTE_FORCE_INDEX_ID\n",
         "for query in queries:\n",
-        "    batch_request_ann.requests.append(get_request(query, DEPLOYED_INDEX_ID))\n",
+        "    batch_request_matching_engine.requests.append(get_request(query, DEPLOYED_INDEX_ID))\n",
         "    batch_request_brute_force.requests.append(\n",
         "        get_request(query, DEPLOYED_BRUTE_FORCE_INDEX_ID)\n",
         "    )\n",
-        "batch_request.requests.append(batch_request_ann)\n",
+        "batch_request.requests.append(batch_request_matching_engine)\n",
         "batch_request.requests.append(batch_request_brute_force)\n",
         "\n",
         "response = stub.BatchMatch(batch_request)\n",
@@ -1783,14 +1964,15 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "_mNwdU9_B_Ez"
       },
       "source": [
-        "### Compute Recall\n",
+        "### Compute the recall metric\n",
         "\n",
-        "Use deployed brute force Index as the ground truth to calculate the recall of ANN Index:"
+        "Use the deployed brute force index as the ground truth to calculate the recall of the Vertex AI Matching Engine index:"
       ]
     },
     {
@@ -1835,6 +2017,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "TpV-iwP9qw9c"
@@ -1844,7 +2027,18 @@
         "\n",
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
-        "You can also manually delete resources that you created by running the following code."
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial:"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "390c331dc7d9"
+      },
+      "source": [
+        "### Delete the Vertex AI Matching Engine resources"
       ]
     },
     {
@@ -1869,6 +2063,31 @@
       "source": [
         "index_endpoint_client.delete_index_endpoint(name=INDEX_ENDPOINT_NAME)"
       ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ff14a85c85fb"
+      },
+      "source": [
+        "### Delete the Google Cloud Storage bucket"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "68d4781faac4"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_NAME"
+      ]
     }
   ],
   "metadata": {

notebooks/community/ml_ops/stage3/get_started_vertex_pipelines_sklearn_with_prediction.ipynb

@@ -560,6 +560,30 @@
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage3/get_started_vertex_pipelines_xgboost_with_experiments.ipynb

@@ -557,6 +557,30 @@
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage3/get_started_vertex_pipelines_xgboost_with_prediction.ipynb

@@ -196,7 +196,7 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "! pip3 install {USER_FLAG} --upgrade --quiet google-cloud-aiplatform \\\n",
-        "                                             google-cloud-pipeline-components \\\n",
+        "                                             google-cloud-pipeline-components==1.0.25 \\\n",
         "                                             kfp "
       ]
     },
@@ -557,6 +557,30 @@
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage3/get_started_with_dataflow_flex_template_component.ipynb

@@ -0,0 +1,832 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title:generic,gcp"
+      },
+      "source": [
+        "# E2E ML on GCP: MLOps stage 3 : formalization: get started with the Dataflow Flex Template component\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
+        "<img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> \n",
+        "        Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>   \n",
+        "    \n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:mlops"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 3 : formalization: get started with the Dataflow Flex Template component."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:mlops,stage3,get_started_dataflow_pipeline_components"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` to execute `Dataflow` [Flex Template](https://cloud.google.com/dataflow/docs/guides/templates/using-flex-templates) jobs.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "- `Dataflow`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Defining a pipeline step to execute a Dataflow Flex Template job within a Vertex AI pipeline.\n",
+        "- Execute a Vertex AI pipeline."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:gsod,lrg"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the sample data from the [Apache Beam Mobile Gaming Pipeline example](https://beam.apache.org/get-started/mobile-gaming-example/)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "* Dataflow\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and [Dataflow pricing](https://cloud.google.com/dataflow/pricing)\n",
+        "and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "source": [
+        "## Installations\n",
+        "\n",
+        "Install the required packages for executing the notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --pre --upgrade google-cloud-pipeline-components $USER_FLAG -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "restart"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Dataflow API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "project_id"
+      },
+      "source": [
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "250cb8c648d5"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "timestamp"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "timestamp"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "927085b84a07"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "40ed98f5cc48"
+      },
+      "source": [
+        "#### If you are using Colab Notebooks, set the project using gcloud config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fde1a355f1e9"
+      },
+      "outputs": [],
+      "source": [
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        ! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aip\n",
+        "from google_cloud_pipeline_components.experimental.dataflow import \\\n",
+        "    DataflowFlexTemplateJobOp\n",
+        "from google_cloud_pipeline_components.v1.wait_gcp_resources import \\\n",
+        "    WaitGcpResourcesOp\n",
+        "from kfp import dsl\n",
+        "from kfp.v2 import compiler"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "writefile:wc.py"
+      },
+      "source": [
+        "### Prepare a Flex Template job to convert a CSV file to Parquet\n",
+        "\n",
+        "In this tutorial, you use the Google-provided [File Format Conversion template](https://cloud.google.com/dataflow/docs/guides/templates/provided/file-format-conversion) to convert a CSV file to Parquet format."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "writefile:requirements,wc"
+      },
+      "source": [
+        "#### Create the Avro schema file\n",
+        "\n",
+        "First, create an Avro schema file that describes the example data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "writefile:requirements,wc"
+      },
+      "outputs": [],
+      "source": [
+        "%%writefile gaming_schema.avsc\n",
+        "\n",
+        "{\n",
+        "   \"type\" : \"record\",\n",
+        "   \"name\" : \"user_score\",\n",
+        "   \"fields\" : [\n",
+        "      { \"name\" : \"user\" , \"type\" : \"string\" },\n",
+        "      { \"name\" : \"team\" , \"type\" : \"string\" },\n",
+        "      { \"name\" : \"score\" , \"type\" : \"int\" },\n",
+        "      { \"name\" : \"ts_epoch\" , \"type\" : \"long\" },\n",
+        "      { \"name\" : \"ts_str\" , \"type\" : \"string\" }\n",
+        "   ]\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "copy_to_gcs:wc"
+      },
+      "source": [
+        "#### Copy the Avro schema file to Cloud Storage\n",
+        "\n",
+        "Next, you copy the Avro schema file to your Cloud Storage bucket.\n",
+        "\n",
+        "Additional, you set the following:\n",
+        "\n",
+        "- The Cloud Storage location of the Flex Template definition file. In this tutorial, you use the location of the File Conversion template.\n",
+        "- A `Dict` containing the user parameters required by the Flex Template. These parameters include:\n",
+        "\n",
+        "    - `inputFileFormat`: The file format of the input files.\n",
+        "    - `outputFileFormat`: The file format of the output files.\n",
+        "    - `inputFileSpec`: The input filepattern to read from.\n",
+        "    - `outputBucket`: The Cloud Storage path to write the output files.\n",
+        "    - `schema`: The Cloud Storage path top the avro schema file used for the conversion.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copy_to_gcs:wc"
+      },
+      "outputs": [],
+      "source": [
+        "GCS_AVRO_SCHEMA = BUCKET_URI + \"/gaming_schema.avsc\"\n",
+        "! gsutil cp gaming_schema.avsc $GCS_AVRO_SCHEMA\n",
+        "\n",
+        "GCS_FLEX_TEMPLATE_PATH = \"gs://dataflow-templates/latest/flex/File_Format_Conversion\"\n",
+        "GCS_CONVERT_IN = \"gs://dataflow-samples/game/5000_gaming_data.csv\"\n",
+        "GCS_CONVERT_OUT = BUCKET_URI + \"/parquet_out/\"\n",
+        "\n",
+        "TEMPLATE_PARAMETERS = {\n",
+        "    \"inputFileFormat\": \"csv\",\n",
+        "    \"outputFileFormat\": \"parquet\",\n",
+        "    \"inputFileSpec\": GCS_CONVERT_IN,\n",
+        "    \"outputBucket\": GCS_CONVERT_OUT,\n",
+        "    \"schema\": GCS_AVRO_SCHEMA,\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataflow_pipeline:wc"
+      },
+      "source": [
+        "### Create and execute the pipeline job\n",
+        "\n",
+        "In this example, the `DataflowFlexTemplateJobOp` component takes the following parameters:\n",
+        "\n",
+        "- `project_id`: The project ID.\n",
+        "- `location`: The region.\n",
+        "- `container_spec_gcs_path`: The Cloud Storage path to a file that contains the Flex Template definition. This file contains a json serialized `ContainerSpec` as content.\n",
+        "- `temp_location`: The Cloud Storage path to use for temporary files.\n",
+        "- `parameters`: The parameters for the Flex Template.\n",
+        "\n",
+        "Learn more about [Google Cloud Pipeline Components for Dataflow](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-2.0.0b2/google_cloud_pipeline_components.experimental.dataflow.html)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataflow_pipeline:wc"
+      },
+      "outputs": [],
+      "source": [
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_file_conversion\".format(BUCKET_URI)\n",
+        "\n",
+        "\n",
+        "@dsl.pipeline(\n",
+        "    name=\"dataflow-file-conversion\", description=\"Dataflow file format conversion\"\n",
+        ")\n",
+        "def pipeline(\n",
+        "    project_id: str = PROJECT_ID,\n",
+        "    location: str = REGION,\n",
+        "    container_spec_gcs_path: str = GCS_FLEX_TEMPLATE_PATH,\n",
+        "    temp_location: str = PIPELINE_ROOT,\n",
+        "    parameters: dict = TEMPLATE_PARAMETERS,\n",
+        "):\n",
+        "    flex_template_op = DataflowFlexTemplateJobOp(\n",
+        "        project=project_id,\n",
+        "        location=location,\n",
+        "        container_spec_gcs_path=container_spec_gcs_path,\n",
+        "        temp_location=temp_location,\n",
+        "        parameters=parameters,\n",
+        "    )\n",
+        "\n",
+        "    _ = WaitGcpResourcesOp(gcp_resources=flex_template_op.outputs[\"gcp_resources\"])\n",
+        "\n",
+        "\n",
+        "compiler.Compiler().compile(\n",
+        "    pipeline_func=pipeline, package_path=\"dataflow_file_conversion.yaml\"\n",
+        ")\n",
+        "\n",
+        "pipeline = aip.PipelineJob(\n",
+        "    display_name=\"dataflow_file_conversion\",\n",
+        "    template_path=\"dataflow_file_conversion.yaml\",\n",
+        "    pipeline_root=PIPELINE_ROOT,\n",
+        "    enable_caching=False,\n",
+        ")\n",
+        "\n",
+        "pipeline.run()\n",
+        "\n",
+        "! gsutil ls $GCS_CONVERT_OUT\n",
+        "\n",
+        "! rm -f dataflow_file_conversion.yaml gaming_schema.avsc"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "delete_pipeline"
+      },
+      "source": [
+        "### Delete a pipeline job\n",
+        "\n",
+        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "delete_pipeline"
+      },
+      "outputs": [],
+      "source": [
+        "pipeline.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "\n",
+        "- Dataset\n",
+        "- Cloud Storage Bucket"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "# Warning: Setting this to true will delete everything in your bucket\n",
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "get_started_with_dataflow_flex_template_component.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb

@@ -1333,7 +1333,6 @@
         "Next, you compile the pipeline and then exeute it. The pipeline takes the following parameters, which are passed as the dictionary `parameter_values`:\n",
         "\n",
         "- `display_name`: A human readable name for the pipeline job.\n",
-        "- `import_file`: The Cloud Storage location to the dataset.\n",
         "- `worker_pool_specs`: The the machine and container, and auto-scaling requirements, as well as command line arguments.\n",
         "- `study_spec_metrics`: The metrics to optimize in the study trials.\n",
         "- `study_spec_parameters`: The parameters to tune."

notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb

@@ -29,22 +29,22 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 4 : formalization: get started with Vertex ML Metadata\n",
+        "# Get started with Vertex ML Metadata\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/get_started_with_vertex_ml_metadata.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/get_started_with_vertex_ml_metadata.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/ml_metadata/get_started_with_vertex_ml_metadata.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -62,7 +62,9 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 4 : formalization: get started with Vertex ML Metadata."
+        "This tutorial demonstrates how to use Vertex ML Metadata.\n",
+        "\n",
+        "Learn more about [Vertex ML Metadata](https://cloud.google.com/vertex-ai/docs/ml-metadata)."
       ]
     },
     {
@@ -144,19 +146,32 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] \\\n",
+        "                         google-cloud-pipeline-components  --quiet"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -170,63 +185,27 @@
         "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "restart"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "before_you_begin"
       },
       "source": [
-        "## Before you begin\n",
-        "\n",
-        "### GPU runtime\n",
-        "\n",
-        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "## Before you begin"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "project_id"
+        "id": "before_you_begin:nogpu"
       },
       "source": [
-        "#### Set your project ID\n",
+        "### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -237,33 +216,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -274,16 +230,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -294,34 +241,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -332,57 +252,70 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
-        "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
-        "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "**Click Create service account**.\n",
-        "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1138a125ea"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
         "IS_COLAB = False\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        IS_COLAB = True\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()\n",
+        "# IS_COLAB = True"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -393,11 +326,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -408,21 +337,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
-        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -445,26 +360,6 @@
         "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -545,19 +440,7 @@
       "source": [
         "### Set up variables\n",
         "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aip"
+        "Next, set up some variables used throughout the tutorial."
       ]
     },
     {
@@ -579,7 +462,10 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform_v1beta1 as aip_beta"
+        "from datetime import datetime\n",
+        "\n",
+        "import google.cloud.aiplatform_v1beta1 as aip_beta\n",
+        "from google.cloud import aiplatform"
       ]
     },
     {
@@ -707,7 +593,7 @@
       "outputs": [],
       "source": [
         "metadata_store = clients[\"metadata\"].create_metadata_store(\n",
-        "    parent=PARENT, metadata_store_id=\"my-metadata-store\"\n",
+        "    parent=PARENT, metadata_store_id=\"my-metadata-store-unique\"\n",
         ")\n",
         "\n",
         "metadata_store_id = str(metadata_store.result())[7:-2]\n",
@@ -1144,7 +1030,7 @@
       "source": [
         "from kfp.v2 import compiler, dsl\n",
         "from kfp.v2.dsl import (Artifact, Dataset, Input, Metrics, Model, Output,\n",
-        "                        OutputPath, component, pipeline)"
+        "                        OutputPath, component)"
       ]
     },
     {
@@ -1196,7 +1082,7 @@
       "outputs": [],
       "source": [
         "@component(\n",
-        "    packages_to_install=[\"google-cloud-bigquery\", \"pandas\", \"pyarrow\"],\n",
+        "    packages_to_install=[\"google-cloud-bigquery\", \"pandas\", \"pyarrow\", \"db-dtypes\"],\n",
         "    base_image=\"python:3.9\",\n",
         "    output_component_file=\"create_dataset.yaml\",\n",
         ")\n",
@@ -1214,7 +1100,7 @@
         "\n",
         "\n",
         "@component(\n",
-        "    packages_to_install=[\"sklearn\", \"pandas\", \"joblib\"],\n",
+        "    packages_to_install=[\"scikit-learn\", \"pandas\", \"joblib\"],\n",
         "    base_image=\"python:3.9\",\n",
         "    output_component_file=\"beans_model_component.yaml\",\n",
         ")\n",
@@ -1298,7 +1184,7 @@
         "    # A name for the pipeline.\n",
         "    name=\"mlmd-pipeline\",\n",
         ")\n",
-        "def pipeline(\n",
+        "def my_pipeline(\n",
         "    bq_table: str = \"\",\n",
         "    output_data_path: str = \"data.csv\",\n",
         "    project: str = PROJECT_ID,\n",
@@ -1332,20 +1218,22 @@
       "source": [
         "NOW = datetime.now().isoformat().replace(\".\", \":\")[:-7]\n",
         "\n",
-        "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"mlmd_pipeline.json\")\n",
+        "compiler.Compiler().compile(\n",
+        "    pipeline_func=my_pipeline, package_path=\"mlmd_pipeline.json\"\n",
+        ")\n",
         "\n",
-        "run1 = aip.PipelineJob(\n",
+        "run1 = aiplatform.PipelineJob(\n",
         "    display_name=\"mlmd-pipeline\",\n",
         "    template_path=\"mlmd_pipeline.json\",\n",
-        "    job_id=\"mlmd-pipeline-small-{}\".format(TIMESTAMP),\n",
+        "    job_id=\"mlmd-pipeline-small-unique\",\n",
         "    parameter_values={\"bq_table\": \"sara-vertex-demos.beans_demo.small_dataset\"},\n",
         "    enable_caching=True,\n",
         ")\n",
         "\n",
-        "run2 = aip.PipelineJob(\n",
+        "run2 = aiplatform.PipelineJob(\n",
         "    display_name=\"mlmd-pipeline\",\n",
         "    template_path=\"mlmd_pipeline.json\",\n",
-        "    job_id=\"mlmd-pipeline-large-{}\".format(TIMESTAMP),\n",
+        "    job_id=\"mlmd-pipeline-large-unique\",\n",
         "    parameter_values={\"bq_table\": \"sara-vertex-demos.beans_demo.large_dataset\"},\n",
         "    enable_caching=True,\n",
         ")\n",
@@ -1382,7 +1270,7 @@
       },
       "outputs": [],
       "source": [
-        "df = aip.get_pipeline_df(pipeline=\"mlmd-pipeline\")\n",
+        "df = aiplatform.get_pipeline_df(pipeline=\"mlmd-pipeline\")\n",
         "print(df)"
       ]
     },
@@ -1466,6 +1354,10 @@
       },
       "outputs": [],
       "source": [
+        "metadata_store_id = (\n",
+        "    f\"projects/{PROJECT_ID}/locations/{REGION}/metadataStores/my-metadata-store-unique\"\n",
+        ")\n",
+        "\n",
         "clients[\"metadata\"].delete_metadata_store(name=metadata_store_id)"
       ]
     },

notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoint_and_shared_vm.ipynb

@@ -1028,6 +1028,9 @@
         "deployment_resource_pool.dedicated_resources.min_replica_count = MIN_NODES\n",
         "deployment_resource_pool.dedicated_resources.max_replica_count = MAX_NODES\n",
         "deployment_resource_pool.dedicated_resources.machine_spec.machine_type = DEPLOY_COMPUTE\n",
+        "if DEPLOY_NGPU:\n",
+        "    deployment_resource_pool.dedicated_resources.machine_spec.accelerator_type = DEPLOY_GPU\n",
+        "    deployment_resource_pool.dedicated_resources.machine_spec.accelerator_count = DEPLOY_NGPU\n",
         "\n",
         "request = aip_beta.CreateDeploymentResourcePoolRequest(\n",
         "    parent=f\"projects/{PROJECT_ID}/locations/{REGION}\",\n",

notebooks/community/model_garden/model_garden_huggingface_local_inference.ipynb

@@ -0,0 +1,358 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4dc4391f6be7"
+      },
+      "source": [
+        "# Vertex AI Model Garden - Hugging Face Local Inference\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_huggingface_local_inference.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_huggingface_local_inference.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_huggingface_local_inference.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 GPU notebook with preinstalled HuggingFace/transformer libraries is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4e8a0fdd6f44"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates how to run local inference with various Hugging Face models by using [Colab](https://colab.research.google.com/) and installing the necessary libraries or by deploying a [Vertex AI Workbench Instance](https://cloud.google.com/vertex-ai-workbench) with preinstalled transformer and diffuser libraries.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "* Run local inference with various transformer or diffusion models.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "69453bf7230e"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "68990d91bc5f"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3d342b32fb08"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()\n",
+        "    ! pip3 install --upgrade pip\n",
+        "    ! pip3 install torchvision==0.14.1\n",
+        "    ! pip3 install transformers==4.27.1\n",
+        "    ! pip3 install diffusers==0.15.1\n",
+        "    ! apt-get update\n",
+        "    ! apt-get install -y --no-install-recommends tesseract-ocr\n",
+        "    ! pip3 install tesseract==0.1.3\n",
+        "    ! pip3 install pytesseract==0.3.10\n",
+        "    ! pip3 install datasets==2.9.0\n",
+        "    ! pip3 install accelerate==0.18.0\n",
+        "    ! pip3 install triton==2.0.0.dev20221120\n",
+        "    ! pip3 install xformers==0.0.16\n",
+        "    ! pip3 install modelscope==1.4.2\n",
+        "    ! pip3 install open_clip_torch==2.17.1\n",
+        "    ! pip3 install pytorch-lightning==1.9.5\n",
+        "    ! pip3 install opencv-python-headless==4.7.0.72\n",
+        "    # Install gdown for downloading example training images.\n",
+        "    ! pip3 install gdown\n",
+        "    # Remove wrong cublas version.\n",
+        "    ! pip3 uninstall nvidia_cublas_cu11 --yes\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "05e23144b125"
+      },
+      "source": [
+        "### Workbench only\n",
+        "\n",
+        "1.   Follow [this link](https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_huggingfacE_local_inference.ipynb) to deploy the notebook to a Vertex AI Workbench Instance.\n",
+        "2.   Select `Create a new Notebook`.\n",
+        "3.   Click `Advanced Options`.\n",
+        "4.   In the **Environment** tab, select `Debian 10` for **Operating System** and select `Custom Container` for **Environment**.\n",
+        "5.   Set the **Docker container image** field to `us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/transformers-notebook`.\n",
+        "6.   In the **Machine Type** tab, select a 1 `T4` GPU and select `Install NVIDIA GPU driver automatically for me`.\n",
+        "7.   Click `Create` to create the Vertex AI Workbench instance.\n"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1a690839d5"
+      },
+      "source": [
+        "## Sample code"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0a4008240483"
+      },
+      "source": [
+        "#### [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) (Text-to-image)\n",
+        "Generate photo-realistic images given any text input."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5ec6b474d1be"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "from diffusers import StableDiffusionPipeline\n",
+        "\n",
+        "model_id = \"runwayml/stable-diffusion-v1-5\"\n",
+        "pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)\n",
+        "pipe = pipe.to(\"cuda\")\n",
+        "\n",
+        "prompt = \"a photo of an astronaut riding a horse on mars\"\n",
+        "image = pipe(prompt).images[0]\n",
+        "\n",
+        "display(image)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ae94b9b23a52"
+      },
+      "source": [
+        "#### [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) (Text guided image-to-image)\n",
+        "Generate an image based on an initial image and a text prompt."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0acd70f4d08a"
+      },
+      "outputs": [],
+      "source": [
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "import torch\n",
+        "from diffusers import StableDiffusionImg2ImgPipeline\n",
+        "from PIL import Image\n",
+        "\n",
+        "device = \"cuda\"\n",
+        "model_id_or_path = \"runwayml/stable-diffusion-v1-5\"\n",
+        "pipe = StableDiffusionImg2ImgPipeline.from_pretrained(\n",
+        "    model_id_or_path, torch_dtype=torch.float16\n",
+        ")\n",
+        "pipe = pipe.to(device)\n",
+        "\n",
+        "url = \"https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg\"\n",
+        "\n",
+        "response = requests.get(url)\n",
+        "init_image = Image.open(BytesIO(response.content)).convert(\"RGB\")\n",
+        "init_image = init_image.resize((768, 512))\n",
+        "\n",
+        "prompt = \"A fantasy landscape, trending on artstation\"\n",
+        "\n",
+        "images = pipe(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e76b3fe8d10c"
+      },
+      "source": [
+        "#### [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) (Image-inpainting)\n",
+        "Generate an image based on an original image and prompt, only editing the areas denoted by a mask image."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8bc3238be4e7"
+      },
+      "outputs": [],
+      "source": [
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "import torch\n",
+        "from diffusers import StableDiffusionInpaintPipeline\n",
+        "from PIL import Image\n",
+        "\n",
+        "image_url = \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png\"\n",
+        "image_response = requests.get(image_url)\n",
+        "init_image = Image.open(BytesIO(image_response.content)).convert(\"RGB\")\n",
+        "display(init_image)\n",
+        "\n",
+        "mask_url = \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png\"\n",
+        "mask_response = requests.get(mask_url)\n",
+        "mask_image = Image.open(BytesIO(mask_response.content)).convert(\"RGB\")\n",
+        "\n",
+        "pipe = StableDiffusionInpaintPipeline.from_pretrained(\n",
+        "    \"runwayml/stable-diffusion-inpainting\",\n",
+        "    revision=\"fp16\",\n",
+        "    torch_dtype=torch.float16,\n",
+        ")\n",
+        "pipe.to(\"cuda\")\n",
+        "\n",
+        "prompt = \"Face of a yellow cat, high resolution, sitting on a park bench\"\n",
+        "images = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1ade95a9b20e"
+      },
+      "source": [
+        "#### [impira/layoutlm-document-qa](https://huggingface.co/impira/layoutlm-document-qa) (Document question answering)\n",
+        "Answer questions about a given document."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "492d9f1de3f2"
+      },
+      "outputs": [],
+      "source": [
+        "from transformers import pipeline\n",
+        "\n",
+        "nlp = pipeline(\n",
+        "    \"document-question-answering\",\n",
+        "    model=\"impira/layoutlm-document-qa\",\n",
+        ")\n",
+        "\n",
+        "print(\n",
+        "    nlp(\n",
+        "        \"https://templates.invoicehome.com/invoice-template-us-neat-750px.png\",\n",
+        "        \"What is the invoice number?\",\n",
+        "    )\n",
+        ")\n",
+        "# [{'score': 0.9943977, 'answer': 'us-001', 'start': 15, 'end': 15}]\n",
+        "\n",
+        "print(\n",
+        "    nlp(\n",
+        "        \"https://miro.medium.com/max/787/1*iECQRIiOGTmEFLdWkVIH2g.jpeg\",\n",
+        "        \"What is the purchase amount?\",\n",
+        "    )\n",
+        ")\n",
+        "# [{'score': 0.9912159, 'answer': '$1,000,000,000', 'start': 97, 'end': 97}]\n",
+        "\n",
+        "print(\n",
+        "    nlp(\n",
+        "        \"https://www.accountingcoach.com/wp-content/uploads/2013/10/income-statement-example@2x.png\",\n",
+        "        \"What are the 2020 net sales?\",\n",
+        "    )\n",
+        ")\n",
+        "# [{'score': 0.978011429309845, 'answer': '$ 3,980', 'start': 15, 'end': 16}]"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_huggingface_local_inference.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb

@@ -0,0 +1,723 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ur8xi4C7S06n"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "TirJ-SGQseby"
+      },
+      "source": [
+        "# Vertex AI Model Garden Keras Stable Diffusion\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>                                                                                               <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dwGLvtIeECLK"
+      },
+      "source": [
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.9\n",
+        "\n",
+        "You can open this notebook directly in colab, or create [google managed](https://cloud.google.com/vertex-ai/docs/workbench/managed/create-instance) or [user managed](https://cloud.google.com/vertex-ai/docs/workbench/user-managed/create-new) workbench instances."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates how to use [Keras Stable Diffusion](https://keras.io/api/keras_cv/models/stable_diffusion) in Vertex AI Model Garden."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0z9r_mBmDeYh"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "* Run local inferences for pretrained or customized models\n",
+        "\n",
+        "* Deploy pretrained or customized models in Google Cloud Vertex AI\n",
+        "\n",
+        "* Finetune models in Google Cloud Vertex AI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "xxo28lDtDxn-"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "We use the dataset\n",
+        "[Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) to show how to finetune the stable diffusion models.\n",
+        "However, we'll use a slightly different version which was derived from the original\n",
+        "dataset to fit better with `tf.data`. Refer to\n",
+        "[the documentation](https://huggingface.co/datasets/sayakpaul/pokemon-blip-original-version)\n",
+        "for more details."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AEnkHABrDijz"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "z__i0w0lCAsW"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the following packages required to execute this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Jvqs-ehKlaYh"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    # Configs for colab notebooks.\n",
+        "    ! pip3 install --upgrade --quiet google-cloud-aiplatform\n",
+        "\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)\n",
+        "\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "# Configs for all notebooks.\n",
+        "! pip3 install --quiet keras-cv==0.4.1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KEukV6uRk_S3"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint.\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set your project, region and buckets\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)\n",
+        "\n",
+        "You can change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations).\n",
+        "\n",
+        "You can create a storage bucket to store intermediate artifacts such as datasets, trained models etc."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YjNCFxq0JxlA"
+      },
+      "outputs": [],
+      "source": [
+        "# The project and bucket are for experiments below.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "! gcloud config set project $PROJECT_ID\n",
+        "\n",
+        "# The form for BUCKET_URI is gs://<bucket-name>.\n",
+        "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
+        "REGION = \"us-central1\"  # @param {type: \"string\"}\n",
+        "\n",
+        "import os\n",
+        "\n",
+        "STAGING_BUCKET = os.path.join(BUCKET_URI, \"temporal\")\n",
+        "EXPERIMENT_BUCKET = os.path.join(BUCKET_URI, \"keras\")\n",
+        "DATA_BUCKET = os.path.join(EXPERIMENT_BUCKET, \"data\")\n",
+        "MODEL_BUCKET = os.path.join(EXPERIMENT_BUCKET, \"model\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "uDjp76aaLZY9"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5uv7-iDKLbO0"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=STAGING_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZZFPe_GezXg8"
+      },
+      "source": [
+        "### Define constants and common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XcYUGwr-AJGY"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import matplotlib.pyplot as plt\n",
+        "from PIL import Image\n",
+        "\n",
+        "# Training constants.\n",
+        "TRAINING_JOB_PREFIX = \"train\"\n",
+        "TRAIN_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/keras-train:latest\"\n",
+        "TRAIN_MACHINE_TYPE = \"a2-highgpu-1g\"\n",
+        "TRAIN_ACCELERATOR_TYPE = \"NVIDIA_TESLA_A100\"\n",
+        "TRAIN_NUM_GPU = 1\n",
+        "RESOLUTION = 512\n",
+        "\n",
+        "# Prediction constants.\n",
+        "PREDICTION_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/keras-serve:latest\"\n",
+        "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_V100\"\n",
+        "PREDICTION_MACHINE_TYPE = \"n1-standard-8\"\n",
+        "DEPLOY_JOB_PREFIX = \"deploy\"\n",
+        "\n",
+        "\n",
+        "def get_job_name_with_datetime(prefix: str):\n",
+        "    return prefix + datetime.now().strftime(\"_%Y%m%d_%H%M%S\")\n",
+        "\n",
+        "\n",
+        "def download_data_to_gcs(tar_filepath, gcs_bucket):\n",
+        "    filename_with_ext = os.path.basename(tar_filepath)\n",
+        "    filename_without_ext = filename_with_ext.replace(\".tar.gz\", \"\")\n",
+        "    print(\"Download files from: \", tar_filepath)\n",
+        "    ! wget $tar_filepath -O $filename_with_ext\n",
+        "    ! mkdir -p $filename_without_ext\n",
+        "    ! tar -xvf $filename_with_ext -C .\n",
+        "\n",
+        "    ! gsutil -m cp -r $filename_without_ext $gcs_bucket/\n",
+        "    gcs_path = os.path.join(gcs_bucket, filename_without_ext)\n",
+        "    print(\"Upload files to: \", gcs_path)\n",
+        "    return gcs_path\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_path, service_account):\n",
+        "\n",
+        "    deploy_model_name = get_job_name_with_datetime(DEPLOY_JOB_PREFIX)\n",
+        "    print(\"The deployed job name is: \", deploy_model_name)\n",
+        "    serving_env = {\n",
+        "        \"MODEL_PATH\": model_path,\n",
+        "        \"IMAGE_WIDTH\": f\"{RESOLUTION}\",\n",
+        "        \"IMAGE_HEIGHT\": f\"{RESOLUTION}\",\n",
+        "    }\n",
+        "\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{deploy_model_name}-endpoint\")\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=deploy_model_name,\n",
+        "        serving_container_image_uri=PREDICTION_CONTAINER_URI,\n",
+        "        serving_container_ports=[8501],\n",
+        "        serving_container_predict_route=\"/predict\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=PREDICTION_MACHINE_TYPE,\n",
+        "        accelerator_type=PREDICTION_ACCELERATOR_TYPE,\n",
+        "        accelerator_count=1,\n",
+        "        min_replica_count=1,\n",
+        "        max_replica_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "        service_account=service_account,\n",
+        "    )\n",
+        "    return model, endpoint\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def display_image(image):\n",
+        "    _ = plt.figure(figsize=(20, 15))\n",
+        "    plt.grid(False)\n",
+        "    plt.imshow(image)\n",
+        "\n",
+        "\n",
+        "def display_image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "epo-RHXzcBBT"
+      },
+      "source": [
+        "## Run inferences\n",
+        "\n",
+        "This section shows how to run inferences with Keras Stable Diffusion models.\n",
+        "\n",
+        "1. Run inferences locally\n",
+        "2. Run inferences with serving dockers\n",
+        "\n",
+        "You can run inferences with pre-trained models from Keras team, or your own finetuned models.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6zsa9vnBHhvO"
+      },
+      "outputs": [],
+      "source": [
+        "# Sets the model_path to empty to load the pre-trained model from Keras team.\n",
+        "# Sets the model_path to a gcs uri to load the finetuned models.\n",
+        "model_path = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ld39hkcIceE2"
+      },
+      "source": [
+        "### Run inferences locally\n",
+        "Local inferences can finish in seconds with GPUs.\n",
+        "\n",
+        "Load models first."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G1nCKVSac3Y5"
+      },
+      "outputs": [],
+      "source": [
+        "from keras_cv.models import StableDiffusion\n",
+        "\n",
+        "model = StableDiffusion(img_height=RESOLUTION, img_width=RESOLUTION, jit_compile=True)\n",
+        "if model_path:\n",
+        "    model.diffusion_model.load_weights(model_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ABaCSIWuP-_G"
+      },
+      "source": [
+        "Then run inferences."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pnyeVsh8RNI5"
+      },
+      "outputs": [],
+      "source": [
+        "batch_size = 1\n",
+        "img = model.text_to_image(\n",
+        "    prompt=\"a squirrel in Picasso style\",\n",
+        "    batch_size=batch_size,  # How many images to generate at once\n",
+        "    num_steps=25,  # Number of iterations (controls image quality)\n",
+        "    seed=123,  # A fixed seed guarantees the same prompt always generates the same image\n",
+        ")\n",
+        "for i in range(batch_size):\n",
+        "    display_image(img[i])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kY87SU9Adq4o"
+      },
+      "source": [
+        "### Serve models with dockers\n",
+        "When serve models with dockers, we will deploy models in Google Cloud Vertex AI. The default setting will use 1 V100 GPU for deployment.\n",
+        "\n",
+        "Please create a Service Account for serving with dockers if you do not have one yet.\n",
+        "\n",
+        "The model deployment will take ~10 minutes to finish."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "yCB9vu7RenY6"
+      },
+      "outputs": [],
+      "source": [
+        "# The service account looks like:\n",
+        "# '<account_name>@<project>.iam.gserviceaccount.com'\n",
+        "# Please go to https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console\n",
+        "# and create service account with `Vertex AI User` and `Storage Object Admin` roles.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_path=model_path,\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
+        ")\n",
+        "\n",
+        "endpoint_id = endpoint.name\n",
+        "print(\"endpoint id is: \", endpoint_id)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "72_BW_BgfvYT"
+      },
+      "source": [
+        "Once deployed, you can send a batch of text prompts to the endpoint to generate images.\n",
+        "\n",
+        "Note, the inference time for the first request for a fresh deployment will need more time to process and take ~45 seconds on one V100 GPU. The inferences for further request is ~12 seconds on one V100 GPU per image."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "U_jrNcZ5eVbH"
+      },
+      "outputs": [],
+      "source": [
+        "# # Loads an existing endpoint as below.\n",
+        "# endpoint_id = <An Existing Endpoint ID>\n",
+        "# aip_endpoint_name = (\n",
+        "#     f\"projects/{PROJECT_ID}/locations/{REGION}/endpoints/{endpoint_id}\"\n",
+        "# )\n",
+        "# endpoint = aiplatform.Endpoint(aip_endpoint_name)\n",
+        "\n",
+        "instances = [\n",
+        "    {\"prompt\": \"a squirrel in Picasso style\"},\n",
+        "    {\"prompt\": \"a dog in Picasso style\"},\n",
+        "    {\"prompt\": \"a cat in Picasso style\"},\n",
+        "    {\"prompt\": \"a deer in Picasso style\"},\n",
+        "]\n",
+        "\n",
+        "parameters = {\n",
+        "    \"batch_size\": 1,  # How many images to generate at once\n",
+        "    \"num_steps\": 25,  # Number of iterations (controls image quality)\n",
+        "    \"seed\": 123,  # A fixed seed guarantees the same prompt always generates the same image\n",
+        "}\n",
+        "response = endpoint.predict(instances=instances, parameters=parameters)\n",
+        "# prediction['predicted_image'] will contains the prediction images in a batch.\n",
+        "# The batch size in this example is 1, and the visualization only parses the\n",
+        "# first predicted image.\n",
+        "images = [\n",
+        "    base64_to_image(prediction[\"predicted_image\"][0])\n",
+        "    for prediction in response.predictions\n",
+        "]\n",
+        "display_image_grid(images, rows=2, cols=2)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "LiQF7fm6f842"
+      },
+      "source": [
+        "### Clean up"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "eqJyypt-f9K6"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploys models and deletes endpoints.\n",
+        "endpoint.delete(force=True)\n",
+        "# Deletes models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RB_xY9ipr7ZU"
+      },
+      "source": [
+        "## Finetune models\n",
+        "This section shows how to finetune Keras Stable diffusion models with trainig dockers.\n",
+        "\n",
+        "If you would like to use finetuned models, please go to the section `Run inferences`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OD3TtaWs5b4v"
+      },
+      "source": [
+        "### Download data\n",
+        " We download the data to GCS storage for the experiments with training dockers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2TVB8MU-5i-q"
+      },
+      "outputs": [],
+      "source": [
+        "# Skips this step if you have already downloaded the dataset.\n",
+        "download_data_to_gcs(\n",
+        "    \"https://huggingface.co/datasets/sayakpaul/pokemon-blip-original-version/resolve/main/pokemon_dataset.tar.gz\",\n",
+        "    DATA_BUCKET,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Ee7Hzq8O5jgF"
+      },
+      "source": [
+        "### Start training jobs\n",
+        "We finetune 512*512 stable diffusion models with 1 epoch and it takes ~15 minutes to finish using 1 A100 GPU with default settings."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "riG_qUokg0XZ"
+      },
+      "outputs": [],
+      "source": [
+        "data_csv = os.path.join(DATA_BUCKET, \"pokemon_dataset/data.csv\")\n",
+        "epochs = 1\n",
+        "\n",
+        "train_job_name = get_job_name_with_datetime(TRAINING_JOB_PREFIX)\n",
+        "model_dir = os.path.join(MODEL_BUCKET, train_job_name)\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": TRAIN_MACHINE_TYPE,\n",
+        "            \"accelerator_type\": TRAIN_ACCELERATOR_TYPE,\n",
+        "            \"accelerator_count\": TRAIN_NUM_GPU,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"disk_spec\": {\n",
+        "            \"boot_disk_type\": \"pd-ssd\",\n",
+        "            \"boot_disk_size_gb\": 500,\n",
+        "        },\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": TRAIN_CONTAINER_URI,\n",
+        "            \"command\": [],\n",
+        "            \"env\": [\n",
+        "                {\n",
+        "                    \"name\": \"RESOLUTION\",\n",
+        "                    \"value\": f\"{RESOLUTION}\",\n",
+        "                },\n",
+        "            ],\n",
+        "            \"args\": [\n",
+        "                f\"--epochs={epochs}\",\n",
+        "                f\"--input_csv_path={data_csv}\",\n",
+        "                f\"--output_model_dir={model_dir}\",\n",
+        "            ],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "train_job = aiplatform.CustomJob(\n",
+        "    display_name=train_job_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "train_job.run()\n",
+        "\n",
+        "model_path = os.path.join(model_dir, \"saved_model.h5\")\n",
+        "print(\"The trained model is saved as: \", model_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "wBlQ6FQlJhBi"
+      },
+      "source": [
+        "After the training finishes, you can use `model_path` and then go to the `Run inferences` section above to run predictions."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kkH2nrpdp4sp"
+      },
+      "source": [
+        "### Clean up"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Ax6vQVZhp9pR"
+      },
+      "outputs": [],
+      "source": [
+        "train_job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1dijQDiZWegt"
+      },
+      "source": [
+        "## References\n",
+        "\n",
+        "- [Fine-tuning Stable Diffusion](https://keras.io/examples/generative/finetune_stable_diffusion/)\n",
+        "- [StableDiffusion image-generation model](https://keras.io/api/keras_cv/models/stable_diffusion/)\n",
+        "- [High-performance image generation using Stable Diffusion in KerasCV](https://keras.io/guides/keras_cv/generate_images_with_stable_diffusion/)"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "name": "model_garden_keras_stable_diffusion.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pipeline_templates_bert.ipynb

@@ -0,0 +1,852 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title:generic,gcp"
+      },
+      "source": [
+        "# Get started with Model Garden Pipeline Templates for BERT models\n",
+        "\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_template_pipelines_bert.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_template_pipelines_bert.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/communitymodel_garden/model_garden_template_pipelines_bert.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>                                                                                               \n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:mlops"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to modify, compile and execute a prebuilt Vertex AI Model Garden pipeline template with Vertex AI Pipelines.\n",
+        "\n",
+        "Learn more about [Create a pipeline template](https://cloud.google.com/vertex-ai/docs/pipelines/create-pipeline-template)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:mlops,stage4,get_started_vertex_model_evaluation"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to use a prebuilt pipeline template with `Vertex AI Pipelines` to fine-tune a BERT text classification model, where the model is accessed from `Vertex AI Model Garden`.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Model Garden`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a user-defined repository in the `Artifact Registry`.\n",
+        "- Upload the prebuilt pipeline template to the `Artifact Registry`.\n",
+        "- Create a pipeline job with the prebuilt pipeline template to fine-tune a BERT model.\n",
+        "- Execute the pipeline using `Vertex AI Pipelines`.\n",
+        "    - Load BERT model from Vertex AI Model Garden\n",
+        "    - Fine-tune train the model\n",
+        "    - Do batch prediction\n",
+        "    - Evaluate the model from the batch prediction results\n",
+        "- Obtain the Vertex AI Model resource from the pipeline artifacts.\n",
+        "- Deploy the model to a Vertex AI Endpoint\n",
+        "- Make a prediction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:bank,lbn"
+      },
+      "source": [
+        "### Model\n",
+        "\n",
+        "This tutorial uses a pre-trained BERT text classification model from `Vertex AI Model Garden`, which is then fine-tuned (transfer learning) on a dataset of text phrases which are classified as either FirstClass or SecondClass.\n",
+        "\n",
+        "Learn more about [BERT pretrained encoder model]( https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/3). "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "* Dataflow\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and [Dataflow pricing](https://cloud.google.com/dataflow/pricing)\n",
+        "and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "source": [
+        "## Installations\n",
+        "\n",
+        "Install the packages required for executing this notebook.\n",
+        "\n",
+        "*Note:* This tutorial requires KFP 2.x."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
+        "                         google-cloud-pipeline-components \\\n",
+        "                         kfp==2.0.0b15"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin"
+      },
+      "source": [
+        "## Before you begin\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c4ccf556d4ea"
+      },
+      "source": [
+        "### Enable APIs\n",
+        "\n",
+        "You can enable the required APIs using `gcloud`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "619529337e6d"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud services enable compute.googleapis.com         \\\n",
+        "                         containerregistry.googleapis.com  \\\n",
+        "                         aiplatform.googleapis.com  \\\n",
+        "                         artifactregistry.googleapis.com"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "IS_COLAB = False\n",
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()\n",
+        "# IS_COLAB=True"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator  \n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer  "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_kfp"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "from kfp.registry import RegistryClient"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9b773e8d2bd2"
+      },
+      "source": [
+        "## Create repo in Artifact Registry\n",
+        "\n",
+        "First, you create your own (user-defined) repository in the `Artifact Registry`. You use this repository to upload and retrieve your pipeline templates.\n",
+        "\n",
+        "The name of your repo is `quickstart-kfp-repo`"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "520de849cee2"
+      },
+      "outputs": [],
+      "source": [
+        "REPO_NAME = \"quickstart-kfp-repo\"\n",
+        "\n",
+        "! gcloud artifacts repositories create {REPO_NAME} --location={REGION} --repository-format=KFP"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1611d3517c0f"
+      },
+      "source": [
+        "### Upload the pipeline template\n",
+        "\n",
+        "Next, you instantiate a client interface to the Artifact Registry. Then with the `upload_pipeline()` method you upload your pipeline template."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "72db37f6d67c"
+      },
+      "outputs": [],
+      "source": [
+        "BERT_YAML = \"gs://cloud-samples-data/vertex-ai/dataset-management/datasets/bert_finetuning/pipeline.yaml\"\n",
+        "\n",
+        "! gsutil cp {BERT_YAML} pipeline.yaml\n",
+        "\n",
+        "client = RegistryClient(\n",
+        "    host=f\"https://{REGION}-kfp.pkg.dev/{PROJECT_ID}/quickstart-kfp-repo\"\n",
+        ")\n",
+        "\n",
+        "templateName, versionName = client.upload_pipeline(\n",
+        "    file_name=\"pipeline.yaml\",\n",
+        "    tags=[\"v1\", \"latest\"],\n",
+        "    extra_headers={\n",
+        "        \"description\": \"This is a pipeline template for fine-tuning a BERT model.\"\n",
+        "    },\n",
+        ")\n",
+        "\n",
+        "! rm pipeline.yaml"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "02f82754fc0d"
+      },
+      "source": [
+        "### View your artifacts in your registry\n",
+        "\n",
+        "Next, using the `gcloud artifacts files` command you view the artifacts, inclusive of the pipeline template, in your artifacts repository."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b2f641eb2056"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud artifacts files list  --repository={REPO_NAME} --location={REGION}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9d5296831cfb"
+      },
+      "source": [
+        "## Load and execute the pipeline job\n",
+        "\n",
+        "Next, you create a Vertex AI Pipeline job from your BERT pipeline template by instantiating a PipelineJob(), with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the pipeline job.\n",
+        "- `template_path`: The path to the pipeline template in the Artifact Registry.\n",
+        "- `enable_caching`: On re-runs, use the results from previous successful and unchanged steps.\n",
+        "- `pipeline_root`: A Cloud storage location for storing pipeline results.\n",
+        "- `parameter_values`: The parameters and values that are input to the template pipeline. In this example, they are:\n",
+        "    - `project`: Your project ID.\n",
+        "    - `class_labels`: A list of valid class labels, in cardinal order.\n",
+        "    - `root_dir`: A Cloud Storage scratch area.\n",
+        "    - `training_data_path`: A Cloud Storage location to the training data.\n",
+        "    - `ground_truth_gcs_source_uris`: A Cloud Storage location to evaluation data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a3c502fc7e41"
+      },
+      "outputs": [],
+      "source": [
+        "PIPELINE_ROOT = f\"{BUCKET_URI}/pipeline_root/bert-finetuning\"\n",
+        "\n",
+        "job = aiplatform.PipelineJob(\n",
+        "    display_name=\"bert-finetuning\",\n",
+        "    template_path=f\"https://{REGION}-kfp.pkg.dev/{PROJECT_ID}/quickstart-kfp-repo/{templateName}/{versionName}\",\n",
+        "    pipeline_root=PIPELINE_ROOT,\n",
+        "    enable_caching=False,\n",
+        "    parameter_values={\n",
+        "        \"project\": PROJECT_ID,\n",
+        "        \"class_labels\": [\"FirstClass\", \"SecondClass\", \"[UNK]\"],\n",
+        "        \"root_dir\": BUCKET_URI,\n",
+        "        \"ground_truth_gcs_source_uris\": [\n",
+        "            \"gs://cloud-samples-data/vertex-ai/dataset-management/datasets/bert_finetuning/wide_and_deep_trainer_container_tests_input.jsonl\"\n",
+        "        ],\n",
+        "        \"training_data_path\": \"gs://cloud-samples-data/vertex-ai/dataset-management/datasets/bert_finetuning/wide_and_deep_trainer_container_tests_input.jsonl\",\n",
+        "    },\n",
+        ")\n",
+        "\n",
+        "job.run()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view_pipleline_results:bqml"
+      },
+      "source": [
+        "### View the pipeline results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "view_pipleline_results:bqml"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_NUMBER = job.gca_resource.name.split(\"/\")[1]\n",
+        "print(PROJECT_NUMBER)\n",
+        "\n",
+        "\n",
+        "def print_pipeline_output(job, output_task_name):\n",
+        "    JOB_ID = job.name\n",
+        "    print(JOB_ID)\n",
+        "    artifact = \"\"\n",
+        "    for _ in range(len(job.gca_resource.job_detail.task_details)):\n",
+        "        TASK_ID = job.gca_resource.job_detail.task_details[_].task_id\n",
+        "        EXECUTE_OUTPUT = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/executor_output.json\"\n",
+        "        )\n",
+        "        GCP_RESOURCES = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/gcp_resources\"\n",
+        "        )\n",
+        "        EVALUATION_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
+        "        # Check if file exists, 0 is success\n",
+        "        !gsutil -q stat $EXECUTE_OUTPUT\n",
+        "        if _exit_code == 0:\n",
+        "            ! gsutil cat $EXECUTE_OUTPUT\n",
+        "            artifact = EXECUTE_OUTPUT\n",
+        "            break\n",
+        "        !gsutil -q stat $GCP_RESOURCES\n",
+        "        if _exit_code == 0:\n",
+        "            ! gsutil cat $GCP_RESOURCES\n",
+        "            artifact = GCP_RESOURCES\n",
+        "            break\n",
+        "        !gsutil -q stat $EVALUATION_METRICS\n",
+        "        if _exit_code == 0:\n",
+        "            ! gsutil cat $EVALUATION_METRICS\n",
+        "            artifact = EVALUATION_METRICS\n",
+        "            break\n",
+        "\n",
+        "    return artifact\n",
+        "\n",
+        "\n",
+        "print(\"get-vertex-model\")\n",
+        "artifacts = print_pipeline_output(job, \"get-vertex-model\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "print(output)\n",
+        "output = json.loads(output[0])\n",
+        "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
+        "print(\"\\n\\n\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f431a9e6f025"
+      },
+      "source": [
+        "### Delete the pipeline job\n",
+        "\n",
+        "The method 'delete()' will delete the pipeline job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "00bf554abbc6"
+      },
+      "outputs": [],
+      "source": [
+        "job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3d183db57ae2"
+      },
+      "source": [
+        "### Deploy the model\n",
+        "\n",
+        "Next, you deploy the model to an endpoint:\n",
+        "\n",
+        "- Use the `model_id` obtained from the pipeline artifacts to instaniate a Vertex AI Model resource instance.\n",
+        "- Deploy the Vertex AI Model resource to a Vertex AI Endpoint resource.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "591ccc049ce5"
+      },
+      "outputs": [],
+      "source": [
+        "model = aiplatform.Model(model_id)\n",
+        "endpoint = model.deploy(\n",
+        "    accelerator_count=1,\n",
+        "    accelerator_type=aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_T4.name,\n",
+        "    machine_type=\"n1-standard-4\",\n",
+        ")\n",
+        "print(endpoint)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "edb781a92864"
+      },
+      "source": [
+        "### Make a prediction\n",
+        "\n",
+        "Finally, you make a prediction with the deployed model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "72d94012a987"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.predict([\"this is a test\"])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "delete_bucket = False\n",
+        "\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
+        "model.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI\n",
+        "\n",
+        "! rm -rf custom custom.tar.gz"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pipeline_templates_bert.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pipeline_templates_t5x.ipynb

@@ -0,0 +1,850 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title:generic,gcp"
+      },
+      "source": [
+        "# Get started with Model Garden Pipeline Templates for T5X models\n",
+        "\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_template_pipelines_t5x.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_template_pipelines_t5x.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/communitymodel_garden/model_garden_template_pipelines_t5x.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>                                                                                               \n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:mlops"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to modify, compile and execute a prebuilt Vertex AI Model Garden pipeline template with Vertex AI Pipelines.\n",
+        "\n",
+        "Learn more about [Create a pipeline template](https://cloud.google.com/vertex-ai/docs/pipelines/create-pipeline-template)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:mlops,stage4,get_started_vertex_model_evaluation"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to use a prebuilt pipeline template with `Vertex AI Pipelines` to fine-tune a T5X text classification model, where the model is accessed from `Vertex AI Model Garden`.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Model Garden`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a user-defined repository in the `Artifact Registry`.\n",
+        "- Upload the prebuilt pipeline template to the `Artifact Registry`.\n",
+        "- Create a pipeline job with the prebuilt pipeline template to fine-tune a T5X model.\n",
+        "- Execute the pipeline using `Vertex AI Pipelines`.\n",
+        "    - Load T5X model from Vertex AI Model Garden\n",
+        "    - Fine-tune train the model\n",
+        "- Obtain the Vertex AI Model resource from the pipeline artifacts.\n",
+        "- Deploy the model to a Vertex AI Endpoint\n",
+        "- Make a prediction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:bank,lbn"
+      },
+      "source": [
+        "### Model\n",
+        "\n",
+        "This tutorial uses a pre-trained T5 text classification model from `Vertex AI Model Garden`, which is then fine-tuned (transfer learning) on a dataset of text phrases which are classified as either FirstClass or SecondClass.\n",
+        "\n",
+        "Learn more about [Text-to-text transfer transformer](https://github.com/google-research/text-to-text-transfer-transformer). "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "* Dataflow\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and [Dataflow pricing](https://cloud.google.com/dataflow/pricing)\n",
+        "and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "source": [
+        "## Installations\n",
+        "\n",
+        "Install the packages required for executing this notebook.\n",
+        "\n",
+        "*Note:* This tutorial requires KFP 2.x."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
+        "                         google-cloud-pipeline-components \\\n",
+        "                         kfp==2.0.0b15"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin"
+      },
+      "source": [
+        "## Before you begin\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c4ccf556d4ea"
+      },
+      "source": [
+        "### Enable APIs\n",
+        "\n",
+        "You can enable the required APIs using `gcloud`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "619529337e6d"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud services enable compute.googleapis.com         \\\n",
+        "                         containerregistry.googleapis.com  \\\n",
+        "                         aiplatform.googleapis.com  \\\n",
+        "                         artifactregistry.googleapis.com"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "IS_COLAB = False\n",
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()\n",
+        "# IS_COLAB=True"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator  \n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer  "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_kfp"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "from kfp.registry import RegistryClient"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9b773e8d2bd2"
+      },
+      "source": [
+        "## Create repo in Artifact Registry\n",
+        "\n",
+        "First, you create your own (user-defined) repository in the `Artifact Registry`. You use this repository to upload and retreive your pipeline templates.\n",
+        "\n",
+        "The name of your repo is `quickstart-kfp-repo`"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "520de849cee2"
+      },
+      "outputs": [],
+      "source": [
+        "REPO_NAME = \"quickstart-kfp-repo\"\n",
+        "\n",
+        "! gcloud artifacts repositories create {REPO_NAME} --location={REGION} --repository-format=KFP"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1611d3517c0f"
+      },
+      "source": [
+        "### Upload the pipeline template\n",
+        "\n",
+        "Next, you instantiate a client interface to the Artifact Registry. Then with the `upload_pipeline()` method you upload your pipeline template."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7f002e57998a"
+      },
+      "outputs": [],
+      "source": [
+        "T5X_YAML = \"gs://cloud-samples-data/vertex-ai/dataset-management/datasets/t5_finetuning/pipeline.yaml\"\n",
+        "\n",
+        "! gsutil cp {T5X_YAML} pipeline.yaml\n",
+        "\n",
+        "client = RegistryClient(\n",
+        "    host=f\"https://{REGION}-kfp.pkg.dev/{PROJECT_ID}/quickstart-kfp-repo\"\n",
+        ")\n",
+        "\n",
+        "templateName, versionName = client.upload_pipeline(\n",
+        "    file_name=\"pipeline.yaml\",\n",
+        "    tags=[\"v1\", \"latest\"],\n",
+        "    extra_headers={\n",
+        "        \"description\": \"This is a pipeline template for fine-tuning a T5 model.\"\n",
+        "    },\n",
+        ")\n",
+        "\n",
+        "! rm pipeline.yaml"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "02f82754fc0d"
+      },
+      "source": [
+        "### View your artifacts in your registry\n",
+        "\n",
+        "Next, using the `gcloud artifacts files` command you view the artifacts, inclusive of the pipeline template, in your artifacts repository."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b2f641eb2056"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud artifacts files list  --repository={REPO_NAME} --location={REGION}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "968a46a3cb6d"
+      },
+      "source": [
+        "## Load and execute the pipeline job\n",
+        "\n",
+        "Next, you create a Vertex AI Pipeline job from your T5 pipeline template by instantiating a PipelineJob(), with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the pipeline job.\n",
+        "- `template_path`: The path to the pipeline template in the Artifact Registry.\n",
+        "- `enable_caching`: On re-runs, use the results from previous successful and unchanged steps.\n",
+        "- `pipeline_root`: A Cloud storage location for storing pipeline results.\n",
+        "- `parameter_values`: The parameters and values that are input to the template pipeline. In this example, they are:\n",
+        "TODO\n",
+        "    - `project`: Your project ID.\n",
+        "    - `class_labels`: A list of valid class labels, in cardinal order.\n",
+        "    - `root_dir`: A Cloud Storage scratch area.\n",
+        "    - `training_data_path`: A Cloud Storage location to the training data.\n",
+        "    - `ground_truth_gcs_source_uris`: A Cloud Storage location to evaluation data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a3c502fc7e41"
+      },
+      "outputs": [],
+      "source": [
+        "PIPELINE_ROOT = f\"{BUCKET_URI}/pipeline_root/t5_finetuning\"\n",
+        "\n",
+        "job = aiplatform.PipelineJob(\n",
+        "    display_name=\"t5x-finetuning\",\n",
+        "    template_path=f\"https://{REGION}-kfp.pkg.dev/{PROJECT_ID}/quickstart-kfp-repo/{templateName}/{versionName}\",\n",
+        "    pipeline_root=PIPELINE_ROOT,\n",
+        "    enable_caching=False,\n",
+        "    parameter_values={\n",
+        "        \"project_id\": PROJECT_ID,\n",
+        "        \"accelerator_count\": 32,\n",
+        "        \"feature_keys\": \"question\",\n",
+        "        \"label_key\": \"answer\",\n",
+        "        \"training_data_path\": \"gs://cloud-llm-public/tfds/natural_questions_open/1.0.0_shortened/natural_questions_open-train.tfrecord-00000-of-00001\",\n",
+        "        \"validation_data_path\": \"gs://cloud-llm-public/tfds/natural_questions_open/1.0.0_shortened/natural_questions_open-validation.tfrecord-00000-of-00001\",\n",
+        "    },\n",
+        ")\n",
+        "\n",
+        "job.run()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view_pipleline_results:bqml"
+      },
+      "source": [
+        "### View the pipeline results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "view_pipleline_results:bqml"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_NUMBER = job.gca_resource.name.split(\"/\")[1]\n",
+        "print(PROJECT_NUMBER)\n",
+        "\n",
+        "\n",
+        "def print_pipeline_output(job, output_task_name):\n",
+        "    JOB_ID = job.name\n",
+        "    print(JOB_ID)\n",
+        "    artifact = \"\"\n",
+        "    for _ in range(len(job.gca_resource.job_detail.task_details)):\n",
+        "        TASK_ID = job.gca_resource.job_detail.task_details[_].task_id\n",
+        "        EXECUTE_OUTPUT = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/executor_output.json\"\n",
+        "        )\n",
+        "        GCP_RESOURCES = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/gcp_resources\"\n",
+        "        )\n",
+        "        EVALUATION_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
+        "        # Check if file exists, 0 is success\n",
+        "        !gsutil -q stat $EXECUTE_OUTPUT\n",
+        "        if _exit_code == 0:\n",
+        "            ! gsutil cat $EXECUTE_OUTPUT\n",
+        "            artifact = EXECUTE_OUTPUT\n",
+        "            break\n",
+        "        !gsutil -q stat $GCP_RESOURCES\n",
+        "        if _exit_code == 0:\n",
+        "            ! gsutil cat $GCP_RESOURCES\n",
+        "            artifact = GCP_RESOURCES\n",
+        "            break\n",
+        "        !gsutil -q stat $EVALUATION_METRICS\n",
+        "        if _exit_code == 0:\n",
+        "            ! gsutil cat $EVALUATION_METRICS\n",
+        "            artifact = EVALUATION_METRICS\n",
+        "            break\n",
+        "\n",
+        "    return artifact\n",
+        "\n",
+        "\n",
+        "print(\"model-upload\")\n",
+        "artifacts = print_pipeline_output(job, \"model-upload\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "print(output)\n",
+        "output = json.loads(output[0])\n",
+        "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
+        "print(\"\\n\\n\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f431a9e6f025"
+      },
+      "source": [
+        "### Delete the pipeline job\n",
+        "\n",
+        "The method 'delete()' will delete the pipeline job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "00bf554abbc6"
+      },
+      "outputs": [],
+      "source": [
+        "job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3d183db57ae2"
+      },
+      "source": [
+        "### Deploy the model\n",
+        "\n",
+        "Next, you deploy the model to an endpoint:\n",
+        "\n",
+        "- Use the `model_id` obtained from the pipeline artifacts to instantiate a Vertex AI Model resource instance.\n",
+        "- Deploy the Vertex AI Model resource to a Vertex AI Endpoint resource.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "591ccc049ce5"
+      },
+      "outputs": [],
+      "source": [
+        "model = aiplatform.Model(model_id)\n",
+        "endpoint = model.deploy(\n",
+        "    accelerator_count=1,\n",
+        "    accelerator_type=aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_T4.name,\n",
+        "    machine_type=\"n1-standard-4\",\n",
+        ")\n",
+        "print(endpoint)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "edb781a92864"
+      },
+      "source": [
+        "### Make a prediction\n",
+        "\n",
+        "Finally, you make a prediction with the deployed model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "72d94012a987"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.predict([\"this is a test\"])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "delete_bucket = True\n",
+        "\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
+        "model.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI\n",
+        "\n",
+        "! rm -rf custom custom.tar.gz"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pipeline_templates_t5x.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_blip2.ipynb

@@ -0,0 +1,468 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - BLIP2\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_blip2.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_blip2.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_blip2.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [BLIP2](https://huggingface.co/Salesforce/blip2-opt-2.7b) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image.\n",
+        "# The model artifacts are embedded within the container, except for model weights which will be downloaded during deployment.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"blip2\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send images to get descriptions."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "19e8aeec969c"
+      },
+      "source": [
+        "### Image captioning"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"Salesforce/blip2-opt-2.7b\", task=\"image-to-text\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 10 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "display(image)\n",
+        "\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image)},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "01e11d85d504"
+      },
+      "source": [
+        "### VQA (Visual-Question-Answering)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "26018d961cf9"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"Salesforce/blip2-opt-2.7b\", task=\"visual-question-answering\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 10 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f19c342829fd"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\n",
+        "    \"https://media.newyorker.com/cartoons/63dc6847be24a6a76d90eb99/master/w_1160,c_limit/230213_a26611_838.jpg\"\n",
+        ")\n",
+        "display(image)\n",
+        "\n",
+        "question = \"Question: What are they doing? Answer:\"\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image), \"text\": question},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(question)\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "712eb9d0b336"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_blip2.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_blip_image_captioning.ipynb

@@ -0,0 +1,399 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - BLIP Image Captioning\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_blip_image_captioning.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_blip_image_captioning.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_blip_image_captioning.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [BLIP Image Captioning](https://huggingface.co/Salesforce/blip-image-captioning-base) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"blip-image-captioning\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send images to get descriptions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"Salesforce/blip-image-captioning-base\", task=\"image-to-text\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "display(image)\n",
+        "\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image)},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_blip_image_captioning.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_blip_vqa.ipynb

@@ -0,0 +1,401 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - BLIP VQA\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_blip_vqa.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_blip_vqa.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_blip_vqa.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [BLIP VQA](https://huggingface.co/Salesforce/blip-vqa-base) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"blip-vqa\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send images and questions to get answers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"Salesforce/blip-vqa-base\", task=\"visual-question-answering\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "display(image)\n",
+        "\n",
+        "question = \"Which cat is bigger?\"\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image), \"text\": question},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(question)\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_blip_vqa.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_clip.ipynb

@@ -0,0 +1,476 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - CLIP\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_clip.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_clip.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_clip.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [CLIP](https://huggingface.co/openai/clip-vit-base-patch32) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"clip\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "99f3c6b404b5"
+      },
+      "source": [
+        "### Zero-shot image classification"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"openai/clip-vit-base-patch32\", task=\"zero-shot-image-classification\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image1 = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "image2 = download_image(\"http://images.cocodataset.org/val2017/000000000285.jpg\")\n",
+        "grid = image_grid([image1, image2], 1, 2)\n",
+        "display(grid)\n",
+        "\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image1), \"text\": \"two cats\"},\n",
+        "    {\"image\": image_to_base64(image2), \"text\": \"a bear\"},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ddf9e9ec7b58"
+      },
+      "source": [
+        "### Image/text feature embedding"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8897bbac6887"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"openai/clip-vit-base-patch32\", task=\"feature-embedding\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9f854c45f8f3"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed after the above model deployment step succeeds and before you run the next step below. Otherwise you might see a ServiceUnavailable: 503 502:Bad Gateway error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2abd54335f36"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "# Extract feature embedding of images.\n",
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "display(image)\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image)},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "image_features = np.array(preds[0][\"image_features\"])\n",
+        "print(image_features.shape)\n",
+        "\n",
+        "# Extract feature embedding of texts.\n",
+        "instances = [\n",
+        "    {\"text\": \"two cats\"},\n",
+        "    {\"text\": \"hello world\"},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "text_features = np.array(preds[0][\"text_features\"])\n",
+        "print(text_features.shape)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "712eb9d0b336"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_clip.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb

@@ -0,0 +1,660 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "99c1c3fc2ca5"
+      },
+      "source": [
+        "# Vertex AI Model Garden - ControlNet\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3de7470326a2"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates finetuning the [ControlNet](https://huggingface.co/lllyasviel/ControlNet) with the [fusing/fill50k](https://huggingface.co/datasets/fusing/fill50k) dataset and deploying the model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Finetune the ControlNet model.\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for text-guided-image-to-image.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb671e75ca7b"
+      },
+      "source": [
+        "### Install dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dc8ee367fb42"
+      },
+      "outputs": [],
+      "source": [
+        "# Install gdown for downloading example training images.\n",
+        "!pip install gdown\n",
+        "# Install libs for generating conditioning images for ControlNet.\n",
+        "!pip install opencv-python"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5244aac3d929"
+      },
+      "source": [
+        "Restart the notebook kernel after installs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "567212ff53a6"
+      },
+      "outputs": [],
+      "source": [
+        "import IPython\n",
+        "\n",
+        "app = IPython.Application.instance()\n",
+        "app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bb7adab99e41"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c460088b873"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "855d6b96f291"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account you created in step-5 above, it's like \"<account_name>@<project>.iam.gserviceaccount.com\"\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e828eb320337"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "12cd25839741"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2cc825514deb"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b42bd4fa2b2d"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built training docker image. It contains training scripts and models.\n",
+        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-train:latest\"\n",
+        "\n",
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c250872074f"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "354da31189dc"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import cv2\n",
+        "import numpy as np\n",
+        "import requests\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def canny(image):\n",
+        "    image = np.array(image)\n",
+        "    image = cv2.Canny(image, 100, 200)\n",
+        "    image = image[:, :, None]\n",
+        "    image = np.concatenate([image, image, image], axis=2)\n",
+        "    image = Image.fromarray(image)\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"controlnet\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e70e3519ff8b"
+      },
+      "source": [
+        "## Finetune with fill50k dataset"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0dc65d8f0689"
+      },
+      "source": [
+        "This section uses the [fusing/fill50k](https://huggingface.co/datasets/fusing/fill50k) dataset to finetune the ControlNet model.\n",
+        "\n",
+        "The job will run on 1 A100 GPU and take ~7 hours to finish 1 epoch of training.\n",
+        "\n",
+        "The ControlNet model will be saved after the finetuning job finishs and it can be loaded to run inference later."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65467b361315"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-trained stable diffusion model to be loaded.\n",
+        "stable_diffusion_model_id = \"runwayml/stable-diffusion-v1-5\"\n",
+        "# The datase id to be loaded.\n",
+        "dataset_id = \"fusing/fill50k\"\n",
+        "# The output path.\n",
+        "output_dir = f\"/gcs/{GCS_BUCKET}/controlnet/output\"\n",
+        "# The training steps. If provided, it overrides num_train_epochs. Set it to None to use num_train_epochs only.\n",
+        "max_train_steps = 10  # @param {type:\"integer\"}\n",
+        "# The training epochs. Set it to a bigger number, like 10, to make training converge better.\n",
+        "num_train_epochs = 1  # @param {type:\"integer\"}\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "machine_type = \"a2-highgpu-1g\"\n",
+        "num_nodes = 1\n",
+        "gpu_type = \"NVIDIA_TESLA_A100\"\n",
+        "num_gpus = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = create_job_name(\"controlnet\")\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "# See https://github.com/huggingface/diffusers/blob/main/examples/controlnet/train_controlnet.py\n",
+        "# for a full list of training arguments.\n",
+        "model = job.run(\n",
+        "    args=[\n",
+        "        f\"--num_machines={num_nodes}\",\n",
+        "        f\"--num_processes={num_gpus}\",\n",
+        "        \"--machine_rank=0\",\n",
+        "        \"--mixed_precision=no\",\n",
+        "        \"--gpu_ids=all\",\n",
+        "        \"--same_network\",\n",
+        "        \"--dynamo_backend=no\",\n",
+        "        \"controlnet/train_controlnet.py\",\n",
+        "        \"--tracker_project_name=train_controlnet\",\n",
+        "        f\"--pretrained_model_name_or_path={stable_diffusion_model_id}\",\n",
+        "        f\"--output_dir={output_dir}\",\n",
+        "        f\"--dataset_name={dataset_id}\",\n",
+        "        f\"--max_train_steps={max_train_steps}\",\n",
+        "        f\"--num_train_epochs={num_train_epochs}\",\n",
+        "        \"--resolution=512\",\n",
+        "        \"--learning_rate=1e-5\",\n",
+        "        \"--train_batch_size=2\",\n",
+        "        \"--checkpointing_steps=50000\",\n",
+        "        \"--checkpoints_total_limit=1\",\n",
+        "    ],\n",
+        "    replica_count=num_nodes,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=gpu_type,\n",
+        "    accelerator_count=num_gpus,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bf7f82732e61"
+      },
+      "source": [
+        "## Upload and Deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1cc26e68d7b0"
+      },
+      "source": [
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd7b56421392"
+      },
+      "source": [
+        "### Pre-trained canny model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6d331b1ea337"
+      },
+      "source": [
+        "Deploy the pre-trained [lllyasviel/sd-controlnet-canny](https://huggingface.co/lllyasviel/sd-controlnet-canny) model for the text-guided image-to-image task. When deployed on one V100 GPU, the average inference time of a request is ~15 seconds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bf55e38815dc"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"lllyasviel/sd-controlnet-canny\", task=\"controlnet\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4ab04da3ec9a"
+      },
+      "outputs": [],
+      "source": [
+        "init_image = download_image(\n",
+        "    \"https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_canny_1.png\"\n",
+        ")\n",
+        "display(init_image)\n",
+        "image = canny(init_image)\n",
+        "display(image)\n",
+        "\n",
+        "instances = [\n",
+        "    {\n",
+        "        \"prompt\": \"bird\",\n",
+        "        \"image\": image_to_base64(image),\n",
+        "    },\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "af21a3cff1e0"
+      },
+      "source": [
+        "Clean up resources:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "911406c1561e"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c1e51f764a60"
+      },
+      "source": [
+        "### Custom finetuned fill50k model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fa686a54047c"
+      },
+      "source": [
+        "Deploy the finetuned fill50k model above for the text-guided image-to-image task. When deployed on one V100 GPU, the averaged inference time of a request is ~15 seconds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65e32356fbd1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/controlnet/output\", task=\"controlnet\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "83a50fd4a1ed"
+      },
+      "outputs": [],
+      "source": [
+        "init_image = download_image(\n",
+        "    \"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/controlnet_training/conditioning_image_1.png\"\n",
+        ")\n",
+        "display(init_image)\n",
+        "\n",
+        "instances = [\n",
+        "    {\n",
+        "        \"prompt\": \"red circle with green background\",\n",
+        "        \"image\": image_to_base64(init_image, format=\"PNG\"),\n",
+        "    },\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ed3795d474b9"
+      },
+      "source": [
+        "Clean up resources:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b53b883257b4"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_controlnet.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb

@@ -0,0 +1,424 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - InstructPix2Pix\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [InstructPix2Pix](https://huggingface.co/timbrooks/instruct-pix2pix) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for text-guided image-to-image.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"instruct-pix2pix\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c277da31bde6"
+      },
+      "source": [
+        "### Text-guided image-to-image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a5a86996222c"
+      },
+      "source": [
+        "Deploy the InstructPix2Pix model for the text-guided image-to-image task.\n",
+        "\n",
+        "Once deployed, you can send prompts to the endpoint to generated images.\n",
+        "\n",
+        "When deployed on one V100 GPU, the averaged inference time of a request is ~15 seconds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"timbrooks/instruct-pix2pix\", task=\"instruct-pix2pix\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "init_image = download_image(\n",
+        "    \"https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png\"\n",
+        ")\n",
+        "display(init_image)\n",
+        "instances = [\n",
+        "    {\n",
+        "        \"prompt\": \"Add fire to the mountain\",\n",
+        "        \"image\": image_to_base64(init_image),\n",
+        "    },\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_instructpix2pix.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_layoutml_document_qa.ipynb

@@ -0,0 +1,403 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - LayoutML Document QA\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_layoutml_document_qa.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_layoutml_document_qa.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_layoutml_document_qa.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [LayoutML](https://huggingface.co/impira/layoutlm-document-qa) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content)).convert(\"RGB\")\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"layoutml\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send document images and questions to get answers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"impira/layoutlm-document-qa\", task=\"document-question-answering\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\n",
+        "    \"https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/invoice.png\"\n",
+        ")\n",
+        "display(image)\n",
+        "\n",
+        "question = \"What is the name of the signer?\"\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image), \"text\": \"\"},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(question)\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_layoutml_document_qa.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_owlvit.ipynb

@@ -0,0 +1,418 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - OWL-ViT\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_owlvit.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_owlvit.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_owlvit.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [OWL-ViT](https://huggingface.co/google/owlvit-base-patch32) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import matplotlib.patches as patches\n",
+        "import matplotlib.pyplot as plt\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def draw_image_with_boxes(image, boxes):\n",
+        "    fig, ax = plt.subplots()\n",
+        "    plt.axis(\"off\")\n",
+        "    ax.imshow(image)\n",
+        "    if len(boxes) == 0:\n",
+        "        return\n",
+        "    boxes = boxes[\"boxes\"]\n",
+        "    for box in boxes:\n",
+        "        x, y = box[\"xmin\"], box[\"ymin\"]\n",
+        "        width, height = box[\"xmax\"] - x, box[\"ymax\"] - y\n",
+        "        rect = patches.Rectangle(\n",
+        "            (x, y), width, height, linewidth=2, edgecolor=\"yellow\", facecolor=\"none\"\n",
+        "        )\n",
+        "        ax.add_patch(rect)\n",
+        "    plt.show()\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"owl-vit\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send images and object texts to get bounding boxes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"google/owlvit-base-patch32\", task=\"zero-shot-object-detection\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image), \"text\": \"cat\"},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "draw_image_with_boxes(image, preds[0])\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_owlvit.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb

@@ -0,0 +1,760 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "99c1c3fc2ca5"
+      },
+      "source": [
+        "# Vertex AI Model Garden - Stable Diffusion V1.5\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 GPU notebook with preinstalled HuggingFace/transformer libraries is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3de7470326a2"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates running local inference for [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) on either [Colab](https://colab.research.google.com) or [Vertex AI Workbench](https://cloud.google.com/vertex-ai-workbench). This notebook also demonstrates finetuning runwayml/stable-diffusion-v1-5 with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth) and deploying it on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Run local predictions for text-to-image and text-guided-image-to-image with serving dockers.\n",
+        "- Finetune the stable-diffusion-v1.5 model with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth).\n",
+        "- Upload the model to [Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model to a [Vertex AI Endpoint resource](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for text-to-image and text-guided-image-to-image.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ioensNKM8ned"
+      },
+      "source": [
+        "### Setup notebook"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "#### Colab only\n",
+        "Run the following commands for Colab and skip this section if you are using Workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()\n",
+        "    ! pip3 install --upgrade pip\n",
+        "    ! pip3 install torchvision==0.14.1\n",
+        "    ! pip3 install transformers==4.27.1\n",
+        "    ! pip3 install diffusers==0.15.1\n",
+        "    ! pip3 install datasets==2.9.0\n",
+        "    ! pip3 install accelerate==0.18.0\n",
+        "    ! pip3 install triton==2.0.0.dev20221120\n",
+        "    ! pip3 install xformers==0.0.16\n",
+        "    # Install gdown for downloading example training images.\n",
+        "    ! pip3 install gdown\n",
+        "    # Remove wrong cublas version.\n",
+        "    ! pip3 uninstall nvidia_cublas_cu11 --yes\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb671e75ca7b"
+      },
+      "source": [
+        "#### Workbench only\n",
+        "1.   Follow [this link](https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb) to deploy the notebook to a Vertex AI Workbench Instance.\n",
+        "2.   Select `Create a new Notebook`.\n",
+        "3.   Click `Advanced Options`.\n",
+        "4.   In the **Environment** tab, select `Debian 10` for **Operating System** and select `Custom Container` for **Environment**.\n",
+        "5.   Set `Docker container image` to `us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/transformers-notebook`.\n",
+        "6.   Under **Machine configuration**, select 1 `T4` GPU and select `Install NVIDIA GPU driver automatically for me`.\n",
+        "7.   Click `Create` to create the Vertex AI Workbench instance."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bb7adab99e41"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c460088b873"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "855d6b96f291"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e828eb320337"
+      },
+      "source": [
+        "Initialize Vertex-AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "12cd25839741"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2cc825514deb"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b42bd4fa2b2d"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built training docker image. It contains training scripts and models.\n",
+        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-train:latest\"\n",
+        "\n",
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c250872074f"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "354da31189dc"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import glob\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "import torch\n",
+        "from google.cloud import aiplatform, storage\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"stable-diffusion-v1\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-{task}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
+        "    )\n",
+        "    return model, endpoint\n",
+        "\n",
+        "\n",
+        "def get_bucket_and_blob_name(filepath):\n",
+        "    # The gcs path is of the form gs://<bucket-name>/<blob-name>\n",
+        "    gs_suffix = filepath.split(\"gs://\", 1)[1]\n",
+        "    return tuple(gs_suffix.split(\"/\", 1))\n",
+        "\n",
+        "\n",
+        "def upload_local_dir_to_gcs(local_dir_path, gcs_dir_path):\n",
+        "    \"\"\"Uploads files in a local directory to a GCS directory.\"\"\"\n",
+        "    client = storage.Client()\n",
+        "    bucket_name = gcs_dir_path.split(\"/\")[2]\n",
+        "    bucket = client.get_bucket(bucket_name)\n",
+        "    for local_file in glob.glob(local_dir_path + \"/**\"):\n",
+        "        if not os.path.isfile(local_file):\n",
+        "            continue\n",
+        "        filename = local_file[1 + len(local_dir_path) :]\n",
+        "        gcs_file_path = os.path.join(gcs_dir_path, filename)\n",
+        "        _, blob_name = get_bucket_and_blob_name(gcs_file_path)\n",
+        "        blob = bucket.blob(blob_name)\n",
+        "        blob.upload_from_filename(local_file)\n",
+        "        print(\"Copied {} to {}.\".format(local_file, gcs_file_path))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e8a42fa49305"
+      },
+      "source": [
+        "## Run inferences locally"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1d5ebc91c786"
+      },
+      "source": [
+        "### Text-to-image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d39ed8c97cc5"
+      },
+      "outputs": [],
+      "source": [
+        "from diffusers import StableDiffusionPipeline\n",
+        "\n",
+        "model_id = \"runwayml/stable-diffusion-v1-5\"\n",
+        "pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)\n",
+        "pipe = pipe.to(\"cuda\")\n",
+        "\n",
+        "prompt = \"a photo of an astronaut riding a horse on mars\"\n",
+        "image = pipe(prompt).images[0]\n",
+        "\n",
+        "display(image)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5aed5ed7b6f6"
+      },
+      "source": [
+        "### Text-guided image-to-image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "faadabb7728f"
+      },
+      "outputs": [],
+      "source": [
+        "from diffusers import StableDiffusionImg2ImgPipeline\n",
+        "\n",
+        "device = \"cuda\"\n",
+        "model_id_or_path = \"runwayml/stable-diffusion-v1-5\"\n",
+        "pipe = StableDiffusionImg2ImgPipeline.from_pretrained(\n",
+        "    model_id_or_path, torch_dtype=torch.float16\n",
+        ")\n",
+        "pipe = pipe.to(device)\n",
+        "\n",
+        "url = \"https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg\"\n",
+        "\n",
+        "response = requests.get(url)\n",
+        "init_image = Image.open(BytesIO(response.content)).convert(\"RGB\")\n",
+        "init_image = init_image.resize((768, 512))\n",
+        "\n",
+        "prompt = \"A fantasy landscape, trending on artstation\"\n",
+        "\n",
+        "images = pipe(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e70e3519ff8b"
+      },
+      "source": [
+        "## Finetune with Dreambooth"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0dc65d8f0689"
+      },
+      "source": [
+        "This section uses [dreambooth](https://dreambooth.github.io/) to finetune the [stable-diffusion-v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with [5 dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ) to personalize the text-to-image model.\n",
+        "\n",
+        "It finetunes both text encoder and unet of the stable diffusion model up to 800 steps. The whole finetuning job takes 30 minutes to finish using 1 A100 GPU.\n",
+        "\n",
+        "The full model will be saved after the finetuning job finishs and it can be loaded by the [StableDiffusionPipeline](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img) to run inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "34048707df5c"
+      },
+      "outputs": [],
+      "source": [
+        "# Download example training images.\n",
+        "!gdown --folder https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ\n",
+        "\n",
+        "# Upload data to Cloud Storage bucket.\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog\")\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog_class\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "969cfeb79317"
+      },
+      "source": [
+        "**NOTE**: If the upload step fails due to lacking of permission, you need to [grant the Storage Object Admin role](https://cloud.google.com/storage/docs/access-control/using-iam-permissions) for the Cloud account of the notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65467b361315"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-trained model to be loaded.\n",
+        "model_id = \"runwayml/stable-diffusion-v1-5\"\n",
+        "\n",
+        "# Input and output path.\n",
+        "instance_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/dog\"\n",
+        "class_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/dog_class\"\n",
+        "output_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/output\"\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "machine_type = \"a2-highgpu-1g\"\n",
+        "num_nodes = 1\n",
+        "gpu_type = \"NVIDIA_TESLA_A100\"\n",
+        "num_gpus = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = create_job_name(\"dreambooth-stable-diffusion\")\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "# See https://github.com/huggingface/diffusers/blob/v0.14.0/examples/dreambooth/train_dreambooth.py#L75\n",
+        "# for a full list of training arguments.\n",
+        "model = job.run(\n",
+        "    args=[\n",
+        "        \"dreambooth/train_dreambooth.py\",\n",
+        "        f\"--pretrained_model_name_or_path={model_id}\",\n",
+        "        \"--train_text_encoder\",\n",
+        "        f\"--instance_data_dir={instance_dir}\",\n",
+        "        f\"--class_data_dir={class_dir}\",\n",
+        "        f\"--output_dir={output_dir}\",\n",
+        "        \"--with_prior_preservation\",\n",
+        "        \"--prior_loss_weight=1.0\",\n",
+        "        \"--instance_prompt='a photo of sks dog'\",\n",
+        "        \"--class_prompt='a photo of dog'\",\n",
+        "        \"--resolution=512\",\n",
+        "        \"--train_batch_size=1\",\n",
+        "        \"--gradient_checkpointing\",\n",
+        "        \"--learning_rate=2e-6\",\n",
+        "        \"--lr_scheduler=constant\",\n",
+        "        \"--lr_warmup_steps=0\",\n",
+        "        \"--num_class_images=200\",\n",
+        "        \"--max_train_steps=800\",\n",
+        "    ],\n",
+        "    replica_count=num_nodes,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=gpu_type,\n",
+        "    accelerator_count=num_gpus,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bf7f82732e61"
+      },
+      "source": [
+        "## Upload and Deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1cc26e68d7b0"
+      },
+      "source": [
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd7b56421392"
+      },
+      "source": [
+        "### Text-to-image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6d331b1ea337"
+      },
+      "source": [
+        "Deploy the stable diffusion model for the text-to-image task.\n",
+        "\n",
+        "Once deployed, you can send a batch of text prompts to the endpoint to generated images.\n",
+        "\n",
+        "When deployed on one V100 GPU, the averaged inference time of a request is ~15 seconds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bf55e38815dc"
+      },
+      "outputs": [],
+      "source": [
+        "# Set the model_id to \"runwayml/stable-diffusion-v1-5\" to load the OSS pre-trained model.\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/dreambooth/output\", task=\"text-to-image\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4ab04da3ec9a"
+      },
+      "outputs": [],
+      "source": [
+        "instances = [\n",
+        "    {\"prompt\": \"a squirrel in Picasso style\"},\n",
+        "    {\"prompt\": \"a dog in Picasso style\"},\n",
+        "    {\"prompt\": \"a cat in Picasso style\"},\n",
+        "    {\"prompt\": \"a deer in Picasso style\"},\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "image_grid(images)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "af21a3cff1e0"
+      },
+      "source": [
+        "Clean up resources:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "911406c1561e"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c1e51f764a60"
+      },
+      "source": [
+        "### Text-guided image-to-image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fa686a54047c"
+      },
+      "source": [
+        "Deploy the stable diffusion model for the text-guided image-to-image task."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65e32356fbd1"
+      },
+      "outputs": [],
+      "source": [
+        "# Set the model_id to a GCS path, like \"gs://GCS_BUCKET/dreambooth/output\", to load the dreambooth finetuned model above.\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"runwayml/stable-diffusion-v1-5\", task=\"image-to-image\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "SsjYFLvNymc0"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "83a50fd4a1ed"
+      },
+      "outputs": [],
+      "source": [
+        "init_image = download_image(\n",
+        "    \"https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg\"\n",
+        ")\n",
+        "display(init_image)\n",
+        "instances = [\n",
+        "    {\n",
+        "        \"prompt\": \"A fantasy landscape, trending on artstation\",\n",
+        "        \"image\": image_to_base64(init_image),\n",
+        "    },\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ed3795d474b9"
+      },
+      "source": [
+        "Clean up resources:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b53b883257b4"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_stable_diffusion.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb

@@ -0,0 +1,667 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1e9c07efb6ac"
+      },
+      "source": [
+        "# Vertex AI Model Garden - Stable Diffusion Inpainting\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 GPU notebook with preinstalled HuggingFace/transformer libraries is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd8433ec804a"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates running local inference for [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) on either [Colab](https://colab.research.google.com) or [Vertex AI Workbench](https://cloud.google.com/vertex-ai-workbench). This notebook also demonstrates finetuning runwayml/stable-diffusion-inpainting with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth) and deploying it on Vertex-AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Run local predictions for image-inpainting with serving dockers.\n",
+        "- Finetune the stable-diffusion-inpainting model with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth).\n",
+        "- Upload the model to [Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model to a [Vertex AI Endpoint resource](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image-inpainting.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Gl3bjJsV3k4J"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CaCslNQE37P_"
+      },
+      "source": [
+        "### Setup notebook"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb671e75ca7b"
+      },
+      "source": [
+        "#### Colab only\n",
+        "Run the following commands for Colab and skip this section if you are using Workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dc8ee367fb42"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()\n",
+        "    ! pip3 install --upgrade pip\n",
+        "    ! pip3 install torchvision==0.14.1\n",
+        "    ! pip3 install transformers==4.27.1\n",
+        "    ! pip3 install diffusers==0.15.1\n",
+        "    ! pip3 install datasets==2.9.0\n",
+        "    ! pip3 install accelerate==0.18.0\n",
+        "    ! pip3 install triton==2.0.0.dev20221120\n",
+        "    ! pip3 install xformers==0.0.16\n",
+        "    # Install gdown for downloading example training images.\n",
+        "    ! pip3 install gdown\n",
+        "    # Remove wrong cublas version.\n",
+        "    ! pip3 uninstall nvidia_cublas_cu11 --yes\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "JaY__7zz3uWk"
+      },
+      "source": [
+        "#### Workbench only\n",
+        "1.   Follow [this link](https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb) to deploy the notebook to a Vertex AI Workbench Instance.\n",
+        "2.   Select `Create a new Notebook`.\n",
+        "3.   Click `Advanced Options`.\n",
+        "4.    **Environment** tab, select `Debian 10` for **Operating System** and select `Custom Container` for **Environment**.\n",
+        "5.   Set `Docker container image` to `us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/transformers-notebook`.\n",
+        "6.   Under **Machine configuration**, select 1 `T4` GPU and select `Install NVIDIA GPU driver automatically for me`.\n",
+        "7.   Click `Create` to create the Vertex AI Workbench instance."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bb7adab99e41"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c460088b873"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "855d6b96f291"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output.\n",
+        "# Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model.\n",
+        "# The service account looks like:\n",
+        "# '<account_name>@<project>.iam.gserviceaccount.com'\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e828eb320337"
+      },
+      "source": [
+        "Initialize Vertex-AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "12cd25839741"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2cc825514deb"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b42bd4fa2b2d"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built training docker image. It contains training scripts and models.\n",
+        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-train:latest\"\n",
+        "\n",
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-serve\""
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c250872074f"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8759e624ebc0"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import glob\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform, storage\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"stable-diffusion-inpainting\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
+        "    )\n",
+        "    return model, endpoint\n",
+        "\n",
+        "\n",
+        "def get_bucket_and_blob_name(filepath):\n",
+        "    # The gcs path is of the form gs://<bucket-name>/<blob-name>\n",
+        "    gs_suffix = filepath.split(\"gs://\", 1)[1]\n",
+        "    return tuple(gs_suffix.split(\"/\", 1))\n",
+        "\n",
+        "\n",
+        "def upload_local_dir_to_gcs(local_dir_path, gcs_dir_path):\n",
+        "    \"\"\"Uploads files in a local directory to a GCS directory.\"\"\"\n",
+        "    client = storage.Client()\n",
+        "    bucket_name = gcs_dir_path.split(\"/\")[2]\n",
+        "    bucket = client.get_bucket(bucket_name)\n",
+        "    for local_file in glob.glob(local_dir_path + \"/**\"):\n",
+        "        if not os.path.isfile(local_file):\n",
+        "            continue\n",
+        "        filename = local_file[1 + len(local_dir_path) :]\n",
+        "        gcs_file_path = os.path.join(gcs_dir_path, filename)\n",
+        "        _, blob_name = get_bucket_and_blob_name(gcs_file_path)\n",
+        "        blob = bucket.blob(blob_name)\n",
+        "        blob.upload_from_filename(local_file)\n",
+        "        print(\"Copied {} to {}.\".format(local_file, gcs_file_path))"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Wx18bDXC2XPR"
+      },
+      "source": [
+        "## Run inferences locally"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OSYVyAvu2mfN"
+      },
+      "source": [
+        "### Image-inpainting"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "CZ2RkKT32Zj2"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "from diffusers import StableDiffusionInpaintPipeline\n",
+        "\n",
+        "image_url = \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png\"\n",
+        "image_response = requests.get(image_url)\n",
+        "init_image = Image.open(BytesIO(image_response.content)).convert(\"RGB\")\n",
+        "display(init_image)\n",
+        "\n",
+        "mask_url = \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png\"\n",
+        "mask_response = requests.get(mask_url)\n",
+        "mask_image = Image.open(BytesIO(mask_response.content)).convert(\"RGB\")\n",
+        "\n",
+        "pipe = StableDiffusionInpaintPipeline.from_pretrained(\n",
+        "    \"runwayml/stable-diffusion-inpainting\",\n",
+        "    revision=\"fp16\",\n",
+        "    torch_dtype=torch.float16,\n",
+        ")\n",
+        "pipe.to(\"cuda\")\n",
+        "\n",
+        "prompt = \"Face of a yellow cat, high resolution, sitting on a park bench\"\n",
+        "images = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e70e3519ff8b"
+      },
+      "source": [
+        "## Finetune with Dreambooth"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f560edbf96c6"
+      },
+      "source": [
+        "This section uses [dreambooth](https://dreambooth.github.io/) to finetune the [stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) model with [5 dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ) to personalize the model.\n",
+        "\n",
+        "It finetunes both text encoder and unet of the stable diffusion model up to 800 steps. The whole finetuning job takes 30 minutes to finish using 1 A100 GPU.\n",
+        "\n",
+        "The full model will be saved after the finetuning job finishs and it can be loaded by the [StableDiffusionInpaintPipeline](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/inpaint) to run inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "34048707df5c"
+      },
+      "outputs": [],
+      "source": [
+        "# Download example training images.\n",
+        "!gdown --folder https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ\n",
+        "\n",
+        "# Upload data to Cloud Storage bucket.\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog\")\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog_class\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f6d5a05592e1"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-trained model to be loaded.\n",
+        "model_id = \"runwayml/stable-diffusion-inpainting\"\n",
+        "\n",
+        "# Input and output path.\n",
+        "instance_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/dog\"\n",
+        "class_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/dog_class\"\n",
+        "output_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/output\"\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "machine_type = \"a2-highgpu-1g\"\n",
+        "num_nodes = 1\n",
+        "gpu_type = \"NVIDIA_TESLA_A100\"\n",
+        "num_gpus = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = create_job_name(\"dreambooth-stable-diffusion-inpainting\")\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "# See https://github.com/huggingface/diffusers/blob/v0.14.0/examples/research_projects/dreambooth_inpaint/train_dreambooth_inpaint.py#L83\n",
+        "# for a full list of training arguments.\n",
+        "model = job.run(\n",
+        "    args=[\n",
+        "        \"research_projects/dreambooth_inpaint/train_dreambooth_inpaint.py\",\n",
+        "        f\"--pretrained_model_name_or_path={model_id}\",\n",
+        "        \"--train_text_encoder\",\n",
+        "        f\"--instance_data_dir={instance_dir}\",\n",
+        "        f\"--class_data_dir={class_dir}\",\n",
+        "        f\"--output_dir={output_dir}\",\n",
+        "        \"--with_prior_preservation\",\n",
+        "        \"--prior_loss_weight=1.0\",\n",
+        "        \"--instance_prompt='a photo of sks dog'\",\n",
+        "        \"--class_prompt='a photo of dog'\",\n",
+        "        \"--resolution=512\",\n",
+        "        \"--train_batch_size=1\",\n",
+        "        \"--gradient_checkpointing\",\n",
+        "        \"--learning_rate=2e-6\",\n",
+        "        \"--lr_scheduler=constant\",\n",
+        "        \"--lr_warmup_steps=0\",\n",
+        "        \"--num_class_images=200\",\n",
+        "        \"--max_train_steps=800\",\n",
+        "    ],\n",
+        "    replica_count=num_nodes,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=gpu_type,\n",
+        "    accelerator_count=num_gpus,\n",
+        ")"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "90d3c379090e"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1cc26e68d7b0"
+      },
+      "source": [
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b8bb7d198315"
+      },
+      "source": [
+        "### Image-inpainting"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "79b66382f849"
+      },
+      "source": [
+        "Deploy the stable diffusion model for the image-inpainting task.\n",
+        "\n",
+        "Once deployed, you can send prompts to the endpoint to generated images.\n",
+        "\n",
+        "When deployed on one V100 GPU, the averaged inference time of a request is ~15 seconds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a881564da1d8"
+      },
+      "outputs": [],
+      "source": [
+        "# Set the model_id to \"runwayml/stable-diffusion-inpainting\" to load the OSS pre-trained model.\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/dreambooth/output\", task=\"image-inpainting\"\n",
+        ")"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ca1761afb66f"
+      },
+      "outputs": [],
+      "source": [
+        "img_url = \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/bertrand-gabioud-CpuFzIsHYJ0.png\"\n",
+        "mask_url = \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/bertrand-gabioud-CpuFzIsHYJ0_mask.png\"\n",
+        "init_image = download_image(img_url).resize((512, 512))\n",
+        "mask_image = download_image(mask_url).resize((512, 512))\n",
+        "display(init_image)\n",
+        "display(mask_image)\n",
+        "\n",
+        "instances = [\n",
+        "    {\n",
+        "        \"prompt\": \"a tree, high resolution, in front of high buildings\",\n",
+        "        \"image\": image_to_base64(init_image),\n",
+        "        \"mask_image\": image_to_base64(mask_image),\n",
+        "    },\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f12f8d9c2786"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "911406c1561e"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_stable_diffusion_inpainting.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_timm.ipynb

@@ -0,0 +1,753 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ApNHZJmT2AMH"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "YfxrFG052AMI"
+      },
+      "source": [
+        "# Vertex AI Model Garden - TIMM\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_timm.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_timm.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_timm.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "76BCoQcm2AMJ"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates running local inference using the [timm](https://github.com/rwightman/pytorch-image-models) library, finetuning the PyTorch [timm models](https://github.com/huggingface/pytorch-image-models#models), and deploying the models on [Vertex AI](https://cloud.google.com/vertex-ai).\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Setup environment.\n",
+        "- Run inference locally using the timm library.\n",
+        "- Create a custom training job on Vertex AI to train or finetune a model.\n",
+        "- Deploy the model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9iU1NKfh2AMJ"
+      },
+      "source": [
+        "## Setup environment"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7l3GN-QL2AMJ"
+      },
+      "source": [
+        "### Setup cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project). Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage.\n",
+        "\n",
+        "1. [Enable Artifact Registry](https://cloud.google.com/artifact-registry/docs/enable-service) and [create a repository](https://cloud.google.com/artifact-registry/docs/repositories/create-repos) for storing docker images.\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hyAQXmgf2AMK"
+      },
+      "source": [
+        "### Setup required libraries\n",
+        "\n",
+        "It's highly recommended to run this notebook on [Vertex AI workbench](https://cloud.google.com/vertex-ai-workbench), where you don't need to manually install any additional libraries.\n",
+        "\n",
+        "If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk) and [gsutil](https://cloud.google.com/storage/docs/gsutil_install)."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1f36f4b5c3"
+      },
+      "source": [
+        "### Install libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cb041d87f50a"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install timm"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-uF7Kb112AMK"
+      },
+      "source": [
+        "### Colab Only\n",
+        "Run the following commands for colab and skip this section if you use workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2lP6dnfy2AMK"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)\n",
+        "\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fo65Wg9Y2AMK"
+      },
+      "source": [
+        "### Setup environment variables\n",
+        "\n",
+        "This notebook supports models in https://huggingface.co/docs/timm/models.\n",
+        "\n",
+        "You can also run\n",
+        "`python -c \"from timm import list_models; print(list_models(pretrained=True))\"`\n",
+        "locally to see all pretrained models.\n",
+        "\n",
+        "The following models have been manually verified to work with this notebook:\n",
+        "\n",
+        "* vit_tiny_patch16_224\n",
+        "* beit_base_patch16_224\n",
+        "* deit3_small_patch16_224\n",
+        "* efficientnet_b2\n",
+        "* mobilenetv2_100\n",
+        "* resnet50\n",
+        "* resnest50d\n",
+        "* convnext_base\n",
+        "* cspdarknet53\n",
+        "* inception_v4"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3msH2i5V2AMK"
+      },
+      "outputs": [],
+      "source": [
+        "# The cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "# The region for running jobs.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The model you want to train and serve. Please select a model from the verified model list above.\n",
+        "# We use a ViT model as the example.\n",
+        "MODEL_NAME = \"vit_tiny_patch16_224\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket name without gs:// prefix for training outputs.\n",
+        "# For example: test_bucket\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model. It looks like:\n",
+        "# '<account_name>@<project>.iam.gserviceaccount.com'\n",
+        "# Follow step 6 above to create this account.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "14a500024b7b"
+      },
+      "source": [
+        "## Run local inference\n",
+        "\n",
+        "This section runs local inference on an image using the model chosen in above section."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "54859170c1ad"
+      },
+      "source": [
+        "### Import libraries\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7505a2bf3897"
+      },
+      "outputs": [],
+      "source": [
+        "import timm\n",
+        "import torch\n",
+        "from PIL import Image\n",
+        "from timm.data import resolve_data_config\n",
+        "from timm.data.transforms_factory import create_transform"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "17e6d8a0dac3"
+      },
+      "source": [
+        "### Load a pretrained model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8b6bbe928998"
+      },
+      "outputs": [],
+      "source": [
+        "model = timm.create_model(MODEL_NAME, pretrained=True)\n",
+        "model.eval()"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f2ce8fa5439"
+      },
+      "source": [
+        "### Load and preprocess the image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6390302c9761"
+      },
+      "outputs": [],
+      "source": [
+        "config = resolve_data_config({}, model=model)\n",
+        "transform = create_transform(**config)\n",
+        "\n",
+        "# The example downloads a test image. You can upload and use your own images\n",
+        "# by changing IMAGE_FILENAME.\n",
+        "! wget https://github.com/pytorch/hub/raw/master/images/dog.jpg -O test.jpg\n",
+        "IMAGE_FILENAME = \"test.jpg\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# You can also copy over images stored in a GCS bucket with the line below.\n",
+        "# ! gsutil cp \"gs://path/to/image\" \"test.jpg\"\n",
+        "\n",
+        "img = Image.open(IMAGE_FILENAME).convert(\"RGB\")\n",
+        "tensor = transform(img).unsqueeze(0)  # transform and add batch dimension\n",
+        "display(img)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8a6e2ea460ad"
+      },
+      "source": [
+        "### Get the model predictions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0a7a666a0aef"
+      },
+      "outputs": [],
+      "source": [
+        "with torch.no_grad():\n",
+        "    out = model(tensor)\n",
+        "probabilities = torch.nn.functional.softmax(out[0], dim=0)\n",
+        "print(probabilities.shape)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "691139fc5789"
+      },
+      "source": [
+        "### Get the top-5 predictions class names"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "147249af5dec"
+      },
+      "outputs": [],
+      "source": [
+        "# Get imagenet class mappings\n",
+        "url, filename = (\n",
+        "    \"https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt\",\n",
+        "    \"imagenet_classes.txt\",\n",
+        ")\n",
+        "urllib.request.urlretrieve(url, filename)\n",
+        "with open(\"imagenet_classes.txt\") as f:\n",
+        "    categories = [s.strip() for s in f.readlines()]"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a8740b668da6"
+      },
+      "source": [
+        "### Print top categories per image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9f18bcd806f2"
+      },
+      "outputs": [],
+      "source": [
+        "top5_prob, top5_catid = torch.topk(probabilities, 5)\n",
+        "for i in range(top5_prob.size(0)):\n",
+        "    print(categories[top5_catid[i]], top5_prob[i].item())\n",
+        "# prints class names and probabilities like:\n",
+        "# [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4120d1585355"
+      },
+      "source": [
+        "## Run training jobs\n",
+        "\n",
+        "This section runs a regular training job or a hyperparameter tuning job on Vertex AI.\n",
+        "\n",
+        "Before creating a training job, you need to prepare the dataset for training and evaluation.\n",
+        "\n",
+        "For example, you can use [ImageNet-1K](https://huggingface.co/datasets/imagenet-1k) held on a Cloud Storage bucket as the input dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qy4gKksX2AMK"
+      },
+      "outputs": [],
+      "source": [
+        "# The prebuilt training docker uri.\n",
+        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-timm-train\"\n",
+        "\n",
+        "# The path to data directory on Cloud Storage without gs:// prefix.\n",
+        "# In the form of: <bucket-name>/path-to-data\n",
+        "GCS_DATA_DIR = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0DnlJhO72AMK"
+      },
+      "source": [
+        "### Create a training job on Vertex AI\n",
+        "\n",
+        "This section creates a training job on Vertex AI. If you want to create a hyperparameter tuning job instead, you can skip to the next section."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1R5JWJGS2AML"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "# Init common setup.\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)\n",
+        "\n",
+        "# Input and output path.\n",
+        "data_dir = f\"/gcs/{GCS_DATA_DIR}\"\n",
+        "output_dir = f\"/gcs/{GCS_BUCKET}/timm\"\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "# Single node with multiple GPUs.\n",
+        "machine_type = \"n1-highmem-32\"\n",
+        "num_nodes = 1\n",
+        "gpu_type = \"NVIDIA_TESLA_P100\"  # @param {type:\"string\"}\n",
+        "num_gpus = 4  # @param {type:\"integer\"}\n",
+        "\n",
+        "# Model specific config.\n",
+        "job_name = f\"pytorch-{MODEL_NAME}\"\n",
+        "batch_size = 32\n",
+        "epochs = 2\n",
+        "\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "model = job.run(\n",
+        "    args=[\n",
+        "        \"--standalone\",\n",
+        "        f\"--nnodes={num_nodes}\",\n",
+        "        f\"--nproc_per_node={num_gpus}\",\n",
+        "        \"train.py\",\n",
+        "        data_dir,\n",
+        "        f\"--model={MODEL_NAME}\",\n",
+        "        \"--pretrained\",\n",
+        "        f\"--output={output_dir}\",\n",
+        "        f\"--batch-size={batch_size}\",\n",
+        "        f\"--epochs={epochs}\",\n",
+        "    ],\n",
+        "    replica_count=num_nodes,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=gpu_type,\n",
+        "    accelerator_count=num_gpus,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Tf6P7ZI82AML"
+      },
+      "source": [
+        "### Create a hyperparameter tuning job on Vertex AI\n",
+        "\n",
+        "You can use a [hyperparameter tuning](https://cloud.google.com/vertex-ai/docs/training/hyperparameter-tuning-overview) job to find the best configuration of your hyperparameters.\n",
+        "\n",
+        "You can skip this section if you already trained a model in the previous section and do not want to tune the hyperparameters."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Hy_aCff_2AML"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
+        "\n",
+        "# Init common setup.\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)\n",
+        "\n",
+        "# Input and output path.\n",
+        "data_dir = f\"/gcs/{GCS_DATA_DIR}\"\n",
+        "output_dir = f\"/gcs/{GCS_BUCKET}/timm\"\n",
+        "\n",
+        "# Model specific config.\n",
+        "job_name = f\"pytorch-hp-{MODEL_NAME}\"\n",
+        "batch_size = 32\n",
+        "epochs = 2\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "machine_type = \"n1-highmem-16\"\n",
+        "num_nodes = 1\n",
+        "gpu_type = \"NVIDIA_TESLA_V100\"  # @param {type:\"string\"}\n",
+        "num_gpus = 2  # @param {type:\"integer\"}\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": machine_type,\n",
+        "            \"accelerator_type\": gpu_type,\n",
+        "            \"accelerator_count\": num_gpus,\n",
+        "        },\n",
+        "        \"replica_count\": num_nodes,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": TRAIN_DOCKER_URI,\n",
+        "            \"args\": [\n",
+        "                \"--standalone\",\n",
+        "                f\"--nnodes={num_nodes}\",\n",
+        "                f\"--nproc_per_node={num_gpus}\",\n",
+        "                \"train.py\",\n",
+        "                data_dir,\n",
+        "                f\"--model={MODEL_NAME}\",\n",
+        "                \"--pretrained\",\n",
+        "                f\"--output={output_dir}\",\n",
+        "                f\"--batch-size={batch_size}\",\n",
+        "                f\"--epochs={epochs}\",\n",
+        "            ],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "# Hyperparameter job specs.\n",
+        "metric_spec = {\"top1_accuracy\": \"maximize\"}\n",
+        "parameter_spec = {\n",
+        "    \"lr\": hpt.DoubleParameterSpec(min=0.001, max=0.05, scale=\"log\"),\n",
+        "}\n",
+        "max_trial_count = 2\n",
+        "parallel_trial_count = 2\n",
+        "\n",
+        "# Launch jobs.\n",
+        "training_job = aiplatform.CustomJob(\n",
+        "    display_name=job_name, worker_pool_specs=worker_pool_specs\n",
+        ")\n",
+        "hp_job = aiplatform.HyperparameterTuningJob(\n",
+        "    display_name=job_name,\n",
+        "    custom_job=training_job,\n",
+        "    metric_spec=metric_spec,\n",
+        "    parameter_spec=parameter_spec,\n",
+        "    max_trial_count=max_trial_count,\n",
+        "    parallel_trial_count=parallel_trial_count,\n",
+        ")\n",
+        "hp_job.run()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "DAyRWwqW2AML"
+      },
+      "source": [
+        "## Deploy model for online prediction\n",
+        "\n",
+        "This section uploads the model to Model Registry and deploys it on an Endpoint resource.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jbNbg0yR2AML"
+      },
+      "outputs": [],
+      "source": [
+        "# The prebuilt serving docker uri.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-timm-serve\"\n",
+        "# The port number used by torchserve traffic.\n",
+        "SERVE_PORT = 7080\n",
+        "# The path to model checkpoint file, including gs:// prefix.\n",
+        "MODEL_PT_PATH = \"gs://path_to_model_best.pth.tar\"  # @param {type:\"string\"}\n",
+        "# [Optional] the path to index_to_name.json, including gs:// prefix.\n",
+        "INDEX_TO_NAME_FILE = \"gs://path_to_index_to_name.json\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "INPri3HQ2AML"
+      },
+      "source": [
+        "### Upload and deploy model on Vertex AI"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WOvqoAaN2AML"
+      },
+      "outputs": [],
+      "source": [
+        "# Upload model.\n",
+        "serving_env = {\n",
+        "    \"MODEL_NAME\": MODEL_NAME,\n",
+        "    \"MODEL_PT_PATH\": MODEL_PT_PATH,\n",
+        "    \"INDEX_TO_NAME_FILE\": INDEX_TO_NAME_FILE,\n",
+        "}\n",
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=MODEL_NAME,\n",
+        "    serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "    serving_container_ports=[SERVE_PORT],\n",
+        "    serving_container_predict_route=\"/predictions/timm_serving\",\n",
+        "    serving_container_health_route=\"/ping\",\n",
+        "    serving_container_environment_variables=serving_env,\n",
+        ")\n",
+        "# Or reuse a pre-uploaded model.\n",
+        "# model = aiplatform.Model('projects/123456789/locations/us-central1/models/123456789@1')\n",
+        "\n",
+        "# Create an endpoint.\n",
+        "endpoint = aiplatform.Endpoint.create(display_name=\"pytorch-timm-endpoint\")\n",
+        "# Or reuse a pre-created endpoint.\n",
+        "# endpoint = aiplatform.Endpoint('projects/123456789/locations/us-central1/endpoints/123456789')\n",
+        "\n",
+        "# Deploy model to endpoint.\n",
+        "model.deploy(\n",
+        "    endpoint=endpoint,\n",
+        "    machine_type=\"n1-standard-8\",\n",
+        "    accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "    accelerator_count=1,\n",
+        "    traffic_percentage=100,\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "s2gnYFEJ2AML"
+      },
+      "source": [
+        "You can mange your uploaded models in the [Model Registry](https://pantheon.corp.google.com/vertex-ai/models) and your endpoints in the [Endpoints](https://pantheon.corp.google.com/vertex-ai/endpoints)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5UP84Q5R2AMM"
+      },
+      "source": [
+        "### Test online prediction\n",
+        "\n",
+        "You will now test the deployed endpoint. Please prepare an image to predict."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "zL2Qbm2x2AMM"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "\n",
+        "# You can get the deployed endpoint object by its resource name returned by Endpoint.create(). For example:\n",
+        "# endpoint = aiplatform.Endpoint('projects/816369962409/locations/us-central1/endpoints/8809168414485512192')\n",
+        "\n",
+        "# Please upload an image and enter its filename below.\n",
+        "IMAGE_FILENAME = \"test.jpg\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Alternatively, uncomment the following line to download a cat image for demonstration.\n",
+        "# ! wget http://images.cocodataset.org/val2017/000000039769.jpg -O test.jpg\n",
+        "\n",
+        "with open(IMAGE_FILENAME, \"rb\") as f:\n",
+        "    image_b64 = base64.b64encode(f.read()).decode(\"utf-8\")\n",
+        "instances = [{\"data\": {\"b64\": image_b64}}]\n",
+        "\n",
+        "prediction = endpoint.predict(instances=instances)\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KqSxSyT42AMM"
+      },
+      "source": [
+        "### Clean Up Resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tMwdxiH-2AMM"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.undeploy_all()\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_timm.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_vilt_vqa.ipynb

@@ -0,0 +1,401 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - ViLT VQA\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_vilt_vqa.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_vilt_vqa.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_vilt_vqa.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [ViLT VQA](https://huggingface.co/dandelin/vilt-b32-finetuned-vqa) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"vilt-vqa\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send images and questions to get answers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"dandelin/vilt-b32-finetuned-vqa\", task=\"visual-question-answering\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "display(image)\n",
+        "\n",
+        "question = \"Which cat is bigger?\"\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image), \"text\": question},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(question)\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_vilt_vqa.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_vit_gpt2_image_captioning.ipynb

@@ -0,0 +1,399 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2bd716bf3e39"
+      },
+      "source": [
+        "# Vertex AI Model Garden - ViT-GPT2 Image Captioning\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_vit_gpt2_image_captioning.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_vit_gpt2_image_captioning.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>                                                                                               <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_vit_gpt2_image_captioning.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d8cd12648da4"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates deploying the pre-trained [ViT-GPT2 Image Captioning](https://huggingface.co/nlpconnect/vit-gpt2-image-captioning) model on Vertex AI for online prediction.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for image captioning.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Setup environment\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "### Colab only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "!pip3 install --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b60a4d7100bf"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import auth as google_auth\n",
+        "\n",
+        "google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0f826ff482a2"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8958ebc71868"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9db30f827a65"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "92f16e22c20b"
+      },
+      "source": [
+        "Initialize Vertex AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1680c257acfb"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ca48b699d17"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de9882ea89ea"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "10188266a5cd"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cac4478ae098"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"vit-gpt2-image-captioning\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
+        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "        artifact_uri=artifact_uri,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_T4\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d2d72ecdb8c9"
+      },
+      "source": [
+        "## Upload and deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9448c5f545fa"
+      },
+      "source": [
+        "This section uploads the pre-trained model to Model Registry and deploys it on the Endpoint with 1 T4 GPU.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "Once deployed, you can send images to get descriptions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b4b46c28d8b1"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"nlpconnect/vit-gpt2-image-captioning\", task=\"image-to-text\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6be655247cb1"
+      },
+      "outputs": [],
+      "source": [
+        "image = download_image(\"http://images.cocodataset.org/val2017/000000039769.jpg\")\n",
+        "display(image)\n",
+        "\n",
+        "instances = [\n",
+        "    {\"image\": image_to_base64(image)},\n",
+        "]\n",
+        "preds = endpoint.predict(instances=instances).predictions\n",
+        "print(preds)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db7ffebdb4be"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ccf3714dbe9"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_vit_gpt2_image_captioning.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_tfvision_image_classification.ipynb

@@ -0,0 +1,908 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ur8xi4C7S06n"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "TirJ-SGQseby"
+      },
+      "source": [
+        "# Vertex AI Model Garden TFVision With Image Classification\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_tfvision_image_classification.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_tfvision_image_classification.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>                                                                                               <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_tfvision_image_classification.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dwGLvtIeECLK"
+      },
+      "source": [
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.9"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates how to use [TFVision](https://github.com/tensorflow/models/blob/master/official/vision/MODEL_GARDEN.md) in Vertex AI Model Garden.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "* Train new models\n",
+        "  * Convert input data to training formats\n",
+        "  * Create [hyperparameter tuning jobs](https://cloud.google.com/vertex-ai/docs/training/hyperparameter-tuning-overview) to train new models\n",
+        "  * Find and export best models\n",
+        "\n",
+        "* Test trained models\n",
+        "  * Upload models to model registry\n",
+        "  * Deploy uploaded models\n",
+        "  * Run predictions\n",
+        "\n",
+        "* Cleanup resources\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KEukV6uRk_S3"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "z__i0w0lCAsW"
+      },
+      "source": [
+        "### Colab Only\n",
+        "Run the following commands for Colab and skip this section if you use Workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Jvqs-ehKlaYh"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)\n",
+        "\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9wExiMUxFk91"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "# The project and bucket are for experiments below.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# You can choose a region from https://cloud.google.com/about/locations.\n",
+        "# Only regions prefixed by \"us\", \"asia\", or \"europe\" are supported.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "REGION_PREFIX = REGION.split(\"-\")[0]\n",
+        "assert REGION_PREFIX in (\n",
+        "    \"us\",\n",
+        "    \"europe\",\n",
+        "    \"asia\",\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"asia\", or \"europe\".'\n",
+        "\n",
+        "! gcloud config set project $PROJECT_ID\n",
+        "\n",
+        "STAGING_BUCKET = os.path.join(BUCKET_URI, \"temporal\")\n",
+        "CHECKPOINT_BUCKET = os.path.join(BUCKET_URI, \"ckpt\")\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=STAGING_BUCKET)\n",
+        "\n",
+        "# Download config files.\n",
+        "CONFIG_DIR = os.path.join(BUCKET_URI, \"config\")\n",
+        "\n",
+        "\n",
+        "def upload_config_to_gcs(url):\n",
+        "    filename = os.path.basename(url)\n",
+        "    destination = os.path.join(CONFIG_DIR, filename)\n",
+        "    print(\"Copy\", url, \"to\", destination)\n",
+        "    ! wget \"$url\" -O \"$filename\"\n",
+        "    ! gsutil cp \"$filename\" \"$destination\"\n",
+        "\n",
+        "\n",
+        "upload_config_to_gcs(\n",
+        "    \"https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/image_classification/imagenet_resnet50_gpu.yaml\"\n",
+        ")\n",
+        "upload_config_to_gcs(\n",
+        "    \"https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/image_classification/imagenet_resnetrs50_i160_gpu.yaml\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "n6IFz75WGCam"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "riG_qUokg0XZ"
+      },
+      "outputs": [],
+      "source": [
+        "OBJECTIVE = \"icn\"\n",
+        "\n",
+        "# Data converter constants.\n",
+        "DATA_CONVERTER_JOB_PREFIX = \"data_converter\"\n",
+        "DATA_CONVERTER_CONTAINER = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter\"\n",
+        "DATA_CONVERTER_MACHINE_TYPE = \"n1-highmem-8\"\n",
+        "\n",
+        "\n",
+        "# Training constants.\n",
+        "TRAINING_JOB_PREFIX = \"train\"\n",
+        "TRAIN_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss\"\n",
+        "TRAIN_MACHINE_TYPE = \"n1-highmem-16\"\n",
+        "TRAIN_ACCELERATOR_TYPE = \"NVIDIA_TESLA_P100\"\n",
+        "TRAIN_NUM_GPU = 1\n",
+        "\n",
+        "# Evaluation constants.\n",
+        "EVALUATION_METRIC = \"accuracy\"\n",
+        "\n",
+        "# Export constants.\n",
+        "EXPORT_JOB_PREFIX = \"export\"\n",
+        "EXPORT_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving\"\n",
+        "EXPORT_MACHINE_TYPE = \"n1-highmem-8\"\n",
+        "\n",
+        "# Prediction constants.\n",
+        "# You can deploy models with\n",
+        "#   pre-build-dockers: https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers.\n",
+        "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
+        "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
+        "# You can adjust accelerator types and machine types to get faster predictions.\n",
+        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
+        "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
+        "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
+        "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
+        "UPLOAD_JOB_PREFIX = \"upload\"\n",
+        "DEPLOY_JOB_PREFIX = \"deploy\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZZFPe_GezXg8"
+      },
+      "source": [
+        "### Define common libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XcYUGwr-AJGY"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import json\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "from typing import Dict, List, Union\n",
+        "\n",
+        "import matplotlib.pyplot as plt\n",
+        "import numpy\n",
+        "import tensorflow as tf\n",
+        "import yaml\n",
+        "from google.protobuf import json_format\n",
+        "from google.protobuf.struct_pb2 import Value\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def get_job_name_with_datetime(prefix: str):\n",
+        "    return prefix + datetime.now().strftime(\"_%Y%m%d_%H%M%S\")\n",
+        "\n",
+        "\n",
+        "def predict_custom_trained_model(\n",
+        "    project: str,\n",
+        "    endpoint_id: str,\n",
+        "    instances: Union[Dict, List[Dict]],\n",
+        "    location: str = \"us-central1\",\n",
+        "):\n",
+        "    # The AI Platform services require regional API endpoints.\n",
+        "    client_options = {\"api_endpoint\": f\"{location}-aiplatform.googleapis.com\"}\n",
+        "    # Initialize client that will be used to create and send requests.\n",
+        "    # This client only needs to be created once, and can be reused for multiple requests.\n",
+        "    client = aiplatform.gapic.PredictionServiceClient(client_options=client_options)\n",
+        "    parameters_dict = {}\n",
+        "    parameters = json_format.ParseDict(parameters_dict, Value())\n",
+        "    endpoint = client.endpoint_path(\n",
+        "        project=project, location=location, endpoint=endpoint_id\n",
+        "    )\n",
+        "    response = client.predict(\n",
+        "        endpoint=endpoint, instances=instances, parameters=parameters\n",
+        "    )\n",
+        "    return response.predictions, response.deployed_model_id\n",
+        "\n",
+        "\n",
+        "def load_img(path):\n",
+        "    img = tf.io.read_file(path)\n",
+        "    img = tf.image.decode_jpeg(img, channels=3)\n",
+        "    return Image.fromarray(numpy.uint8(img)).convert(\"RGB\")\n",
+        "\n",
+        "\n",
+        "def display_image(image):\n",
+        "    _ = plt.figure(figsize=(20, 15))\n",
+        "    plt.grid(False)\n",
+        "    plt.imshow(image)\n",
+        "\n",
+        "\n",
+        "def get_prediction_instances(test_filepath, new_width=-1):\n",
+        "    if new_width <= 0:\n",
+        "        with tf.io.gfile.GFile(test_filepath, \"rb\") as input_file:\n",
+        "            encoded_string = base64.b64encode(input_file.read()).decode(\"utf-8\")\n",
+        "    else:\n",
+        "        img = load_img(test_filepath)\n",
+        "        width, height = img.size\n",
+        "        print(\"original input image size: \", width, \" , \", height)\n",
+        "        new_height = int(height * new_width / width)\n",
+        "        new_img = img.resize((new_width, new_height))\n",
+        "        print(\"resized input image size: \", new_width, \" , \", new_height)\n",
+        "        buffered = BytesIO()\n",
+        "        new_img.save(buffered, format=\"JPEG\")\n",
+        "        encoded_string = base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
+        "\n",
+        "    instances = [\n",
+        "        {\n",
+        "            \"encoded_image\": {\"b64\": encoded_string},\n",
+        "        }\n",
+        "    ]\n",
+        "    return instances\n",
+        "\n",
+        "\n",
+        "def get_label_map(label_map_yaml_filepath):\n",
+        "    with tf.io.gfile.GFile(label_map_yaml_filepath, \"rb\") as input_file:\n",
+        "        label_map = yaml.safe_load(input_file.read())\n",
+        "    return label_map\n",
+        "\n",
+        "\n",
+        "def get_best_trial(model_dir, max_trial_count, evaluation_metric):\n",
+        "    best_trial_dir = \"\"\n",
+        "    best_trial_evaluation_results = {}\n",
+        "    best_performance = -1\n",
+        "\n",
+        "    for i in range(max_trial_count):\n",
+        "        current_trial = i + 1\n",
+        "        current_trial_dir = os.path.join(model_dir, \"trial_\" + str(current_trial))\n",
+        "        current_trial_best_ckpt_dir = os.path.join(current_trial_dir, \"best_ckpt\")\n",
+        "        current_trial_best_ckpt_evaluation_filepath = os.path.join(\n",
+        "            current_trial_best_ckpt_dir, \"info.json\"\n",
+        "        )\n",
+        "        with tf.io.gfile.GFile(current_trial_best_ckpt_evaluation_filepath, \"rb\") as f:\n",
+        "            eval_metric_results = json.load(f)\n",
+        "            current_performance = eval_metric_results[evaluation_metric]\n",
+        "            if current_performance > best_performance:\n",
+        "                best_performance = current_performance\n",
+        "                best_trial_dir = current_trial_dir\n",
+        "                best_trial_evaluation_results = eval_metric_results\n",
+        "    return best_trial_dir, best_trial_evaluation_results\n",
+        "\n",
+        "\n",
+        "def upload_checkpoint_to_gcs(checkpoint_url):\n",
+        "    filename = os.path.basename(checkpoint_url)\n",
+        "    checkpoint_name = filename.replace(\".tar.gz\", \"\")\n",
+        "    print(\"Download checkpoint from\", checkpoint_url, \"and store to\", CHECKPOINT_BUCKET)\n",
+        "    ! wget $checkpoint_url -O $filename\n",
+        "    ! mkdir -p $checkpoint_name\n",
+        "    ! tar -xvzf $filename -C $checkpoint_name\n",
+        "\n",
+        "    # Search for relative path to the checkpoint.\n",
+        "    checkpoint_path = None\n",
+        "    for root, dirs, files in os.walk(checkpoint_name):\n",
+        "        for file in files:\n",
+        "            if file.endswith(\".index\"):\n",
+        "                checkpoint_path = os.path.join(root, os.path.splitext(file)[0])\n",
+        "                checkpoint_path = os.path.relpath(checkpoint_path, checkpoint_name)\n",
+        "                break\n",
+        "\n",
+        "    ! gsutil cp -r $checkpoint_name $CHECKPOINT_BUCKET/\n",
+        "    checkpoint_uri = os.path.join(CHECKPOINT_BUCKET, checkpoint_name, checkpoint_path)\n",
+        "    print(\"Checkpoint uploaded to\", checkpoint_uri)\n",
+        "    return checkpoint_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RB_xY9ipr7ZU"
+      },
+      "source": [
+        "## Train new models\n",
+        "This section shows how to train new models.\n",
+        "1. Convert input data to training formats\n",
+        "2. Create hyperparameter tuning jobs to train new models\n",
+        "3. Find and export best models\n",
+        "\n",
+        "If you already trained models, please go to the section `Test Trained models`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zgPO1eR3CYjk"
+      },
+      "source": [
+        "### Prepare input data for training\n",
+        "\n",
+        "Prepare data in the format as described [here](https://cloud.google.com/vertex-ai/docs/image-data/classification/prepare-data), and then convert them to the training formats as below:\n",
+        "\n",
+        "* `input_file_path`: The input file path for preparing data.\n",
+        "* `input_file_type`: The input file type, such as csv or jsonl.\n",
+        "* `split_ratio`: The proportion of data to split into train/validation/test.\n",
+        "* `num_shard`: The number of shards for train/validation/test.\n",
+        "* `output_dir`: The output directory, which will container prepared train/test/validation data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "IndQ_m6ddUEM"
+      },
+      "outputs": [],
+      "source": [
+        "# This job will convert input data as training format, with given split ratios\n",
+        "# and number of shards on train/test/validation.\n",
+        "\n",
+        "data_converter_job_name = get_job_name_with_datetime(\n",
+        "    DATA_CONVERTER_JOB_PREFIX + \"_\" + OBJECTIVE\n",
+        ")\n",
+        "\n",
+        "input_file_path = \"\"  # @param {type:\"string\"}\n",
+        "input_file_type = \"csv\"  # @param [\"csv\", \"jsonl\"]\n",
+        "num_classes = 5  # @param {type:\"integer\"}\n",
+        "split_ratio = \"0.8,0.1,0.1\"\n",
+        "num_shard = \"10,10,10\"\n",
+        "data_converter_output_dir = os.path.join(BUCKET_URI, data_converter_job_name)\n",
+        "\n",
+        "\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": DATA_CONVERTER_MACHINE_TYPE,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": DATA_CONVERTER_CONTAINER,\n",
+        "            \"command\": [],\n",
+        "            \"args\": [\n",
+        "                \"--input_file_path=%s\" % input_file_path,\n",
+        "                \"--input_file_type=%s\" % input_file_type,\n",
+        "                \"--objective=%s\" % OBJECTIVE,\n",
+        "                \"--num_shard=%s\" % num_shard,\n",
+        "                \"--split_ratio=%s\" % split_ratio,\n",
+        "                \"--output_dir=%s\" % data_converter_output_dir,\n",
+        "            ],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "data_converter_custom_job = aiplatform.CustomJob(\n",
+        "    display_name=data_converter_job_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "data_converter_custom_job.run()\n",
+        "\n",
+        "input_train_data_path = os.path.join(data_converter_output_dir, \"train.tfrecord*\")\n",
+        "input_validation_data_path = os.path.join(data_converter_output_dir, \"val.tfrecord*\")\n",
+        "label_map_path = os.path.join(data_converter_output_dir, \"label_map.yaml\")\n",
+        "print(\"input_train_data_path for training: \", input_train_data_path)\n",
+        "print(\"input_validation_data_path for training: \", input_validation_data_path)\n",
+        "print(\"label_map_path for prediction: \", label_map_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "aaff6f5be7f6"
+      },
+      "source": [
+        "### Create a Vertex AI custom job with hyperparameter tuning\n",
+        "\n",
+        "You use the Vertex AI SDK to create and run the hyperparameter tuning job with Vertex AI Model Garden Training Dockers.\n",
+        "\n",
+        "#### Define the following specifications\n",
+        "* `worker_pool_specs`: Dictionary specifying the machine type and Docker image. This example defines a single node cluster with one `n1-standard-4` machine with two `NVIDIA_TESLA_T4` GPUs.\n",
+        "* `parameter_spec`: Dictionary specifying the parameters to optimize. The dictionary key is the string assigned to the command line argument for each hyperparameter in your training application code, and the dictionary value is the parameter specification. The parameter specification includes the type, min/max values, and scale for the hyperparameter.\n",
+        "* `metric_spec`: Dictionary specifying the metric to optimize. The dictionary key is the `hyperparameter_metric_tag` that you set in your training application code, and the value is the optimization goal."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "um_XKbmpTaHx"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
+        "\n",
+        "# Input train and validation datasets can be found from the section above\n",
+        "# `Convert input data for training`.\n",
+        "# Set prepared datasets if exists.\n",
+        "# input_train_data_path = ''\n",
+        "# input_validation_data_path = ''\n",
+        "\n",
+        "experiment = \"ResNet-50\"  # @param [\"ResNet-50\",\"ResNet-RS-50\",\"Efficientnetv2-m\",\"ViT-ti16\",\"ViT-s16\",\"ViT-b16\",\"ViT-l16\"]\n",
+        "\n",
+        "train_job_name = get_job_name_with_datetime(TRAINING_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "model_dir = os.path.join(BUCKET_URI, train_job_name)\n",
+        "\n",
+        "# The arguments here are mainly for test purposes. Please update them\n",
+        "# to get better performances.\n",
+        "common_args = {\n",
+        "    \"input_train_data_path\": input_train_data_path,\n",
+        "    \"input_validation_data_path\": input_validation_data_path,\n",
+        "    \"objective\": OBJECTIVE,\n",
+        "    \"model_dir\": model_dir,\n",
+        "    \"num_classes\": num_classes,\n",
+        "    \"global_batch_size\": 4,\n",
+        "    \"prefetch_buffer_size\": 32,\n",
+        "    \"train_steps\": 2000,\n",
+        "    \"input_size\": \"224,224\",\n",
+        "}\n",
+        "\n",
+        "# Arguments for different experiments.\n",
+        "experiment_container_args_dict = {\n",
+        "    \"ResNet-50\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"resnet_imagenet\",\n",
+        "            \"config_file\": os.path.join(CONFIG_DIR, \"imagenet_resnet50_gpu.yaml\"),\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/resnet/resnet-50-i224.tar.gz\",\n",
+        "        },\n",
+        "    ),\n",
+        "    \"ResNet-RS-50\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"resnet_rs_imagenet\",\n",
+        "            \"config_file\": os.path.join(\n",
+        "                CONFIG_DIR, \"imagenet_resnetrs50_i160_gpu.yaml\"\n",
+        "            ),\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/resnet-rs/resnet-rs-50-i160.tar.gz\",\n",
+        "            \"input_size\": \"160,160\",\n",
+        "        },\n",
+        "    ),\n",
+        "    \"Efficientnetv2-m\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"hub_model\",\n",
+        "        },\n",
+        "    ),\n",
+        "    \"ViT-ti16\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"deit_imagenet_pretrain\",\n",
+        "            \"model_name\": \"vit-ti16\",\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/vit/vit-deit-imagenet-ti16.tar.gz\",\n",
+        "            \"input_size\": \"224,224\",\n",
+        "        },\n",
+        "    ),\n",
+        "    \"ViT-s16\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"deit_imagenet_pretrain\",\n",
+        "            \"model_name\": \"vit-s16\",\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/vit/vit-deit-imagenet-s16.tar.gz\",\n",
+        "            \"input_size\": \"224,224\",\n",
+        "        },\n",
+        "    ),\n",
+        "    \"ViT-b16\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"deit_imagenet_pretrain\",\n",
+        "            \"model_name\": \"vit-b16\",\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/vit/vit-deit-imagenet-b16.tar.gz\",\n",
+        "            \"input_size\": \"224,224\",\n",
+        "        },\n",
+        "    ),\n",
+        "    \"ViT-l16\": dict(\n",
+        "        common_args,\n",
+        "        **{\n",
+        "            \"experiment\": \"deit_imagenet_pretrain\",\n",
+        "            \"model_name\": \"vit-l16\",\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/vit/vit-deit-imagenet-l16.tar.gz\",\n",
+        "            \"input_size\": \"224,224\",\n",
+        "        },\n",
+        "    ),\n",
+        "}\n",
+        "experiment_container_args = experiment_container_args_dict[experiment]\n",
+        "\n",
+        "# Copy checkpoint to GCS bucket if specified.\n",
+        "init_checkpoint = experiment_container_args.get(\"init_checkpoint\")\n",
+        "if init_checkpoint:\n",
+        "    experiment_container_args[\"init_checkpoint\"] = upload_checkpoint_to_gcs(\n",
+        "        init_checkpoint\n",
+        "    )\n",
+        "\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": TRAIN_MACHINE_TYPE,\n",
+        "            \"accelerator_type\": TRAIN_ACCELERATOR_TYPE,\n",
+        "            # Each training job uses TRAIN_NUM_GPU GPUs.\n",
+        "            \"accelerator_count\": TRAIN_NUM_GPU,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": TRAIN_CONTAINER_URI,\n",
+        "            \"args\": [\n",
+        "                \"--mode=train_and_eval\",\n",
+        "                \"--params_override=runtime.num_gpus=%d\" % TRAIN_NUM_GPU,\n",
+        "            ]\n",
+        "            + [\"--{}={}\".format(k, v) for k, v in experiment_container_args.items()],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "metric_spec = {\"model_performance\": \"maximize\"}\n",
+        "\n",
+        "\n",
+        "LEARNING_RATES = [5e-4, 1e-3]\n",
+        "# Models will be trained with each learning rate separately and max trial count is the number of learning rates.\n",
+        "MAX_TRIAL_COUNT = len(LEARNING_RATES)\n",
+        "parameter_spec = {\n",
+        "    \"learning_rate\": hpt.DiscreteParameterSpec(values=LEARNING_RATES, scale=\"linear\"),\n",
+        "}\n",
+        "\n",
+        "print(worker_pool_specs, metric_spec, parameter_spec)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HwcCjwlBTQIz"
+      },
+      "source": [
+        "#### Run the hyperparameter tuning job\n",
+        "* `max_trial_count`: Sets an upper bound on the number of trials the service will run. The recommended practice is to start with a smaller number of trials and get a sense of how impactful your chosen hyperparameters are before scaling up.\n",
+        "\n",
+        "* `parallel_trial_count`:  If you use parallel trials, the service provisions multiple training processing clusters. The worker pool spec that you specify when creating the job is used for each individual training cluster.  Increasing the number of parallel trials reduces the amount of time the hyperparameter tuning job takes to run; however, it can reduce the effectiveness of the job overall. This is because the default tuning strategy uses results of previous trials to inform the assignment of values in subsequent trials.\n",
+        "\n",
+        "* `search_algorithm`: The available search algorithms are grid, random, or default (None). The default option applies Bayesian optimization to search the space of possible hyperparameter values and is the recommended algorithm.\n",
+        "\n",
+        "Click on the generated link in the output to see your run in the Cloud Console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aec22792ee84"
+      },
+      "outputs": [],
+      "source": [
+        "train_custom_job = aiplatform.CustomJob(\n",
+        "    display_name=train_job_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "train_hpt_job = aiplatform.HyperparameterTuningJob(\n",
+        "    display_name=train_job_name,\n",
+        "    custom_job=train_custom_job,\n",
+        "    metric_spec=metric_spec,\n",
+        "    parameter_spec=parameter_spec,\n",
+        "    max_trial_count=MAX_TRIAL_COUNT,\n",
+        "    parallel_trial_count=MAX_TRIAL_COUNT,\n",
+        "    project=PROJECT_ID,\n",
+        "    search_algorithm=None,\n",
+        ")\n",
+        "\n",
+        "train_hpt_job.run()\n",
+        "\n",
+        "print(\"experiment is: \", experiment)\n",
+        "print(\"model_dir is: \", model_dir)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "mV-Djz-frBni"
+      },
+      "source": [
+        "### Export best models as TF Saved Model format"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "09Rz1AYspK19"
+      },
+      "outputs": [],
+      "source": [
+        "# This job will export models from TF checkpoints to TF saved model format.\n",
+        "# model_dir is from the section above.\n",
+        "best_trial_dir, best_trial_evaluation_results = get_best_trial(\n",
+        "    model_dir, MAX_TRIAL_COUNT, EVALUATION_METRIC\n",
+        ")\n",
+        "print(\"best_trial_dir: \", best_trial_dir)\n",
+        "print(\"best_trial_evaluation_results: \", best_trial_evaluation_results)\n",
+        "\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": EXPORT_MACHINE_TYPE,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": EXPORT_CONTAINER_URI,\n",
+        "            \"command\": [],\n",
+        "            \"args\": [\n",
+        "                \"--objective=%s\" % OBJECTIVE,\n",
+        "                \"--input_image_size=%s\" % experiment_container_args[\"input_size\"],\n",
+        "                \"--experiment=%s\" % experiment_container_args[\"experiment\"],\n",
+        "                \"--config_file=%s/params.yaml\" % best_trial_dir,\n",
+        "                \"--checkpoint_path=%s/best_ckpt\" % best_trial_dir,\n",
+        "                \"--export_dir=%s/best_model\" % model_dir,\n",
+        "            ],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "model_export_name = get_job_name_with_datetime(EXPORT_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "model_export_custom_job = aiplatform.CustomJob(\n",
+        "    display_name=model_export_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "\n",
+        "model_export_custom_job.run()\n",
+        "\n",
+        "print(\"best model is saved to: \", os.path.join(model_dir, \"best_model\"))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "g0BGaofgsMsy"
+      },
+      "source": [
+        "## Test trained models\n",
+        "This section shows how to test with trained models.\n",
+        "1. Upload and deploy models to model registry\n",
+        "2. Run predictions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NYuQowyZEtxK"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Upload and deploy models\n",
+        "# model_dir is from the section above.\n",
+        "trained_model_dir = os.path.join(model_dir, \"best_model/saved_model\")\n",
+        "\n",
+        "upload_job_name = get_job_name_with_datetime(UPLOAD_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "\n",
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=upload_job_name,\n",
+        "    artifact_uri=trained_model_dir,\n",
+        "    serving_container_image_uri=PREDICTION_CONTAINER_URI,\n",
+        "    serving_container_args=SERVING_CONTAINER_ARGS,\n",
+        ")\n",
+        "\n",
+        "model.wait()\n",
+        "\n",
+        "print(\"The uploaded model name is: \", upload_job_name)\n",
+        "\n",
+        "deploy_model_name = get_job_name_with_datetime(DEPLOY_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "print(\"The deployed job name is: \", deploy_model_name)\n",
+        "\n",
+        "endpoint = model.deploy(\n",
+        "    deployed_model_display_name=deploy_model_name,\n",
+        "    machine_type=PREDICTION_MACHINE_TYPE,\n",
+        "    traffic_split={\"0\": 100},\n",
+        "    accelerator_type=PREDICTION_ACCELERATOR_TYPE,\n",
+        "    accelerator_count=1,\n",
+        "    min_replica_count=1,\n",
+        "    max_replica_count=1,\n",
+        ")\n",
+        "\n",
+        "endpoint_id = endpoint.name\n",
+        "print(\"endpoint id is: \", endpoint_id)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vbIW9me1F2RY"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Run predictions\n",
+        "\n",
+        "# endpoint_id was generated in the section above (`Upload and deploy models`).\n",
+        "endpoint_id = endpoint.name\n",
+        "\n",
+        "test_filepath = \"\"  # @param {type:\"string\"}\n",
+        "# If the input image is too large, we will resize it for prediction.\n",
+        "instances = get_prediction_instances(test_filepath, new_width=1000)\n",
+        "\n",
+        "# The label map file was generated from the section above (`Convert input data for training`).\n",
+        "label_map = get_label_map(label_map_path)[\"label_map\"]\n",
+        "\n",
+        "predictions, _ = predict_custom_trained_model(\n",
+        "    project=PROJECT_ID, location=REGION, endpoint_id=endpoint_id, instances=instances\n",
+        ")\n",
+        "\n",
+        "probs = dict(predictions[0])[\"probs\"]\n",
+        "max_prob = max(probs)\n",
+        "max_index = probs.index(max_prob)\n",
+        "print(\"The test image: \", test_filepath)\n",
+        "print(\"max_prob: \", max_prob, \", for label: \", label_map[max_index])\n",
+        "img = load_img(test_filepath)\n",
+        "display_image(img)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kkH2nrpdp4sp"
+      },
+      "source": [
+        "## Clean up"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Ax6vQVZhp9pR"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "# Delete models.\n",
+        "model.delete()\n",
+        "# Delete custom and hpt jobs.\n",
+        "if data_converter_custom_job.list(filter=f'display_name=\"{data_converter_job_name}\"'):\n",
+        "    data_converter_custom_job.delete()\n",
+        "if train_hpt_job.list(filter=f'display_name=\"{train_job_name}\"'):\n",
+        "    train_hpt_job.delete()\n",
+        "if model_export_custom_job.list(filter=f'display_name=\"{model_export_name}\"'):\n",
+        "    model_export_custom_job.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_tfvision_image_classification.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb

@@ -0,0 +1,980 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ur8xi4C7S06n"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "TirJ-SGQseby"
+      },
+      "source": [
+        "# Vertex AI Model Garden TFVision With Image Segmentation\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>                                                                                               <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dwGLvtIeECLK"
+      },
+      "source": [
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.9"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates how to use [TFVision](https://github.com/tensorflow/models/blob/master/official/vision/MODEL_GARDEN.md) in Vertex AI Model Garden.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "* Train new models\n",
+        "  * Convert input data to training formats\n",
+        "  * Create [hyperparameter tuning jobs](https://cloud.google.com/vertex-ai/docs/training/hyperparameter-tuning-overview) to train new models\n",
+        "  * Find and export best models\n",
+        "\n",
+        "* Test trained models\n",
+        "  * Upload models to model registry\n",
+        "  * Deploy uploaded models\n",
+        "  * Run predictions\n",
+        "\n",
+        "* Cleanup resources\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KEukV6uRk_S3"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "z__i0w0lCAsW"
+      },
+      "source": [
+        "### Colab Only\n",
+        "\n",
+        "Run the following commands for Colab and skip this section if you use Workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Jvqs-ehKlaYh"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)\n",
+        "\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9wExiMUxFk91"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "# The project and bucket are for experiments below.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# You can choose a region from https://cloud.google.com/about/locations.\n",
+        "# Only regions prefixed by \"us\", \"asia\", or \"europe\" are supported.\n",
+        "REGION = \"europe-west4\"  # @param {type:\"string\"}\n",
+        "REGION_PREFIX = REGION.split(\"-\")[0]\n",
+        "assert REGION_PREFIX in (\n",
+        "    \"us\",\n",
+        "    \"europe\",\n",
+        "    \"asia\",\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"asia\", or \"europe\".'\n",
+        "\n",
+        "! gcloud config set project $PROJECT_ID\n",
+        "\n",
+        "STAGING_BUCKET = os.path.join(BUCKET_URI, \"temporal\")\n",
+        "CHECKPOINT_BUCKET = os.path.join(BUCKET_URI, \"ckpt\")\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=STAGING_BUCKET)\n",
+        "\n",
+        "# Download config files.\n",
+        "CONFIG_DIR = os.path.join(BUCKET_URI, \"config\")\n",
+        "! wget https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/semantic_segmentation/deeplabv3plus_resnet101_cityscapes_gpu_multiworker_mirrored.yaml\n",
+        "! gsutil cp deeplabv3plus_resnet101_cityscapes_gpu_multiworker_mirrored.yaml $CONFIG_DIR/"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "n6IFz75WGCam"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "riG_qUokg0XZ"
+      },
+      "outputs": [],
+      "source": [
+        "OBJECTIVE = \"isg\"\n",
+        "\n",
+        "# Data converter constants.\n",
+        "DATA_CONVERTER_JOB_PREFIX = \"data_converter\"\n",
+        "DATA_CONVERTER_CONTAINER = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter\"\n",
+        "DATA_CONVERTER_MACHINE_TYPE = \"n1-highmem-8\"\n",
+        "\n",
+        "\n",
+        "# Training constants.\n",
+        "TRAINING_JOB_PREFIX = \"train\"\n",
+        "TRAIN_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss\"\n",
+        "TRAIN_MACHINE_TYPE = \"n1-highmem-16\"\n",
+        "TRAIN_ACCELERATOR_TYPE = \"NVIDIA_TESLA_V100\"\n",
+        "TRAIN_NUM_GPU = 2\n",
+        "TRAIN_DEEPLABV3PLUS_CONFIG = os.path.join(\n",
+        "    CONFIG_DIR, \"deeplabv3plus_resnet101_cityscapes_gpu_multiworker_mirrored.yaml\"\n",
+        ")\n",
+        "\n",
+        "# Evaluation constants.\n",
+        "EVALUATION_METRIC = \"mean_iou\"\n",
+        "\n",
+        "# Export constants.\n",
+        "EXPORT_JOB_PREFIX = \"export\"\n",
+        "EXPORT_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving\"\n",
+        "EXPORT_MACHINE_TYPE = \"n1-highmem-8\"\n",
+        "\n",
+        "# Prediction constants.\n",
+        "# You can deploy models with\n",
+        "#   pre-build-dockers: https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers.\n",
+        "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
+        "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
+        "# You can adjust accelerator types and machine types to get faster predictions.\n",
+        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
+        "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
+        "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
+        "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
+        "UPLOAD_JOB_PREFIX = \"upload\"\n",
+        "DEPLOY_JOB_PREFIX = \"deploy\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZZFPe_GezXg8"
+      },
+      "source": [
+        "### Define common libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XcYUGwr-AJGY"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import json\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "from typing import Dict, List, Union\n",
+        "\n",
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np\n",
+        "import tensorflow as tf\n",
+        "import yaml\n",
+        "from google.cloud import aiplatform\n",
+        "from google.protobuf import json_format\n",
+        "from google.protobuf.struct_pb2 import Value\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def get_job_name_with_datetime(prefix: str):\n",
+        "    return prefix + datetime.now().strftime(\"_%Y%m%d_%H%M%S\")\n",
+        "\n",
+        "\n",
+        "def predict_custom_trained_model(\n",
+        "    project: str,\n",
+        "    endpoint_id: str,\n",
+        "    instances: Union[Dict, List[Dict]],\n",
+        "    location: str = \"us-central1\",\n",
+        "):\n",
+        "    # The AI Platform services require regional API endpoints.\n",
+        "    client_options = {\"api_endpoint\": f\"{location}-aiplatform.googleapis.com\"}\n",
+        "    # Initialize client that will be used to create and send requests.\n",
+        "    # This client only needs to be created once, and can be reused for multiple requests.\n",
+        "    client = aiplatform.gapic.PredictionServiceClient(client_options=client_options)\n",
+        "    parameters_dict = {}\n",
+        "    parameters = json_format.ParseDict(parameters_dict, Value())\n",
+        "    endpoint = client.endpoint_path(\n",
+        "        project=project, location=location, endpoint=endpoint_id\n",
+        "    )\n",
+        "    response = client.predict(\n",
+        "        endpoint=endpoint, instances=instances, parameters=parameters\n",
+        "    )\n",
+        "    return response.predictions, response.deployed_model_id\n",
+        "\n",
+        "\n",
+        "def load_img(path):\n",
+        "    img = tf.io.read_file(path)\n",
+        "    img = tf.image.decode_jpeg(img, channels=3)\n",
+        "    return Image.fromarray(np.uint8(img)).convert(\"RGB\")\n",
+        "\n",
+        "\n",
+        "def display_image(original_image, category_image_color, score_image_grayscale):\n",
+        "    _, axarr = plt.subplots(1, 3, figsize=(20, 15))\n",
+        "    axarr[0].imshow(original_image)\n",
+        "    axarr[1].imshow(category_image_color)\n",
+        "    axarr[2].imshow(score_image_grayscale.convert(\"RGB\"))\n",
+        "\n",
+        "\n",
+        "def get_prediction_instances(test_filepath, new_width=-1):\n",
+        "    if new_width <= 0:\n",
+        "        with tf.io.gfile.GFile(test_filepath, \"rb\") as input_file:\n",
+        "            encoded_string = base64.b64encode(input_file.read()).decode(\"utf-8\")\n",
+        "    else:\n",
+        "        img = load_img(test_filepath)\n",
+        "        width, height = img.size\n",
+        "        print(\"original input image size: \", width, \" , \", height)\n",
+        "        new_height = int(height * new_width / width)\n",
+        "        new_img = img.resize((new_width, new_height))\n",
+        "        print(\"resized input image size: \", new_width, \" , \", new_height)\n",
+        "        buffered = BytesIO()\n",
+        "        new_img.save(buffered, format=\"JPEG\")\n",
+        "        encoded_string = base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
+        "\n",
+        "    instances = [\n",
+        "        {\n",
+        "            \"encoded_image\": {\"b64\": encoded_string},\n",
+        "        }\n",
+        "    ]\n",
+        "    return instances\n",
+        "\n",
+        "\n",
+        "def get_label_map(label_map_yaml_filepath):\n",
+        "    with tf.io.gfile.GFile(label_map_yaml_filepath, \"rb\") as input_file:\n",
+        "        label_map = yaml.safe_load(input_file.read())\n",
+        "    return label_map\n",
+        "\n",
+        "\n",
+        "def get_best_trial(model_dir, max_trial_count, evaluation_metric):\n",
+        "    best_trial_dir = \"\"\n",
+        "    best_trial_evaluation_results = {}\n",
+        "    best_performance = -1\n",
+        "\n",
+        "    for i in range(max_trial_count):\n",
+        "        current_trial = i + 1\n",
+        "        current_trial_dir = os.path.join(model_dir, \"trial_\" + str(current_trial))\n",
+        "        current_trial_best_ckpt_dir = os.path.join(current_trial_dir, \"best_ckpt\")\n",
+        "        current_trial_best_ckpt_evaluation_filepath = os.path.join(\n",
+        "            current_trial_best_ckpt_dir, \"info.json\"\n",
+        "        )\n",
+        "        with tf.io.gfile.GFile(current_trial_best_ckpt_evaluation_filepath, \"rb\") as f:\n",
+        "            eval_metric_results = json.load(f)\n",
+        "            current_performance = eval_metric_results[evaluation_metric]\n",
+        "            if current_performance > best_performance:\n",
+        "                best_performance = current_performance\n",
+        "                best_trial_dir = current_trial_dir\n",
+        "                best_trial_evaluation_results = eval_metric_results\n",
+        "    return best_trial_dir, best_trial_evaluation_results\n",
+        "\n",
+        "\n",
+        "def create_coco_stuff_label_colormap():\n",
+        "    \"\"\"Creates a label colormap used in COCO-Stuff segmentation benchmark.\n",
+        "\n",
+        "    Returns:\n",
+        "      A colormap for visualizing segmentation results.\n",
+        "    \"\"\"\n",
+        "    return np.asarray(\n",
+        "        [\n",
+        "            [54, 178, 118],\n",
+        "            [0, 85, 178],\n",
+        "            [150, 178, 22],\n",
+        "            [107, 0, 0],\n",
+        "            [0, 0, 89],\n",
+        "            [0, 117, 178],\n",
+        "            [47, 178, 124],\n",
+        "            [178, 116, 0],\n",
+        "            [0, 0, 178],\n",
+        "            [79, 178, 92],\n",
+        "            [134, 0, 0],\n",
+        "            [22, 178, 150],\n",
+        "            [178, 87, 0],\n",
+        "            [178, 146, 0],\n",
+        "            [0, 5, 178],\n",
+        "            [0, 0, 125],\n",
+        "            [0, 53, 178],\n",
+        "            [0, 132, 178],\n",
+        "            [111, 178, 60],\n",
+        "            [178, 131, 0],\n",
+        "            [0, 29, 178],\n",
+        "            [178, 109, 0],\n",
+        "            [178, 35, 0],\n",
+        "            [0, 148, 178],\n",
+        "            [9, 172, 163],\n",
+        "            [0, 0, 178],\n",
+        "            [178, 124, 0],\n",
+        "            [178, 102, 0],\n",
+        "            [0, 156, 175],\n",
+        "            [178, 43, 0],\n",
+        "            [0, 0, 170],\n",
+        "            [178, 94, 0],\n",
+        "            [0, 0, 134],\n",
+        "            [67, 178, 105],\n",
+        "            [99, 178, 73],\n",
+        "            [0, 37, 178],\n",
+        "            [86, 178, 86],\n",
+        "            [15, 178, 156],\n",
+        "            [0, 0, 152],\n",
+        "            [178, 21, 0],\n",
+        "            [0, 124, 178],\n",
+        "            [0, 61, 178],\n",
+        "            [178, 50, 0],\n",
+        "            [0, 109, 178],\n",
+        "            [137, 178, 35],\n",
+        "            [0, 13, 178],\n",
+        "            [0, 101, 178],\n",
+        "            [0, 0, 116],\n",
+        "            [0, 45, 178],\n",
+        "            [41, 178, 131],\n",
+        "            [0, 0, 161],\n",
+        "            [178, 72, 0],\n",
+        "            [0, 0, 143],\n",
+        "            [116, 0, 0],\n",
+        "            [28, 178, 143],\n",
+        "            [170, 6, 0],\n",
+        "            [156, 178, 15],\n",
+        "            [89, 0, 0],\n",
+        "            [143, 178, 28],\n",
+        "            [73, 178, 99],\n",
+        "            [118, 178, 54],\n",
+        "            [92, 178, 79],\n",
+        "            [152, 0, 0],\n",
+        "            [178, 153, 0],\n",
+        "            [98, 0, 0],\n",
+        "            [178, 65, 0],\n",
+        "            [60, 178, 111],\n",
+        "            [169, 175, 3],\n",
+        "            [105, 178, 67],\n",
+        "            [178, 13, 0],\n",
+        "            [163, 178, 9],\n",
+        "            [3, 164, 169],\n",
+        "            [125, 0, 0],\n",
+        "            [175, 168, 0],\n",
+        "            [178, 138, 0],\n",
+        "            [178, 28, 0],\n",
+        "            [35, 178, 137],\n",
+        "            [0, 140, 178],\n",
+        "            [0, 0, 98],\n",
+        "            [131, 178, 41],\n",
+        "            [0, 77, 178],\n",
+        "            [0, 0, 107],\n",
+        "            [0, 93, 178],\n",
+        "            [143, 0, 0],\n",
+        "            [178, 58, 0],\n",
+        "            [161, 0, 0],\n",
+        "            [0, 69, 178],\n",
+        "            [178, 160, 0],\n",
+        "            [178, 80, 0],\n",
+        "            [0, 21, 178],\n",
+        "            [124, 178, 47],\n",
+        "            [255, 214, 0],\n",
+        "        ]\n",
+        "    )\n",
+        "\n",
+        "\n",
+        "def parse_segmentation_prediction(prediction):\n",
+        "    score_bytes = prediction[\"score_bytes\"]\n",
+        "    score_image_grayscale = Image.open(\n",
+        "        BytesIO(base64.b64decode(dict(score_bytes)[\"b64\"]))\n",
+        "    )\n",
+        "    category_bytes = prediction[\"category_bytes\"]\n",
+        "    category_image_grayscale = Image.open(\n",
+        "        BytesIO(base64.b64decode(dict(category_bytes)[\"b64\"]))\n",
+        "    )\n",
+        "\n",
+        "    # Visualize category images.\n",
+        "    color_map = create_coco_stuff_label_colormap()\n",
+        "    category_image_grayscale_np = np.array(category_image_grayscale)\n",
+        "    rendered_image_shape = category_image_grayscale_np.shape + (3,)\n",
+        "    category_image_color_np = np.zeros(rendered_image_shape, dtype=np.uint8)\n",
+        "    unique_labels = np.unique(category_image_grayscale_np)\n",
+        "    for label in unique_labels:\n",
+        "        if label == 0:\n",
+        "            continue\n",
+        "        category_image_color_np[category_image_grayscale_np == label] = color_map[\n",
+        "            label % len(color_map)\n",
+        "        ]\n",
+        "    category_image_color = Image.fromarray(category_image_color_np)\n",
+        "\n",
+        "    return score_image_grayscale, category_image_color\n",
+        "\n",
+        "\n",
+        "def upload_checkpoint_to_gcs(checkpoint_url):\n",
+        "    filename = os.path.basename(checkpoint_url)\n",
+        "    checkpoint_name = filename.replace(\".tar.gz\", \"\")\n",
+        "    print(\"Download checkpoint from\", checkpoint_url, \"and store to\", CHECKPOINT_BUCKET)\n",
+        "    ! wget $checkpoint_url -O $filename\n",
+        "    ! mkdir -p $checkpoint_name\n",
+        "    ! tar -xvzf $filename -C $checkpoint_name\n",
+        "\n",
+        "    # Search for relative path to the checkpoint.\n",
+        "    checkpoint_path = None\n",
+        "    for root, dirs, files in os.walk(checkpoint_name):\n",
+        "        for file in files:\n",
+        "            if file.endswith(\".index\"):\n",
+        "                checkpoint_path = os.path.join(root, os.path.splitext(file)[0])\n",
+        "                checkpoint_path = os.path.relpath(checkpoint_path, checkpoint_name)\n",
+        "                break\n",
+        "\n",
+        "    ! gsutil cp -r $checkpoint_name $CHECKPOINT_BUCKET/\n",
+        "    checkpoint_uri = os.path.join(CHECKPOINT_BUCKET, checkpoint_name, checkpoint_path)\n",
+        "    print(\"Checkpoint uploaded to\", checkpoint_uri)\n",
+        "    return checkpoint_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RB_xY9ipr7ZU"
+      },
+      "source": [
+        "## Train new models\n",
+        "This section shows how to train new models.\n",
+        "1. Convert input data to training formats\n",
+        "2. Create hyperparameter tuning jobs to train new models\n",
+        "3. Find and export best models\n",
+        "\n",
+        "If you already trained models, please go to the section `Test trained models`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zgPO1eR3CYjk"
+      },
+      "source": [
+        "### Prepare input data for training\n",
+        "\n",
+        "Prepare data in the format as described [here](https://cloud.google.com/vertex-ai/docs/image-data/classification/prepare-data), and then convert them to the training formats as below:\n",
+        "\n",
+        "* `input_file_path`: The input file path in coco json formats.\n",
+        "* `split_ratio`: The proportion of data to split into train/validation/test.\n",
+        "* `num_shard`: The number of shards for train/validation/test.\n",
+        "* `output_dir`: The output directory, which will container prepared train/test/validation data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "IndQ_m6ddUEM"
+      },
+      "outputs": [],
+      "source": [
+        "# This job will convert input data as training format, with given split ratios\n",
+        "# and number of shards on train/test/validation.\n",
+        "data_converter_job_name = get_job_name_with_datetime(\n",
+        "    DATA_CONVERTER_JOB_PREFIX + \"_\" + OBJECTIVE\n",
+        ")\n",
+        "\n",
+        "input_file_path = \"\"  # @param {type:\"string\"}\n",
+        "split_ratio = \"0.8,0.1,0.1\"\n",
+        "num_shard = \"10,10,10\"\n",
+        "data_converter_output_dir = os.path.join(BUCKET_URI, data_converter_job_name)\n",
+        "\n",
+        "\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": DATA_CONVERTER_MACHINE_TYPE,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": DATA_CONVERTER_CONTAINER,\n",
+        "            \"command\": [],\n",
+        "            \"args\": [\n",
+        "                \"--input_file_path=%s\" % input_file_path,\n",
+        "                \"--input_file_type=coco_json\",\n",
+        "                \"--objective=%s\" % OBJECTIVE,\n",
+        "                \"--num_shard=%s\" % num_shard,\n",
+        "                \"--split_ratio=%s\" % split_ratio,\n",
+        "                \"--output_dir=%s\" % data_converter_output_dir,\n",
+        "            ],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "data_converter_custom_job = aiplatform.CustomJob(\n",
+        "    display_name=data_converter_job_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "data_converter_custom_job.run()\n",
+        "\n",
+        "input_train_data_path = os.path.join(data_converter_output_dir, \"train.tfrecord*\")\n",
+        "input_validation_data_path = os.path.join(data_converter_output_dir, \"val.tfrecord*\")\n",
+        "label_map_path = os.path.join(data_converter_output_dir, \"label_map.yaml\")\n",
+        "print(\"input_train_data_path for training: \", input_train_data_path)\n",
+        "print(\"input_validation_data_path for training: \", input_validation_data_path)\n",
+        "print(\"label_map_path for prediction: \", label_map_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "S6dU2IrIqW3H"
+      },
+      "source": [
+        "### Create a Vertex AI custom job with hyperparameter tuning\n",
+        "\n",
+        "You use the Vertex AI SDK to create and run the hyperparameter tuning job with Vertex AI Model Garden Training Dockers."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "aaff6f5be7f6"
+      },
+      "source": [
+        "#### Define the following specifications\n",
+        "* `worker_pool_specs`: Dictionary specifying the machine type and Docker image. This example defines a single node cluster with one `n1-standard-4` machine with two `NVIDIA_TESLA_T4` GPUs.\n",
+        "* `parameter_spec`: Dictionary specifying the parameters to optimize. The dictionary key is the string assigned to the command line argument for each hyperparameter in your training application code, and the dictionary value is the parameter specification. The parameter specification includes the type, min/max values, and scale for the hyperparameter.\n",
+        "* `metric_spec`: Dictionary specifying the metric to optimize. The dictionary key is the `hyperparameter_metric_tag` that you set in your training application code, and the value is the optimization goal."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "um_XKbmpTaHx"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
+        "\n",
+        "label_map = get_label_map(label_map_path)\n",
+        "num_classes = len(label_map[\"label_map\"]) + 1\n",
+        "\n",
+        "# Input train and validation datasets can be found from the section above\n",
+        "# `Convert input data for training`.\n",
+        "# Set prepared datasets if exists.\n",
+        "# input_train_data_path = ''\n",
+        "# input_validation_data_path = ''\n",
+        "\n",
+        "# Refer to https://github.com/tensorflow/models/blob/master/official/vision/MODEL_GARDEN.md\n",
+        "# for more model details.\n",
+        "experiment = \"deeplabv3plus\"  # @param [\"deeplabv3plus\"]\n",
+        "\n",
+        "train_job_name = get_job_name_with_datetime(TRAINING_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "model_dir = os.path.join(BUCKET_URI, train_job_name)\n",
+        "\n",
+        "# The arguments here are mainly for test purposes. Please update them\n",
+        "# to get better performances.\n",
+        "experiment_container_args_dict = {\n",
+        "    # deeplabv3plus experiment args.\n",
+        "    \"deeplabv3plus\": {\n",
+        "        \"experiment\": \"seg_deeplabv3plus_pascal\",\n",
+        "        \"config_file\": TRAIN_DEEPLABV3PLUS_CONFIG,\n",
+        "        \"input_train_data_path\": input_train_data_path,\n",
+        "        \"input_validation_data_path\": input_validation_data_path,\n",
+        "        \"objective\": OBJECTIVE,\n",
+        "        \"model_dir\": model_dir,\n",
+        "        \"num_classes\": num_classes,\n",
+        "        \"global_batch_size\": 2,\n",
+        "        \"prefetch_buffer_size\": 12,\n",
+        "        \"train_steps\": 500,\n",
+        "        \"output_size\": \"1024,2048\",\n",
+        "        \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/deeplabv3plus/dilated-resnet-101-deeplabv3plus.tar.gz\",\n",
+        "    }\n",
+        "}\n",
+        "experiment_container_args = experiment_container_args_dict[experiment]\n",
+        "\n",
+        "# Copy checkpoint to GCS bucket if specified.\n",
+        "init_checkpoint = experiment_container_args.get(\"init_checkpoint\")\n",
+        "if init_checkpoint:\n",
+        "    experiment_container_args[\"init_checkpoint\"] = upload_checkpoint_to_gcs(\n",
+        "        init_checkpoint\n",
+        "    )\n",
+        "\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": TRAIN_MACHINE_TYPE,\n",
+        "            \"accelerator_type\": TRAIN_ACCELERATOR_TYPE,\n",
+        "            \"accelerator_count\": TRAIN_NUM_GPU,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": TRAIN_CONTAINER_URI,\n",
+        "            \"args\": [\n",
+        "                \"--mode=train_and_eval\",\n",
+        "            ]\n",
+        "            + [\"--{}={}\".format(k, v) for k, v in experiment_container_args.items()],\n",
+        "        },\n",
+        "    },\n",
+        "]\n",
+        "\n",
+        "metric_spec = {\"model_performance\": \"maximize\"}\n",
+        "\n",
+        "LEARNING_RATES = [0.001]\n",
+        "# Models will be trained with each learning rate separately and max trial count is the number of learning rates.\n",
+        "MAX_TRIAL_COUNT = len(LEARNING_RATES)\n",
+        "parameter_spec = {\n",
+        "    \"learning_rate\": hpt.DiscreteParameterSpec(values=LEARNING_RATES, scale=\"linear\"),\n",
+        "}\n",
+        "\n",
+        "print(worker_pool_specs, metric_spec, parameter_spec)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HwcCjwlBTQIz"
+      },
+      "source": [
+        "#### Run hyperparameter tuning jobs\n",
+        "* `max_trial_count`: Sets an upper bound on the number of trials the service will run. The recommended practice is to start with a smaller number of trials and get a sense of how impactful your chosen hyperparameters are before scaling up.\n",
+        "\n",
+        "* `parallel_trial_count`:  If you use parallel trials, the service provisions multiple training processing clusters. The worker pool spec that you specify when creating the job is used for each individual training cluster.  Increasing the number of parallel trials reduces the amount of time the hyperparameter tuning job takes to run; however, it can reduce the effectiveness of the job overall. This is because the default tuning strategy uses results of previous trials to inform the assignment of values in subsequent trials.\n",
+        "\n",
+        "* `search_algorithm`: The available search algorithms are grid, random, or default (None). The default option applies Bayesian optimization to search the space of possible hyperparameter values and is the recommended algorithm.\n",
+        "\n",
+        "Click on the generated link in the output to see your run in the Cloud Console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aec22792ee84"
+      },
+      "outputs": [],
+      "source": [
+        "train_custom_job = aiplatform.CustomJob(\n",
+        "    display_name=train_job_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "train_hpt_job = aiplatform.HyperparameterTuningJob(\n",
+        "    display_name=train_job_name,\n",
+        "    custom_job=train_custom_job,\n",
+        "    metric_spec=metric_spec,\n",
+        "    parameter_spec=parameter_spec,\n",
+        "    max_trial_count=MAX_TRIAL_COUNT,\n",
+        "    parallel_trial_count=1,\n",
+        "    project=PROJECT_ID,\n",
+        "    search_algorithm=None,\n",
+        ")\n",
+        "\n",
+        "train_hpt_job.run()\n",
+        "\n",
+        "print(\"experiment is: \", experiment)\n",
+        "print(\"model_dir is: \", model_dir)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "mV-Djz-frBni"
+      },
+      "source": [
+        "### Export best models as TF Saved Model format"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "09Rz1AYspK19"
+      },
+      "outputs": [],
+      "source": [
+        "# This job will export models from TF checkpoints to TF saved model format.\n",
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "# model_dir is from the section above.\n",
+        "best_trial_dir, best_trial_evaluation_results = get_best_trial(\n",
+        "    model_dir, MAX_TRIAL_COUNT, EVALUATION_METRIC\n",
+        ")\n",
+        "print(\"best_trial_dir: \", best_trial_dir)\n",
+        "print(\"best_trial_evaluation_results: \", best_trial_evaluation_results)\n",
+        "\n",
+        "worker_pool_specs = [\n",
+        "    {\n",
+        "        \"machine_spec\": {\n",
+        "            \"machine_type\": EXPORT_MACHINE_TYPE,\n",
+        "        },\n",
+        "        \"replica_count\": 1,\n",
+        "        \"container_spec\": {\n",
+        "            \"image_uri\": EXPORT_CONTAINER_URI,\n",
+        "            \"command\": [],\n",
+        "            \"args\": [\n",
+        "                \"--objective=%s\" % OBJECTIVE,\n",
+        "                \"--experiment=%s\" % experiment_container_args[\"experiment\"],\n",
+        "                \"--config_file=%s/params.yaml\" % best_trial_dir,\n",
+        "                \"--checkpoint_path=%s/best_ckpt\" % best_trial_dir,\n",
+        "                \"--export_dir=%s/best_model\" % model_dir,\n",
+        "                \"--input_image_size=%s\" % experiment_container_args[\"output_size\"],\n",
+        "            ],\n",
+        "        },\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "model_export_name = get_job_name_with_datetime(EXPORT_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "model_export_custom_job = aiplatform.CustomJob(\n",
+        "    display_name=model_export_name,\n",
+        "    project=PROJECT_ID,\n",
+        "    worker_pool_specs=worker_pool_specs,\n",
+        "    staging_bucket=STAGING_BUCKET,\n",
+        ")\n",
+        "\n",
+        "\n",
+        "model_export_custom_job.run()\n",
+        "\n",
+        "print(\"best model is saved to: \", os.path.join(model_dir, \"best_model\"))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "g0BGaofgsMsy"
+      },
+      "source": [
+        "## Test trained models\n",
+        "This section shows how to test with trained models.\n",
+        "1. Upload and deploy models\n",
+        "2. Run predictions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NYuQowyZEtxK"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Upload and deploy models\n",
+        "# model_dir is from the section above.\n",
+        "trained_model_dir = os.path.join(model_dir, \"best_model/saved_model\")\n",
+        "\n",
+        "upload_job_name = get_job_name_with_datetime(UPLOAD_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "\n",
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=upload_job_name,\n",
+        "    artifact_uri=trained_model_dir,\n",
+        "    serving_container_image_uri=PREDICTION_CONTAINER_URI,\n",
+        "    serving_container_args=SERVING_CONTAINER_ARGS,\n",
+        ")\n",
+        "\n",
+        "model.wait()\n",
+        "\n",
+        "print(\"The uploaded model name is: \", upload_job_name)\n",
+        "\n",
+        "deploy_model_name = get_job_name_with_datetime(DEPLOY_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
+        "print(\"The deployed job name is: \", deploy_model_name)\n",
+        "\n",
+        "endpoint = model.deploy(\n",
+        "    deployed_model_display_name=deploy_model_name,\n",
+        "    machine_type=PREDICTION_MACHINE_TYPE,\n",
+        "    traffic_split={\"0\": 100},\n",
+        "    accelerator_type=PREDICTION_ACCELERATOR_TYPE,\n",
+        "    accelerator_count=1,\n",
+        "    min_replica_count=1,\n",
+        "    max_replica_count=1,\n",
+        ")\n",
+        "\n",
+        "endpoint_id = endpoint.name\n",
+        "print(\"endpoint id is: \", endpoint_id)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vbIW9me1F2RY"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Run predictions\n",
+        "# endpoint_id was generated in the section above (`Upload and deploy models`).\n",
+        "endpoint_id = endpoint.name\n",
+        "\n",
+        "# The test image file path.\n",
+        "test_filepath = \"\"  # @param {type:\"string\"}\n",
+        "score_threshold = 0.5  # @param {type:\"number\"}\n",
+        "# If the input image is too large, we will resize it for prediction.\n",
+        "instances = get_prediction_instances(test_filepath, new_width=1000)\n",
+        "\n",
+        "# The label map file was generated from the section above (`Convert input data for training`).\n",
+        "label_map = get_label_map(label_map_path)[\"label_map\"]\n",
+        "\n",
+        "predictions, _ = predict_custom_trained_model(\n",
+        "    project=PROJECT_ID, location=REGION, endpoint_id=endpoint_id, instances=instances\n",
+        ")\n",
+        "\n",
+        "score_image_grayscale, category_image_color = parse_segmentation_prediction(\n",
+        "    dict(predictions[0])\n",
+        ")\n",
+        "display_image(\n",
+        "    load_img(test_filepath), category_image_color, score_image_grayscale.convert(\"RGB\")\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kkH2nrpdp4sp"
+      },
+      "source": [
+        "## Clean up"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Ax6vQVZhp9pR"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "# Delete models.\n",
+        "model.delete()\n",
+        "# Delete custom and hpt jobs.\n",
+        "if data_converter_custom_job.list(filter=f'display_name=\"{data_converter_job_name}\"'):\n",
+        "    data_converter_custom_job.delete()\n",
+        "if train_hpt_job.list(filter=f'display_name=\"{train_job_name}\"'):\n",
+        "    train_hpt_job.delete()\n",
+        "if model_export_custom_job.list(filter=f'display_name=\"{model_export_name}\"'):\n",
+        "    model_export_custom_job.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_tfvision_image_segmentation.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb

@@ -54,18 +54,20 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "239ba71252d3"
       },
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook shows how to use `Vertex AI Pipelines` and `BigQuery ML pipeline components` to train and evaluate a demand forecasting model.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "The dataset is a modified version of the dataset in [Build and visualize demand forecast predictions using Datastream, Dataflow, BigQuery ML, and Looker\n",
-        "](https://cloud.google.com/architecture/build-visualize-demand-forecast-prediction-datastream-dataflow-bigqueryml-looker) solution architecture\n",
-        "\n",
+        "This notebook shows how to use `Vertex AI Pipelines` and `BigQuery ML pipeline components` to train and evaluate a demand forecasting model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "25c28706c23e"
+      },
+      "source": [
         "### Objective\n",
         "\n",
         "In this tutorial, you learn how to train and evaluate a BigQuery ML model using Vertex AI Pipelines and BigQuery ML pipeline components. \n",
@@ -87,8 +89,27 @@
         "  - Generate the ARIMA Plus forecasts\n",
         "  - Generate the ARIMA PLUS forecast explainations\n",
         "- Compile the pipeline.\n",
-        "- Execute the pipeline.\n",
+        "- Execute the pipeline."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "586acfa9b502"
+      },
+      "source": [
+        "### Dataset\n",
         "\n",
+        "The dataset is a modified version of the dataset in [Build and visualize demand forecast predictions using Datastream, Dataflow, BigQuery ML, and Looker\n",
+        "](https://cloud.google.com/architecture/build-visualize-demand-forecast-prediction-datastream-dataflow-bigqueryml-looker) solution architecture\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -352,9 +373,8 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "#### UUID\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -365,9 +385,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -485,7 +512,7 @@
       "outputs": [],
       "source": [
         "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"-aip-\" + TIMESTAMP\n",
+        "    BUCKET_NAME = PROJECT_ID + \"-aip-\" + UUID\n",
         "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
@@ -706,6 +733,7 @@
         "KFP_COMPONENTS_PATH = \"components\"\n",
         "PIPELINES_PATH = \"pipelines\"\n",
         "\n",
+        "! mkdir -m 777 -p {DATA_PATH}\n",
         "! mkdir -m 777 -p {KFP_COMPONENTS_PATH}\n",
         "! mkdir -m 777 -p {PIPELINES_PATH}"
       ]
@@ -771,7 +799,7 @@
         "  --location={LOCATION} \\\n",
         "  --source_format=CSV \\\n",
         "  --skip_leading_rows=1\\\n",
-        "  fast_fresh.orders_{TIMESTAMP} \\\n",
+        "  fast_fresh.orders_{UUID} \\\n",
         "  {RAW_DATA_URI} \\\n",
         "  time_of_sale:DATETIME,order_id:INTEGER,product_name:STRING,price:NUMERIC,quantity:NUMERIC,payment_method:STRING,store_id:INTEGER,user_id:INTEGER"
       ]
@@ -782,7 +810,7 @@
         "id": "ZrgOD30o7HcL"
       },
       "source": [
-        "## BQML Training Formalization\n",
+        "## BigQuery ML Training Formalization\n",
         "\n",
         "In the next cells, you build the components and pipeline to train and evaluate the BQML demand forecasting model."
       ]
@@ -820,13 +848,13 @@
         "BQ_EVALUATE_MODEL_TABLE_PREFIX = \"orders_arima_model_evaluate\"\n",
         "BQ_FORECAST_TABLE_PREFIX = \"orders_arima_forecast\"\n",
         "BQ_EXPLAIN_FORECAST_TABLE_PREFIX = \"orders_arima_explain_forecast\"\n",
-        "BQ_ORDERS_TABLE = f\"{BQ_ORDERS_TABLE_PREFIX}_{TIMESTAMP}\"\n",
-        "BQ_TRAINING_TABLE = f\"{BQ_TRAINING_TABLE_PREFIX}_{TIMESTAMP}\"\n",
-        "BQ_MODEL_TABLE = f\"{BQ_MODEL_TABLE_PREFIX}_{TIMESTAMP}\"\n",
-        "BQ_EVALUATE_TS_TABLE = f\"{BQ_EVALUATE_TS_TABLE_PREFIX}_{TIMESTAMP}\"\n",
-        "BQ_EVALUATE_MODEL_TABLE = f\"{BQ_EVALUATE_MODEL_TABLE_PREFIX}_{TIMESTAMP}\"\n",
-        "BQ_FORECAST_TABLE = f\"{BQ_FORECAST_TABLE_PREFIX}_{TIMESTAMP}\"\n",
-        "BQ_EXPLAIN_FORECAST_TABLE = f\"{BQ_EXPLAIN_FORECAST_TABLE_PREFIX}_{TIMESTAMP}\"\n",
+        "BQ_ORDERS_TABLE = f\"{BQ_ORDERS_TABLE_PREFIX}_{UUID}\"\n",
+        "BQ_TRAINING_TABLE = f\"{BQ_TRAINING_TABLE_PREFIX}_{UUID}\"\n",
+        "BQ_MODEL_TABLE = f\"{BQ_MODEL_TABLE_PREFIX}_{UUID}\"\n",
+        "BQ_EVALUATE_TS_TABLE = f\"{BQ_EVALUATE_TS_TABLE_PREFIX}_{UUID}\"\n",
+        "BQ_EVALUATE_MODEL_TABLE = f\"{BQ_EVALUATE_MODEL_TABLE_PREFIX}_{UUID}\"\n",
+        "BQ_FORECAST_TABLE = f\"{BQ_FORECAST_TABLE_PREFIX}_{UUID}\"\n",
+        "BQ_EXPLAIN_FORECAST_TABLE = f\"{BQ_EXPLAIN_FORECAST_TABLE_PREFIX}_{UUID}\"\n",
         "\n",
         "BQ_TRAIN_CONFIGURATION = {\n",
         "    \"destinationTable\": {\n",
@@ -1022,7 +1050,7 @@
         "id": "pcSL1FHk69KT"
       },
       "source": [
-        "### Build the BQML training pipeline\n",
+        "### Build the BigQuery ML training pipeline\n",
         "\n",
         "Define your workflow using Kubeflow Pipelines DSL package. \n",
         "\n",
@@ -1094,8 +1122,8 @@
         "        location=location,\n",
         "    ).set_display_name(\"get train data\")\n",
         "\n",
-        "    # Train the ARIMA PLUS model\n",
-        "    bq_arima_model_op = (\n",
+        "    # Run an ARIMA PLUS experiment\n",
+        "    bq_arima_model_exp_op = (\n",
         "        BigqueryCreateModelJobOp(\n",
         "            query=f\"\"\"\n",
         "        -- create model table\n",
@@ -1104,10 +1132,7 @@
         "        MODEL_TYPE = \\'ARIMA_PLUS\\',\n",
         "        TIME_SERIES_TIMESTAMP_COL = \\'hourly_timestamp\\',\n",
         "        TIME_SERIES_DATA_COL = \\'total_sold\\',\n",
-        "        TIME_SERIES_ID_COL = [\\'product_name\\'],\n",
-        "        MODEL_REGISTRY = \\'vertex_ai\\',\n",
-        "        VERTEX_AI_MODEL_ID = \\'order_demand_forecasting\\',\n",
-        "        VERTEX_AI_MODEL_VERSION_ALIASES = [\\'staging\\']\n",
+        "        TIME_SERIES_ID_COL = [\\'product_name\\']\n",
         "        ) AS\n",
         "        SELECT\n",
         "          hourly_timestamp,\n",
@@ -1119,7 +1144,7 @@
         "            project=project,\n",
         "            location=location,\n",
         "        )\n",
-        "        .set_display_name(\"train arima plus model\")\n",
+        "        .set_display_name(\"run arima+ model experiment\")\n",
         "        .after(create_training_dataset_op)\n",
         "    )\n",
         "\n",
@@ -1128,12 +1153,12 @@
         "        BigqueryMLArimaEvaluateJobOp(\n",
         "            project=project,\n",
         "            location=location,\n",
-        "            model=bq_arima_model_op.outputs[\"model\"],\n",
+        "            model=bq_arima_model_exp_op.outputs[\"model\"],\n",
         "            show_all_candidate_models=False,\n",
         "            job_configuration_query=bq_evaluate_time_series_configuration,\n",
         "        )\n",
         "        .set_display_name(\"evaluate arima plus time series\")\n",
-        "        .after(bq_arima_model_op)\n",
+        "        .after(bq_arima_model_exp_op)\n",
         "    )\n",
         "\n",
         "    # Evaluate ARIMA Plus model\n",
@@ -1141,12 +1166,12 @@
         "        BigqueryEvaluateModelJobOp(\n",
         "            project=project,\n",
         "            location=location,\n",
-        "            model=bq_arima_model_op.outputs[\"model\"],\n",
+        "            model=bq_arima_model_exp_op.outputs[\"model\"],\n",
         "            query_statement=f\"\"\"SELECT * FROM `{project}.{bq_dataset}.{bq_training_table}` WHERE split='TEST'\"\"\",\n",
         "            job_configuration_query=bq_evaluate_model_configuration,\n",
         "        )\n",
         "        .set_display_name(\"evaluate arima plus model\")\n",
-        "        .after(bq_arima_model_op)\n",
+        "        .after(bq_arima_model_exp_op)\n",
         "    )\n",
         "\n",
         "    # Plot model metrics\n",
@@ -1164,6 +1189,34 @@
         "        < PERF_THRESHOLD,\n",
         "        name=\"avg. mae good\",\n",
         "    ):\n",
+        "        # Train the ARIMA PLUS model\n",
+        "        bq_arima_model_op = (\n",
+        "            BigqueryCreateModelJobOp(\n",
+        "                query=f\"\"\"\n",
+        "        -- create model table\n",
+        "        CREATE OR REPLACE MODEL `{project}.{bq_dataset}.{bq_model_table}`\n",
+        "        OPTIONS(\n",
+        "        MODEL_TYPE = \\'ARIMA_PLUS\\',\n",
+        "        TIME_SERIES_TIMESTAMP_COL = \\'hourly_timestamp\\',\n",
+        "        TIME_SERIES_DATA_COL = \\'total_sold\\',\n",
+        "        TIME_SERIES_ID_COL = [\\'product_name\\'],\n",
+        "        MODEL_REGISTRY = \\'vertex_ai\\',\n",
+        "        VERTEX_AI_MODEL_ID = \\'order_demand_forecasting\\',\n",
+        "        VERTEX_AI_MODEL_VERSION_ALIASES = [\\'staging\\']\n",
+        "        ) AS\n",
+        "        SELECT\n",
+        "          DATETIME_TRUNC(time_of_sale, HOUR) as hourly_timestamp,\n",
+        "          product_name,\n",
+        "          SUM(quantity) AS total_sold,\n",
+        "          FROM `{project}.{bq_dataset}.{bq_orders_table}`\n",
+        "        GROUP BY hourly_timestamp, product_name;\n",
+        "        \"\"\",\n",
+        "                project=project,\n",
+        "                location=location,\n",
+        "            )\n",
+        "            .set_display_name(\"train arima+ model\")\n",
+        "            .after(get_evaluation_model_metrics_op)\n",
+        "        )\n",
         "\n",
         "        # Generate the ARIMA PLUS forecasts\n",
         "        bq_arima_forecast_op = (\n",
@@ -1224,7 +1277,7 @@
       "source": [
         "### Execute your pipeline\n",
         "\n",
-        "Next, you execute the pipeline. It takes the following parameters which we set as default:\n",
+        "Next, we execute the pipeline. It takes the following parameters which we set as default:\n",
         "\n",
         "- `bq_dataset`: The BigQuery dataset to train on.\n",
         "- `bq_orders_table` : The BigQuery table of raw data.\n",
@@ -1266,7 +1319,7 @@
       "source": [
         "### View BigQuery ML training pipeline results\n",
         "\n",
-        "Finally, you will view the artifact outputs of each task in the pipeline."
+        "Finally, you view the artifact outputs of each task in the pipeline."
       ]
     },
     {
@@ -1342,8 +1395,8 @@
         "print(\"bigquery-ml-arima-evaluate-job\")\n",
         "artifacts = print_pipeline_output(bqml_pipeline, \"bigquery-ml-arima-evaluate-job\")\n",
         "print(\"\\n\\n\")\n",
-        "print(\"get-model-evaluation-metrics\")\n",
-        "artifacts = print_pipeline_output(bqml_pipeline, \"get-model-evaluation-metrics\")\n",
+        "print(\"bigquery-evaluate-model-job\")\n",
+        "artifacts = print_pipeline_output(bqml_pipeline, \"bigquery-evaluate-model-job\")\n",
         "print(\"\\n\\n\")\n",
         "print(\"bigquery-forecast-model-job\")\n",
         "artifacts = print_pipeline_output(bqml_pipeline, \"bigquery-forecast-model-job\")\n",
@@ -1407,7 +1460,8 @@
         "\n",
         "# Remove local resorces\n",
         "! rm -rf {KFP_COMPONENTS_PATH}\n",
-        "! rm -rf {PIPELINES_PATH}"
+        "! rm -rf {PIPELINES_PATH}\n",
+        "! rm -rf {DATA_PATH}"
       ]
     }
   ],

notebooks/community/pipelines/google_cloud_pipeline_components_cloud_natural_language_pipeline.ipynb

@@ -42,12 +42,12 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/natural_language/cloud_natural_language_pipeline.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/pipelines/google_cloud_pipeline_components_cloud_natural_language_pipeline.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/natural_language/cloud_natural_language_pipeline.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/pipelines/google_cloud_pipeline_components_cloud_natural_language_pipeline.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
@@ -328,7 +328,7 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"cloud-ml-language-test\"  # @param {type:\"string\"}\n",
+        "PROJECT_ID = \"your-project-id\"  # @param {type:\"string\"}\n",
         "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
         "    # Get your GCP project id from gcloud\n",
         "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
@@ -368,7 +368,7 @@
       "source": [
         "REGION = \"us\"  # @param {type:\"string\"}\n",
         "LOCATION = \"us-central1\"  # @param {type:\"string\"}\n",
-        "TRAINING_DATA_LOCATION = \"gs://dougchen-20221130-pipeline-colab-test/data-00001-of-00001.jsonl\"  # @param {type:\"string\"}\n",
+        "TRAINING_DATA_LOCATION = \"gs://your-training-data-location\"  # @param {type:\"string\"}\n",
         "TASK_TYPE = \"CLASSIFICATION\"  # @param [\"CLASSIFICATION\", \"MULTILABEL_CLASSIFICATION\"]"
       ]
     },
@@ -740,7 +740,7 @@
         "\n",
         "This sends a create pipeline job request to Vertex Pipelines. Note that this  task run synchronously and may take a while to complete.\n",
         "\n",
-        "You may view the progress of the job at any time by clicking on the generated links (after \"View Pipeline Job\" in the console output of the cell below). Once the pipeline finishes, you may examine the artifacts produced from this pipeline. See "
+        "You may view the progress of the job at any time by clicking on the generated links (after \"View Pipeline Job\" in the console output of the cell below). Once the pipeline finishes, you may examine the artifacts produced from this pipeline."
       ]
     },
     {

notebooks/community/pipelines/google_cloud_pipeline_components_ready_to_go_text_classification_pipeline.ipynb

@@ -42,12 +42,12 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/community-content/ready_to_go_text_classification_pipeline/ready_to_go_text_classification_pipeline.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/pipelines/google_cloud_pipeline_components_ready_to_go_text_classification_pipeline.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/community-content/ready_to_go_text_classification_pipeline/ready_to_go_text_classification_pipeline.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/pipelines/google_cloud_pipeline_components_ready_to_go_text_classification_pipeline.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
@@ -706,7 +706,7 @@
         ")\n",
         "\n",
         "# The GCS directory for keeping staging files for model evaluation.\n",
-        "ROOT_DIR = 'f\"{BASE_OUTPUT_DIR}/root\"'  # @param {type:\"string\"}"
+        "ROOT_DIR = \"'f\\\"{BASE_OUTPUT_DIR}/root\\\"'\"  # @param {type:\"string\"}"
       ]
     },
     {

notebooks/community/vertex_endpoints/optimized_tensorflow_runtime/benchmark.py

@@ -112,7 +112,7 @@ def benchmark(
 
     results = []
     for qps in qps_list:
-        num_requests = max(qps * duration_sec, 10)
+        num_requests = int(max(qps * duration_sec, 10))
         requests_for_qps = list(
             itertools.islice(itertools.cycle(requests), num_requests)
         )

notebooks/community/vertex_endpoints/optimized_tensorflow_runtime/tabular_optimized_online_prediction.ipynb

@@ -1479,7 +1479,7 @@
       "source": [
         "For more information about VPC peering in Vertex AI, see https://cloud.google.com/vertex-ai/docs/general/vpc-peering.\n",
         "\n",
-        "**IMPORTANT: you can only setup one VPC peering to servicenetworking.googleapis.com per project.**"
+        "**IMPORTANT: you can only setup one VPC peering to servicenetworking.googleapis.com per VPC network.**"
       ]
     },
     {

notebooks/community/vertex_endpoints/torchserve/dreambooth_stablediffusion.ipynb

@@ -0,0 +1,987 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "18ebbd838e32"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "# https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "219f1b1fe8fe"
+      },
+      "source": [
+        "# Deploy and host a Stable Diffusion model on Vertex AI\n"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "JAPoU8Sm5E6e"
+      },
+      "source": [
+        "<table align=\"left\">\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/vertex_endpoints/torchserve/dreambooth_stablediffusion.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/vertex_endpoints/torchserve/dreambooth_stablediffusion.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        " <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/vertex_endpoints/torchserve/dreambooth_stablediffusion.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fce05a8186d6"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates how to deploy and host a fine-tuned [Stable Diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) model on Vertex AI. For hosting, you use the PyTorch 3 container built for Vertex AI with [TorchServe](https://pytorch.org/serve/index.html)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c76216b03fec"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to host and deploy a Stable Diffusion 1.5 model on Vertex AI.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "+ Vertex AI `Model` resource\n",
+        "+ Vertex AI `Endpoint` resource\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "+ Create a `torchserve` handler for responding to prediction requests.\n",
+        "+ Upload a Stable Diffusion 1.5 model on a prebuilt PyTorch container in Vertex AI.\n",
+        "+ Deploy a model to a Vertex AI Endpoint.\n",
+        "+ Send requests to the endpoint and parse the responses using Vertex AI Prediction service."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c6deba5a8557"
+      },
+      "source": [
+        "### Model\n",
+        "\n",
+        "This notebook uses a collection of model artifacts fine-tuned to generate images of a small dog. These are the same images used in the original [DreamBooth paper](https://dreambooth.github.io/)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "911dc651ea9c"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI models\n",
+        "* Vertex AI endpoints\n",
+        "* Vertex AI prediction\n",
+        "* Cloud Storage\n",
+        "* (Optionally) Vertex AI Workbench\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0d36bd3d53fa"
+      },
+      "source": [
+        "## Hardware requirements\n",
+        "\n",
+        "This notebook requires that you use a GPU with a sufficient amount of VRAM available. It was tested on a `NVIDIA Tesla A100 GPU` with 85 GB of VRAM. Run the following cell to ensure that you have the correct hardware configuration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3dd4022552e5"
+      },
+      "outputs": [],
+      "source": [
+        "!nvidia-smi --query-gpu=name,memory.total,memory.free --format=\"csv,noheader\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a782627e5f73"
+      },
+      "source": [
+        "### Create a user-managed notebook on Vertex AI\n",
+        "\n",
+        "If you are using Vertex AI Workbench, you can create a notebook with the correct configuration by doing the following:\n",
+        "\n",
+        "+ Go to [Vertex AI Workbench](https://console.cloud.google.com/vertex-ai/workbench/user-managed) in the Google Cloud Console.\n",
+        "+ Click **New Notebook** and then click **PyTorch 1.13** > **With 1 NVIDIA T4**.\n",
+        "+ In the **New notebook** dialog box, click **Advanced Options**. The **Create a user-managed notebook** page opens up.\n",
+        "+ In the **Create a user-managed notebook** page, do the following:\n",
+        "  * In the **Notebook name** box, type a name for your notebook, for example \"my-stablediffusion-nb\".\n",
+        "  * In the **Machine type** drop-down, select **A2 highgpu** > **a2-highgpu-1g**.\n",
+        "  * In the **GPU type** drop-down, select **NVIDIA Tesla A100**.\n",
+        "  * Check the box next to **Install NVIDIA GPU driver automatically for me**\n",
+        "  * Expand **Disk(s)** and do the following:\n",
+        "    - Under **Boot disk type**, select **SSD Persistent Disk**.\n",
+        "    - Under **Data disk type**, select **SSD Persistent Disk**.\n",
+        "  * Click **Create**."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FAPoU8Sm5E6e"
+      },
+      "source": [
+        "<div style=\"background:#feefe3; padding:5px; color:#aa0000\">\n",
+        "<strong>Caution:</strong> Using a Vertex AI Workbench notebook with the above configuration can increase your costs significantly. You can estimate your costs using the <a href=\"https://cloud.google.com/products/calculator\"><u>costs calculator</u></a>.</div>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0bb4201cc99a"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the following packages required to execute this notebook.\n",
+        "\n",
+        "**Note**: You might need to change the version of PyTorch (`torch`) installed by `pip`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9c769df171a6"
+      },
+      "outputs": [],
+      "source": [
+        "%%writefile requirements.txt\n",
+        "diffusers\n",
+        "ftfy\n",
+        "google-cloud-aiplatform\n",
+        "gradio\n",
+        "ninja\n",
+        "tensorboard==1.15.0\n",
+        "torch\n",
+        "torchaudio\n",
+        "torchvision\n",
+        "torchserve\n",
+        "torch-model-archiver\n",
+        "torch-workflow-archiver\n",
+        "transformers"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e46804ac90d8"
+      },
+      "outputs": [],
+      "source": [
+        "%pip install -r requirements.txt"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "58707a750154"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "77c11549298a"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "294df346a918"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "3. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WReHDGG5g0XY"
+      },
+      "source": [
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "oM1iC_MfAts1"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "sBCra4QMA2wR"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "74ccc9e52986"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "de775a3773ba"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "254614fa0c46"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ef21552ccea8"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "603adbbf0532"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f6b2ccc891ed"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cb5c4ca3e851"
+      },
+      "source": [
+        "### Import libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7348591eda51"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import math\n",
+        "\n",
+        "import torch\n",
+        "from diffusers import StableDiffusionPipeline\n",
+        "from google.cloud import aiplatform\n",
+        "from IPython import display\n",
+        "from PIL import Image\n",
+        "from torch import autocast"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "697566b5f660"
+      },
+      "source": [
+        "## Optional: View model inferences\n",
+        "\n",
+        "Before uploading the model to Vertex AI, you can review the expected output from the model. The model used in this notebook is available for your use and can be downloaded from Cloud Storage. This download may take a few minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d63df8d91215"
+      },
+      "outputs": [],
+      "source": [
+        "!gsutil -m cp gs://cloud-samples-data/vertex-ai/model-deployment/models/stable-diffusion/model_artifacts.zip \\\n",
+        "   ."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89d613ae9573"
+      },
+      "outputs": [],
+      "source": [
+        "!unzip model_artifacts.zip"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9192ea4f3b57"
+      },
+      "source": [
+        "### Create new images\n",
+        "\n",
+        "With everything in place, you can now generate new images from the Stable Diffusion model. First you must load your model into a `StableDiffusionPipeline`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cd1f30223b79"
+      },
+      "outputs": [],
+      "source": [
+        "model_path = \"model_artifacts\"\n",
+        "\n",
+        "pipe = StableDiffusionPipeline.from_pretrained(\n",
+        "    model_path, torch_dtype=torch.float16\n",
+        ").to(\"cuda\")\n",
+        "\n",
+        "g_cuda = None"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dd91520f58cf"
+      },
+      "outputs": [],
+      "source": [
+        "g_cuda = torch.Generator(device=\"cuda\")\n",
+        "seed = 52362\n",
+        "g_cuda.manual_seed(seed)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1e9c5d734b9f"
+      },
+      "source": [
+        "With the model loaded into a `StableDiffusionPipeline`, you can now generate results (inferences) from the model. Each set of inference requires an input (called a [prompt](https://learnprompting.org/)) that specifies what the model should create.\n",
+        "\n",
+        "You can also vary other inputs into the model, as shown in the following cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a28b73de55ce"
+      },
+      "outputs": [],
+      "source": [
+        "prompt = \"photo of examplePup dog in a Monet style\"\n",
+        "\n",
+        "num_samples = 4\n",
+        "num_batches = 1\n",
+        "num_columns = 2\n",
+        "guidance_scale = 10\n",
+        "num_inference_steps = 50\n",
+        "height = 512\n",
+        "width = 512"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "11a7bb79de59"
+      },
+      "outputs": [],
+      "source": [
+        "def image_grid(imgs, cols):\n",
+        "    total = len(imgs)\n",
+        "    rows = math.ceil(total / cols)\n",
+        "\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    grid_w, grid_h = grid.size\n",
+        "\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "all_images = []\n",
+        "for _ in range(num_batches):\n",
+        "    with autocast(\"cuda\"):\n",
+        "        images = pipe(\n",
+        "            [prompt] * num_samples,\n",
+        "            height=height,\n",
+        "            width=width,\n",
+        "            num_inference_steps=num_inference_steps,\n",
+        "            guidance_scale=guidance_scale,\n",
+        "        ).images\n",
+        "        all_images.extend(images)\n",
+        "\n",
+        "\n",
+        "grid = image_grid(all_images, num_columns)\n",
+        "grid"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bbc72963ff88"
+      },
+      "source": [
+        "## Deploy the model to Vertex AI\n",
+        "\n",
+        "You can host your Stable Diffusion 1.5 model on a Vertex AI endpoint where you can get inferences from it online. Uploading your model is a four step process: \n",
+        "\n",
+        "1. Create a custom TorchServe handler.\n",
+        "1. Upload the model artifacts onto Cloud Storage.\n",
+        "2. Create a Vertex AI model with the model artifacts and a prebuilt PyTorch container image.\n",
+        "3. Deploy the Vertex AI model onto an endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "eafbb0e0-40e6-43a0-a38e-edc54323da51"
+      },
+      "source": [
+        "### Create the custom TorchServe handler\n",
+        "\n",
+        "The model deployed to Vertex AI uses [TorchServe](https://pytorch.org/serve/) to handle requests and return responses from the model. You must create a custom TorchServe handler to include in with the model artifacts uploaded to Vertex AI.\n",
+        "\n",
+        "The handler file should be included in the directory with the other model artifacts."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "94567a87-9d74-4c87-a749-306ddaf01b61"
+      },
+      "outputs": [],
+      "source": [
+        "%%writefile model_artifacts/handler.py\n",
+        "\n",
+        "\"\"\"Customized handler for Stable Diffusion 1.5.\"\"\"\n",
+        "import base64\n",
+        "import logging\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import torch\n",
+        "from diffusers import EulerDiscreteScheduler\n",
+        "from diffusers import StableDiffusionPipeline\n",
+        "from ts.torch_handler.base_handler import BaseHandler\n",
+        "\n",
+        "logger = logging.getLogger(__name__)\n",
+        "model_id = 'runwayml/stable-diffusion-v1-5'\n",
+        "\n",
+        "\n",
+        "class ModelHandler(BaseHandler):\n",
+        "\n",
+        "  def __init__(self):\n",
+        "    self.initialized = False\n",
+        "    self.map_location = None\n",
+        "    self.device = None\n",
+        "    self.use_gpu = True\n",
+        "    self.store_avg = True\n",
+        "    self.pipe = None\n",
+        "\n",
+        "  def initialize(self, context):\n",
+        "    \"\"\"Initializes the pipe.\"\"\"\n",
+        "    properties = context.system_properties\n",
+        "    gpu_id = properties.get('gpu_id')\n",
+        "\n",
+        "    self.map_location, self.device, self.use_gpu = \\\n",
+        "      ('cuda', torch.device('cuda:' + str(gpu_id)),\n",
+        "       True) if torch.cuda.is_available() else \\\n",
+        "        ('cpu', torch.device('cpu'), False)\n",
+        "\n",
+        "    # Use the Euler scheduler here instead\n",
+        "    scheduler = EulerDiscreteScheduler.from_pretrained(model_id,\n",
+        "                                                       subfolder='scheduler')\n",
+        "    pipe = StableDiffusionPipeline.from_pretrained(model_id,\n",
+        "                                                   scheduler=scheduler,\n",
+        "                                                   torch_dtype=torch.float16)\n",
+        "    pipe = pipe.to('cuda')\n",
+        "    # Uncomment the following line to reduce the GPU memory usage.\n",
+        "    # pipe.enable_attention_slicing()\n",
+        "    self.pipe = pipe\n",
+        "\n",
+        "    self.initialized = True\n",
+        "\n",
+        "  def preprocess(self, requests):\n",
+        "    \"\"\"Noting to do here.\"\"\"\n",
+        "    logger.info('requests: %s', requests)\n",
+        "    return requests\n",
+        "\n",
+        "  def inference(self, preprocessed_data, *args, **kwargs):\n",
+        "    \"\"\"Run the inference.\"\"\"\n",
+        "    images = []\n",
+        "    for pd in preprocessed_data:\n",
+        "      prompt = pd['prompt']\n",
+        "      images.extend(self.pipe(prompt).images)\n",
+        "    return images\n",
+        "\n",
+        "  def postprocess(self, output_batch):\n",
+        "    \"\"\"Converts the images to base64 string.\"\"\"\n",
+        "    postprocessed_data = []\n",
+        "    for op in output_batch:\n",
+        "      fp = BytesIO()\n",
+        "      op.save(fp, format='JPEG')\n",
+        "      postprocessed_data.append(base64.b64encode(fp.getvalue()).decode('utf-8'))\n",
+        "      fp.close()\n",
+        "    return postprocessed_data\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6ace1dac0af0"
+      },
+      "source": [
+        "After creating the handler file, you must package the handler as a model archiver (MAR) file. The output file must be named 'model.mar'."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "67707f95d440"
+      },
+      "outputs": [],
+      "source": [
+        "!torch-model-archiver \\\n",
+        "  -f \\\n",
+        "  --model-name model \\\n",
+        "  --version 1.0 \\\n",
+        "  --handler model_artifacts/handler.py \\\n",
+        "  --export-path model_artifacts"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ffab030f4bc8"
+      },
+      "source": [
+        "### Upload the model artifacts to Cloud Storage\n",
+        "\n",
+        "Create a new folder in your Cloud Storage bucket to hold the model artifacts"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "MzGDU7TWdts_"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_NAME = \"your-bucket-name-unique\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}/\"\n",
+        "FULL_GCS_PATH = f\"{BUCKET_URI}model_artifacts\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-EcIXiGsCePi"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NIq7R4HZCfIc"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "971232e28657"
+      },
+      "source": [
+        "Next, upload the model archive file and your trained Stable Diffusion 1.5 model to the folder on Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ef6baf44c808"
+      },
+      "outputs": [],
+      "source": [
+        "!gsutil cp -r model_artifacts $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "402370ca9396"
+      },
+      "source": [
+        "### Create the Vertex AI model\n",
+        "\n",
+        "Once you've uploaded the model artifacts into a Cloud Storage bucket, you can create a new Vertex AI model. This notebook uses the [Vertex AI SDK](https://cloud.google.com/vertex-ai/docs/start/use-vertex-ai-python-sdk) to create the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b6c58a74a0fd"
+      },
+      "outputs": [],
+      "source": [
+        "PYTORCH_PREDICTION_IMAGE_URI = (\n",
+        "    \"us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest\"\n",
+        ")\n",
+        "APP_NAME = \"my-stable-diffusion\"\n",
+        "VERSION = 1\n",
+        "MODEL_DISPLAY_NAME = \"stable_diffusion_1_5-unique\"\n",
+        "MODEL_DESCRIPTION = \"stable_diffusion_1_5 container\"\n",
+        "ENDPOINT_DISPLAY_NAME = f\"{APP_NAME}-endpoint\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "07c3503a1a2e"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FAPoU8Sm5E6e"
+      },
+      "source": [
+        "<div style=\"background:#e3effe; padding:5px; color:#0000aa\">\n",
+        "<strong>Note:</strong> The next cell fails if you haven't <a href=\"https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com\"><u>enabled the Vertex API</u></a>.</div>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a776324dd16f"
+      },
+      "outputs": [],
+      "source": [
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=MODEL_DISPLAY_NAME,\n",
+        "    description=MODEL_DESCRIPTION,\n",
+        "    serving_container_image_uri=PYTORCH_PREDICTION_IMAGE_URI,\n",
+        "    artifact_uri=FULL_GCS_PATH,\n",
+        ")\n",
+        "\n",
+        "model.wait()\n",
+        "\n",
+        "print(model.display_name)\n",
+        "print(model.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0fbc3d371574"
+      },
+      "source": [
+        "### Deploy the model to an endpoint\n",
+        "\n",
+        "To get online preductions from your Stable Diffusion 2.0 model, you must [deploy it to a Vertex AI endpoint](https://cloud.google.com/vertex-ai/docs/predictions/overview). You can again use the Vertex AI SDK to create the endpoint and deploy your model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ab29f0a770cb"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint = aiplatform.Endpoint.create(display_name=ENDPOINT_DISPLAY_NAME)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "25f703df88c7"
+      },
+      "outputs": [],
+      "source": [
+        "model.deploy(\n",
+        "    endpoint=endpoint,\n",
+        "    deployed_model_display_name=MODEL_DISPLAY_NAME,\n",
+        "    machine_type=\"n1-standard-8\",\n",
+        "    accelerator_type=\"NVIDIA_TESLA_P100\",\n",
+        "    accelerator_count=1,\n",
+        "    traffic_percentage=100,\n",
+        "    deploy_request_timeout=1200,\n",
+        "    sync=True,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c9fc560df0a9"
+      },
+      "source": [
+        "The previous cell, which deploys your model to the endpoint, can take a while to complete. If the previous cell times out before returning, your endpoint might still be successfully deployed to an endpoint. Check the [Cloud Console](https://console.cloud.google.com/vertex-ai/endpoints) to verify the results.\n",
+        "\n",
+        "You can also extend the time to wait for deployment by changing the `deploy_request_timeout` argument passed to `model.deploy()`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "88a5304dfdc9"
+      },
+      "source": [
+        "## Get online predictions\n",
+        "\n",
+        "Finally, with your Stable Diffusion 1.5 model deployed to a Vertex AI endpoint, you can now get online predictions from it. Using the Vertex AI SDK, you only need a few lines of code to get an inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0d6bc4aa34d6"
+      },
+      "outputs": [],
+      "source": [
+        "instances = [{\"prompt\": \"An examplePup dog with a baseball jersey.\"}]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "\n",
+        "with open(\"img5.jpg\", \"wb\") as g:\n",
+        "    g.write(base64.b64decode(response.predictions[0]))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65bafefda60c"
+      },
+      "outputs": [],
+      "source": [
+        "display.Image(\"img5.jpg\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "TpV-iwP9qw9c"
+      },
+      "source": [
+        "## Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "sx_vKniMq9ZX"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "# Delete endpoint resource\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
+        "\n",
+        "# Delete model resource\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete Cloud Storage objects that were created\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "dreambooth_stablediffusion.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/curated.csv

@@ -1,34 +0,0 @@
-tag,notebook,doc
-"AutoML, Text data",official/automl/automl-text-classification.ipynb,vertex-ai/docs/text-data/classification/train-model
-"AutoML, Tabular data",official/automl/sdk_automl_tabular_forecasting_batch.ipynb,vertex-ai/docs/tabular-data/forecasting/tutorials-samples
-"BigQuery, Vertex AI Workbench",official/workbench/exploratory_data_analysis/explore_data_in_bigquery_with_workbench.ipynb,
-"BigQuery ML, Vertex AI Model Registry, Batch prediction",official/model-registry/bqml-vertexai-model-registry.ipynb,
-"BigQuery ML, Vertex AI Model Registry, Online prediction",official/bigquery_ml/bqml-online-prediction.ipynb,
-Custom Training,official/custom/sdk-custom-image-classification-batch.ipynb,
-Custom Training,official/custom/sdk-custom-image-classification-online.ipynb,
-Tabular Data,official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb,vertex-ai/docs/tabular-data/forecasting-arima/overview
-"AutoML, Tabular Data",official/automl/automl_tabular_on_vertex_pipelines.ipynb,vertex-ai/docs/tabular-data/tabular-workflows/e2e-automl
-Vertex AI Experiments,official/experiments/comparing_pipeline_runs.ipynb,
-Vertex AI Experiments,official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb,
-Vertex AI Experiments,official/experiments/comparing_local_trained_models.ipynb,
-Vertex AI Feature Store,official/feature_store/sdk-feature-store.ipynb,
-Matching Engine,official/matching_engine/sdk_matching_engine_for_indexing.ipynb,
-Model Monitoring,official/model_monitoring/model_monitoring.ipynb,
-Vertex AI Pipelines,official/pipelines/lightweight_functions_component_io_kfp.ipynb,
-"Vertex AI Pipelines Image data",official/pipelines/google_cloud_pipeline_components_automl_images.ipynb,
-"Vertex AI Pipelines, Tabular data",official/pipelines/automl_tabular_classification_beans.ipynb,
-"Vertex AI Pipelines, Tabular data",official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb,
-"Vertex AI Pipelines, Text data",official/pipelines/google_cloud_pipeline_components_automl_text.ipynb,
-Vertex AI Pipelines,official/pipelines/custom_model_training_and_batch_prediction.ipynb,
-Vertex AI Pipelines,official/pipelines/google_cloud_pipeline_components_model_train_upload_deploy.ipynb,
-Vertex AI Pipelines,official/pipelines/control_flow_kfp.ipynb,
-Vertex AI Pipelines,official/pipelines/metrics_viz_run_compare_kfp.ipynb,
-Vertex AI Pipelines,official/pipelines/pipelines_intro_kfp.ipynb,
-Vertex AI Vizier,official/vizier/gapic-vizier-multi-objective-optimization.ipynb,vertex-ai/docs/vizier/using-vizier
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_automl_tabular_classification_online_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Image data",official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Image data",official/explainable_ai/sdk_custom_image_classification_online_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_custom_tabular_regression_batch_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-Vertex ML Metadata,official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb,

notebooks/notebook_template.ipynb

@@ -74,7 +74,9 @@
       "source": [
         "## Overview\n",
         "\n",
-        "{TODO: Include a paragraph or two explaining what this example demonstrates, who should be interested in it, and what you need to know before you get started.}"
+        "{TODO: Include a paragraph or two explaining what this example demonstrates, who should be interested in it, and what you need to know before you get started.}\n",
+        "\n",
+        "Learn more about [web-doc-title](linkback-to-webdoc-page). {TODO: if more than one primary feature, add tag/linkback for each one}"
       ]
     },
     {
@@ -160,7 +162,7 @@
       "outputs": [],
       "source": [
         "# Install the packages\n",
-        "! pip3 install --user --upgrade google-cloud-aiplatform"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform"
       ]
     },
     {
@@ -351,7 +353,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -371,7 +373,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l {REGION} -p {PROJECT_ID} {BUCKET_URI}"
       ]
     },
     {

notebooks/notebook_template_review.py

@@ -12,6 +12,10 @@
         --errors-codes: A list of error codes to report errors. Otherwise, all errors are reported.
         --errors-csv: Report errors in CSV format
         
+        # options for automatic fixing
+        --fix: Automatic fix
+        --fix-codes: A list of fix codes to fix. Otherwise, all fix codes are enabled.
+        
         # index generatation
         --repo: Generate index in markdown format
         --web: Generate index in HTML format
@@ -19,6 +23,7 @@
         --desc: Add description to index
         --steps: Add steps to index
         --uses: Add "resources" used to index
+        --linkback: Add linkback to index
         
     Format of CSV file for notebooks to review:
     
@@ -690,7 +695,26 @@ class ObjectiveRule(NotebookRule):
             ret = notebook.report_error(ErrorCode.ERROR_OBJECTIVE_MISSING_DESC, "Objective section missing desc")
         else:
             self.desc = self.desc.lstrip()
-            sentences = self.desc.split('.')
+            
+            bracket = False
+            paren = False
+            sentences = ""
+            for _ in range(len(self.desc)):
+                if self.desc[_] == '[':
+                    bracket = True
+                    continue
+                elif self.desc[_] == ']':
+                    bracket = False
+                    continue
+                elif self.desc[_] == '(':
+                    paren = True
+                elif self.desc[_] == ')':
+                    paren = False
+                    continue
+                    
+                if not paren:
+                    sentences += self.desc[_]
+            sentences = sentences.split('.')
             if len(sentences) > 1:
                 self.desc = sentences[0] + '.\n'
             if self.desc.startswith('In this tutorial, you learn') or self.desc.startswith('In this notebook, you learn'):
@@ -1116,32 +1140,44 @@ def add_index(path: str,
             print(f'            {tag.strip()}<br/>\n')
         print('        </td>')
         print('        <td>')
-        print(f'            <b>{title}</b><br/>\n')
+        print(f'            <b>{title}</b>. ')
         if args.desc:
             desc = replace_cl(desc.replace('`', ''))
             print('<br/>')
-            print(f'            {desc}<br/>\n')
+            print(f'            {desc}\n')
             
-        if args.steps:
-            steps = replace_cl(steps.replace('\n', '<br/>').replace('-', '&nbsp;&nbsp;-').replace('**', '').replace('*', '&nbsp;&nbsp;-').replace('`', ''))
-            print('<br/>' + steps +  '<br/>')
             
         if args.linkback and linkbacks:
             num = len(tags)
             for _ in range(num):
                 if linkbacks[_].startswith("vertex-ai"):
-                    print(f'<br/>            Learn more about <a href="https://cloud.google.com/{linkbacks[_]}" target="_blank">{replace_cl(tags[_])}</a>.\n')
+                    print(f' Learn more about <a href="https://cloud.google.com/{linkbacks[_]}" target="_blank">{replace_cl(tags[_])}</a>.\n')
                 else:
-                    print(f'<br/>            Learn more about <a href="{linkbacks[_]}" target="_blank">{replace_cl(tags[_])}</a>.\n')
+                    print(f' Learn more about <a href="{linkbacks[_]}" target="_blank">{replace_cl(tags[_])}</a>.\n')
+                    
+        if args.steps:
+            print("<devsite-expandable>\n")
+            print('  <p class="showalways">Tutorial steps</p>\n')
+            print('  <ul>\n')
+            
+            if ":" in steps:
+                steps = steps.split(':')[1].replace('*', '').replace('-', '').strip().split('\n')
+            else:
+                steps = []
+              
+            for step in steps:
+                print(f'    <li>{replace_cl(step)}</li>\n')
+            print('  </ul>\n')
+            print("</devsite-expandable>\n")
                     
         print('        </td>')
         print('        <td>')
         if colab_link:
-            print(f'            <a href="{colab_link}" target="_blank">Colab</a><br/>\n')
+            print(f'            <a href="{colab_link}" target="_blank" class="external" track-type="notebookTutorial" track-name="colabLink">Colab</a><br/>\n')
         if git_link:
-            print(f'            <a href="{git_link}" target="_blank">GitHub</a><br/>\n')
+            print(f'            <a href="{git_link}" target="_blank" class="external" track-type="notebookTutorial" track-name="gitHubLink">GitHub</a><br/>\n')
         if workbench_link:
-            print(f'            <a href="{workbench_link}" target="_blank">Vertex AI Workbench</a><br/>\n')
+            print(f'            <a href="{workbench_link}" target="_blank" class="external" track-type="notebookTutorial" track-name="workbenchLink">Vertex AI Workbench</a><br/>\n')
         print('        </td>')
         print('    </tr>\n')
     elif args.repo:
@@ -1204,14 +1240,16 @@ def replace_cl(text : str ) -> str:
         'Vertex AI Prediction': '{{vertex_prediction_name}}',
         'Vertex TensorBoard': '{{vertex_tensorboard_name}}',
         'Vertex AI TensorBoard': '{{vertex_tensorboard_name}}',
+        'TensorBoard': '{{vertex_tensorboard_name}}',
+        'Tensorboard': '{{vertex_tensorboard_name}}',
         'Vertex ML Metadata': '{{vertex_metadata_name}}',
         'Vertex Pipelines': '{{vertex_pipelines_name}}',
         'Vertex AI Pipelines': '{{vertex_pipelines_name}}',
         'Vertex AI Data Labeling': '{{vertex_data_labeling_name}}',
         'Vertex AI Experiments': '{{vertex_experiments_name}}',
         'Vertex Experiments': '{{vertex_experiments_name}}',
-        'Vertex AI Matching Engine': '{vertex_matching_engine_name}}',
-        'Vertex Matching Engine': '{vertex_matching_engine_name}}',
+        'Vertex AI Matching Engine': '{{vertex_matching_engine_name}}',
+        'Vertex Matching Engine': '{{vertex_matching_engine_name}}',
         'Vertex Model Monitoring': '{{vertex_model_monitoring_name}}',
         'Vertex AI Model Monitoring': '{{vertex_model_monitoring_name}}',
         'Vertex Feature Store': '{{vertex_featurestore_name}}',
@@ -1229,6 +1267,8 @@ def replace_cl(text : str ) -> str:
         'Vertex AI': '{{vertex_ai_name}}',
         
         'Cloud Storage': '{{storage_name}}',
+        'GCS': '{{storage_name}}',
+        'GCP': '{{gcp_name}}',
         'TensorFlow Enterprise': '{{tf4gcp_name}}',
         'TensorFlow': '{{tensorflow_name}}',
     }
@@ -1277,9 +1317,14 @@ if args.web:
     print('}')
     print('</style>')
     print('<table>')
-    print('    <th width="180px">Services</th>')
-    print('    <th>Description</th>')
-    print('    <th width="80px">Open in</th>')
+    print('    <thead>')
+    print('        <tr>')
+    print('            <th width="180px">Services</th>')
+    print('            <th>Description</th>')
+    print('            <th width="80px">Open in</th>')
+    print('        </tr>')
+    print('    </thead>')
+    print('    <tbody class="list">')
 
 if args.notebook_dir:
     if not os.path.isdir(args.notebook_dir):
@@ -1315,6 +1360,7 @@ else:
     exit(1)
 
 if args.web:
+    print('    </tbody>\n')
     print('</table>\n')
 
 exit(exit_code)

notebooks/notebook_template_writing_guidelines.md

@@ -23,7 +23,62 @@
     - Incorrect examples: "Let's update the field", "We'll update the field", "The user should update the field"
 - **Googlers**: Please follow our [branding guidelines](http://goto/cloud-branding).
 
-### Code
+
+## Authoring guidelines
+
+### Focus
+
+Notebooks for official are expected to be narrow focused, which highlight a subset of features of a Vertex AI product/service.
+The product/feature is to be highlighted in the Overview section. For example:
+
+```
+This tutorial demonstrates using Vertex AI Training to train an XGBoost model using a XGBoost pre-built training container.
+```
+
+In the above example, the Vertex AI product/service is `Vertex AI Training` and the feature is `XGBoost pre-built training container`.
+
+### Scope
+
+Notebooks for official are expected to be narrow in scope, without extra extraneous steps. For example, if the notebook is about training, we discourage ending the notebook with deploying the model and doing an online/batch prediction. On the later, we recommend a separate notebook about prediction that uses a pretrained model.
+
+#### Training
+
+Notebooks for training should be constructed as follows:
+
+1. If the training script(s) are small, embed them in the notebook and use %writefile to store them locally.
+2. If the training script(s) are large, store them in our public bucket: gs://cloud-samples-data/vertex-ai/dataset-management/script, and use !wgets to retrieve and store the script locally.
+3. Train the model using the Vertex AI SDK methods for custom training.
+4. Preferrable have the service upload the trained model to the Vertex AI Model Registry.
+4. Have the script do an evaluation.
+5. Retrieve the evaluation metrics and attach them as an artifact to the corresponding entry in the Model Registry.
+6. Optionally, download the model artifacts and test locally -- i.e., make a local prediction request.
+
+#### Evaluation
+
+Notebooks for evaluation should be constructed as follows:
+
+1. Use a pretrained model from a public repository.
+2. Upload the pretrained model to the Vertex AI Model Registry.
+3. Perform a model evaluation.
+4. Review the model evaluation.
+4. Attach the model evaluation to the corresponding entry in the Model Registry.
+
+#### Prediction
+
+Notebooks for prediction should be constructed as follows:
+
+1. Use a pretrained model from a public repository.
+2. If relevant, attach a serving function to the model artifacts.
+3. Upload the pretrained model to the Vertex AI Model Registry.
+4. For online:<br/>
+    A. Deploy the model.<br/>
+    B. Perform an online prediction.</br>
+    C. Review the result.
+5. For batch:<br/>
+    A. Perform a batch prediction.</br/>
+    B. Review the result.
+    
+## Code
 
 - Put all your installs and imports in a setup section.
 - Save the notebook with the Table of Contents open.
@@ -31,7 +86,7 @@
 - Follow the [Google Python Style guide](https://github.com/google/styleguide/blob/gh-pages/pyguide.md) and write readable code.
 - Keep cells small (max ~20 lines).
 
-## TensorFlow code style
+### TensorFlow code style
 
 Use the highest level API that gets the job done (unless the goal is to demonstrate the low level API). For example, when using Tensorflow:
 

notebooks/official.csv

@@ -1,70 +0,0 @@
-tag,notebook,doc
-"AutoML, Text data",official/automl/automl-text-classification.ipynb,vertex-ai/docs/text-data/classification/train-model
-"AutoML, Text data",official/automl/sdk_automl_text_entity_extraction_online.ipynb,
-"AutoML, Text data",official/automl/sdk_automl_text_sentiment_analysis_online.ipynb,
-"AutoML, Tabular data",official/automl/sdk_automl_tabular_forecasting_batch.ipynb,vertex-ai/docs/tabular-data/forecasting/tutorials-samples
-"AutoML, Tabular Data",official/automl/automl_tabular_on_vertex_pipelines.ipynb,vertex-ai/docs/tabular-data/tabular-workflows/e2e-automl
-"AutoML, Tabular Data",official/automl/sdk_automl_tabular_regression_batch_bq.ipynb,
-"AutoML, Tabular Data",official/automl/sdk_automl_tabular_regression_batch_bq.ipynb,
-"AutoML, Forecasting",official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb,vertex-ai/docs/tabular-data/forecasting-arima/overview
-"AutoML, Forecasting",official/automl/sdk_automl_tabular_forecasting_batch.ipynb,
-"AutoML, Image data",official/automl/sdk_automl_text_sentiment_analysis_online.ipynb,
-"AutoML, Video data",official/automl/sdk_automl_text_sentiment_analysis_online.ipynb,
-"AutoML, Video data",official/automl/sdk_automl_video_classification_batch.ipynb,
-"AutoML, Video data",official/automl/sdk_automl_video_object_tracking_batch.ipynb,
-"AutoML, Video data",official/sdk/SDK_AutoML_Video_Classification.ipynb,
-"BigQuery, Vertex AI Workbench",official/workbench/exploratory_data_analysis/explore_data_in_bigquery_with_workbench.ipynb,
-"BigQuery ML, Vertex AI Model Registry, Batch prediction",official/model_registry/bqml_vertexai_model_registry.ipynb,
-"BigQuery ML, Vertex AI Model Registry, Online prediction",official/bigquery_ml/bqml-online-prediction.ipynb,
-"BigQuery ML",official/structured_data/rapid_prototyping_bqml_automl.ipynb,
-Custom Training,official/custom/sdk-custom-image-classification-batch.ipynb,
-Custom Training,official/custom/sdk-custom-image-classification-online.ipynb,
-Custom Training,official/custom/SDK_Custom_Container_Prediction.ipynb,
-"Custom Training, BiqQuery dataset",official/custom/custom-tabular-bq-managed-dataset.ipynb,
-"Custom Training, TensorBoard",official/custom/custom-tabular-bq-managed-dataset.ipynb,
-"Custom Training, TensorBoard",official/tensorboard/tensorboard_custom_training_with_custom_container.ipynb,
-"Custom Training, TensorBoard",official/tensorboard/tensorboard_custom_training_with_prebuilt_container.ipynb
-"Custom Training, Managed dataset",official/sdk/SDK_Custom_Training_Python_Package_Managed_Text_Dataset_Tensorflow_Serving_Container.ipynb,
-"Custom Training, Distributed",official/training/multi_node_ddp_gloo_vertex_training_with_custom_container.ipynb,
-"Custom Training, Distributed",official/training/multi_node_ddp_nccl_vertex_training_with_custom_container.ipynb
-Vertex AI Experiments,official/experiments/comparing_pipeline_runs.ipynb,
-Vertex AI Experiments,official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb,
-Vertex AI Experiments,official/experiments/comparing_local_trained_models.ipynb,
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_automl_tabular_classification_online_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Image data",official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_custom_tabular_regression_batch_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-"Vertex Explainable AI, Tabular data",official/explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-Vertex ML Metadata,official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb,
-"Vertex Explainable AI, Image data",official/explainable_ai/sdk_custom_image_classification_online_explain.ipynb,vertex-ai/docs/explainable-ai/overview
-Vertex AI Feature Store,official/feature_store/sdk-feature-store.ipynb,
-Vertex AI Feature Store,official/feature_store/sdk-feature-store-pandas.ipynb,
-Vertex AI Matching Engine,official/matching_engine/sdk_matching_engine_for_indexing.ipynb,
-Vertex ML Metadata,official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb,
-Vertex ML Metadata,official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb,
-"Vertex ML Metadata, Vertex AI Pipelines",official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb,
-"Vertex AI Model Evaluation, AutoML",official/model_evaluation/automl_tabular_classification_model_evaluation.ipynb,
-"Vertex AI Model Evaluation, AutoML",official/model_evaluation/automl_tabular_regression_model_evaluation.ipynb,
-"Vertex AI Model Evaluation, AutoML",official/model_evaluation/automl_text_classification_model_evaluation.ipynb,
-"Vertex AI Model Evaluation, AutoML",official/model_evaluation/automl_video_classification_model_evaluation.ipynb,
-"Vertex AI Model Evaluation, Custom Training",official/model_evaluation/custom_tabular_regression_model_evaluation.ipynb,
-Model Monitoring,official/model_monitoring/model_monitoring.ipynb,
-Vertex AI Pipelines,official/pipelines/pipelines_intro_kfp.ipynb,
-Vertex AI Pipelines,official/pipelines/control_flow_kfp.ipynb,
-Vertex AI Pipelines,official/pipelines/metrics_viz_run_compare_kfp.ipynb,
-Vertex AI Pipelines,official/pipelines/lightweight_functions_component_io_kfp.ipynb,
-"Vertex AI Pipelines Image data",official/pipelines/google_cloud_pipeline_components_automl_images.ipynb,
-"Vertex AI Pipelines, Tabular data",official/pipelines/automl_tabular_classification_beans.ipynb,
-"Vertex AI Pipelines, Tabular data",official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb,
-"Vertex AI Pipelines, Tabular data",official/pipelines/google_cloud_pipeline_components_dataproc_tabular.ipynb,
-"Vertex AI Pipelines, Text data",official/pipelines/google_cloud_pipeline_components_automl_text.ipynb,
-"Vertex AI Pipelines, Text data",official/pipelines/google_cloud_pipeline_components_bqml_text.ipynb,
-Vertex AI Pipelines,official/pipelines/custom_model_training_and_batch_prediction.ipynb,
-Vertex AI Pipelines,official/pipelines/google_cloud_pipeline_components_model_train_upload_deploy.ipynb,
-Vertex AI Pipelines,official/pipelines/google_cloud_pipeline_components_model_upload_predict_evaluate.ipynb,
-"Vertex AI Training, Reduction Server, PyTorch",official/reduction_server/pytorch_distributed_training_reduction_server.ipynb,
-"Tabular Workflows, Vertex AI TabNet",official/tabnet/tabnet_vertex_tutorial.ipynb,
-"Tabular Workflows, Vertex AI TabNet, Vertex Explainablee AI",official/tabnet/ai-explanations-tabnet-algorithm.ipynb,
-"Tabular Workflows, Vertex AI TabNet, Vertex AI Pipelines",official/tabular_workflows/tabnet_on_vertex_pipelines.ipynb,
-"Tabular Workflows, Vertex AI Wide and Deep",official/tabular_workflows/wide_and_deep_on_vertex_pipelines.ipynb,
-Vertex AI Vizier,official/vizier/gapic-vizier-multi-objective-optimization.ipynb,vertex-ai/docs/vizier/using-vizier

notebooks/official/CODEOWNERS

@@ -29,17 +29,17 @@
 /pipelines/google_cloud_pipelines_dataproc_tabular @inardini
 /automl/automl_forecasting_bqml_arima_plus_comparison.ipynb @TheMichaelHu
 /automl/automl_tabular_on_vertex_pipelines.ipynb @helinwang
-/custom/custom_training_tensorboard_profiler.ipynb @itseric
+/custom/custom_training_tensorboard_profiler.ipynb @gericdong
+/custom/get_started_with_vertex_endpoint_and_shared_vm.ipynb @andrewferlitsch
 /workbench/spark/spark_sample_notebook.ipynb @bradmiro
 /workbench/spark/spark_ml.ipynb @bradmiro
 /model_registry/bqml_vertexai_model_registry.ipynb @soheilazangeneh
-/workbench/exploratory_data_analysis/explore_data_in_bigquery_with_workbench.ipynb @alokpattani
 /model_evaluation/automl_tabular_classification_model_evaluation.ipynb @soheilazangeneh
 /model_evaluation/automl_tabular_regression_model_evaluation.ipynb @soheilazangeneh
-/tabular_workflows/tabnet_on_vertex_pipelines.ipynb @sakagarwal
-/tabular_workflows/wide_and_deep_on_vertex_pipelines.ipynb @sakagarwal
+/tabular_workflows/prophet_on_vertex_pipelines.ipynb @TheMichaelHu
 /model_evaluation/custom_tabular_classification_model_evaluation.ipynb @soheilazangeneh
 /sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
-/automl/sdk_automl_forecasting_hierarchical_batch.ipynb @ivanmkc
-/prediction/custom_batch_prediction_feature_filter.ipynb @soheilazangeneh
-/feature_store/feature_store_streaming_ingestion_sdk.ipynb @soheilazangeneh
+/pipelines/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines @Ark-kun
+/experiments/get_started_with_vertex_experiments_autologging.ipynb @inardini
+/experiments/delete_outdated_tensorboard_experiments.ipynb @inardini
+/experiments/get_started_with_custom_training_autologging_local_script.ipynb @inardini

notebooks/official/README.md

@@ -4,441 +4,3 @@ The official notebooks are a collection of curated and non-curated notebooks aut
 
 The official notebooks are organized by Google Cloud Vertex AI services.
 
-## Manifest of Curated Notebooks
-
-### AutoML  Text data 
-
-
-[Create, train, and deploy an AutoML text classification model](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl-text-classification.ipynb)
-
-Learn how to use `AutoML` to train a text classification model.
-
-The steps performed include:
-
-* Create a `Vertex AI Dataset`.
-* Train an `AutoML` text classification `Model` resource.
-* Obtain the evaluation metrics for the `Model` resource.
-* Create an `Endpoint` resource.
-* Deploy the `Model` resource to the `Endpoint` resource.
-* Make an online prediction
-* Make a batch prediction
-
-### AutoML  Tabular data 
-
-
-[AutoML tabular forecasting model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb)
-
-Learn how to create an `AutoML` tabular forecasting model from a Python script, and then do a batch prediction using the Vertex AI SDK.
-
-The steps performed include:
-
-- Create a `Vertex AI Dataset` resource.
-- Train an `AutoML` tabular forecasting `Model` resource.
-- Obtain the evaluation metrics for the `Model` resource.
-- Make a batch prediction.
-
-### BigQuery ML  Vertex AI Model Registry  Batch prediction 
-
-
-[Deploy BiqQuery ML Model on Vertex AI Model Registry and make predictions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model-registry/bqml-vertexai-model-registry.ipynb)
-
-Learn how to use `Vertex AI Model Registry` with `BigQuery ML` and make batch predictions:
-
-The steps performed include:
-
-- Train a model with `BigQuery ML`
-- Upload the model to `Vertex AI Model Registry` 
-- Create a `Vertex AI Endpoint` resource
-- Deploy the `Model` resource to the `Endpoint` resource
-- Make `prediction` requests to the model endpoint
-- Run `batch prediction` job on the `Model` resource 
-
-
-### BigQuery ML  Vertex AI Model Registry  Online prediction 
-
-
-[Online prediction with BigQuery ML](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/bigquery_ml/bqml-online-prediction.ipynb)
-
-Learn how to train and deploy a churn prediction model for real-time inference, with the data in BigQuery and model trained using BigQuery ML, registered to Vertex AI Model Registry, and deployed to an endpoint on Vertex AI for online predictions.
-
-The steps performed include:
-
-- Using Python & SQL to query the public data in BigQuery
-- Preparing the data for modeling
-- Training a classification model using BigQuery ML and registering it to Vertex AI Model Registry
-- Inspecting the model on Vertex AI Model Registry
-- Deploying the model to an endpoint on Vertex AI
-- Making sample online predictions to the model endpoint
-
-
-### Custom Training 
-
-
-[Custom training and batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-batch.ipynb)
-
-Learn to use `Vertex AI Training` to create a custom trained model and use `Vertex AI Batch Prediction` to do a batch prediction on the trained model.
-
-The steps performed include:
-
-- Create a `Vertex AI` custom job for training a TensorFlow model.
-- Upload the trained model artifacts as a `Model` resource.
-- Make a batch prediction.
-
-[Custom training and online prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-online.ipynb)
-
-Learn to use `Vertex AI Training` to create a custom-trained model from a Python script in a Docker container, and learn to use `Vertex AI Prediction` to do a prediction on the deployed model by sending data.
-
-The steps performed include:
-
-- Create a `Vertex AI` custom job for training a TensorFlow model.
-- Upload the trained model artifacts to a `Model` resource.
-- Create a serving `Endpoint` resource.
-- Deploy the `Model` resource to a serving `Endpoint` resource.
-- Make a prediction.
-- Undeploy the `Model` resource.
-
-### Tabular Data 
-
-
-[Compare Vertex AI Forecasting and BigQuery ML ARIMA_PLUS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb)
-
-Learn how to create an BQML ARIMA_PLUS model using a training [Vertex AI Pipeline](https://cloud.
-
-The steps performed are:
-
-- Train the BQML ARIMA_PLUS model.
-- View BQML model evaluation.
-- Make a batch prediction with the BQML model.
-- Create a Vertex AI `Dataset` resource.
-- Train the Vertex AI Forecasting model.
-- View the Model evaluation.
-- Make a batch prediction with the Model.
-
-
-### AutoML  Tabular Data 
-
-
-[AutoML Tabular Pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb)
-
-Learn how to create two regression models using [Vertex Pipelines](https://cloud.
-
-The steps performed are:
-
-- Create a training pipeline that reduces the search space from the default to save time.
-- Create a training pipeline that reuses the architecture search results from the previous pipeline to save time.
-
-### Vertex AI Experiments 
-
-
-[Compare pipeline runs with Vertex AI Experiments](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/comparing_pipeline_runs.ipynb)
-
-Learn how to use `Vertex AI Experiments` to log a pipeline job and compare different pipeline jobs.
-
-
-
-[Build Vertex AI Experiment lineage for custom training](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb)
-
-Learn how to integrate preprocessing code in a Vertex AI experiments.
-
-
-
-[Track parameters and metrics for locally trained models](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/comparing_local_trained_models.ipynb)
-
-Learn how to use Vertex AI Experiments to compare and evaluate model experiments.
-
-The steps performed include:
-
-- log the model parameters
-- log the loss and metrics on every epoch to TensorBoard
-- log the evaluation metrics
-
-
-### Vertex AI Feature Store 
-
-
-[Online and Batch predictions using Vertex AI Feature Store](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/feature_store/sdk-feature-store.ipynb)
-
-Learn how to use `Vertex AI Feature Store` to import feature data, and to access the feature data for both online serving and offline tasks, such as training.
-
-The steps performed include:
-
-- Create featurestore, entity type, and feature resources.
-- Import feature data into `Vertex AI Feature Store` resource.
-- Serve online prediction requests using the imported features.
-- Access imported features in offline jobs, such as training jobs.
-
-### Matching Engine 
-
-
-[Create Vertex AI Matching Engine index](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb)
-
-Learn how to create Approximate Nearest Neighbor (ANN) Index, query against indexes, and validate the performance of the index.
-
-The steps performed include:
-
-* Create ANN Index and Brute Force Index
-* Create an IndexEndpoint with VPC Network
-* Deploy ANN Index and Brute Force Index
-* Perform online query
-* Compute recall
-
-
-### Model Monitoring 
-
-
-[Vertex AI Model Monitoring with Explainable AI Feature Attributions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring/model_monitoring.ipynb)
-
-Learn to use the `Vertex AI Model Monitoring` service to detect drift and anomalies in prediction requests from a deployed `Vertex AI Model` resource.
-
-The steps performed include:
-
-- Upload a pre-trained model as a `Vertex AI Model` resource.
-- Create an `Vertex AI Endpoint` resource.
-- Deploy the `Model` resource to the `Endpoint` resource.
-- Configure the `Endpoint` resource for model monitoring.
-- Initialize the baseline distribution for model monitoring.
-- Generate synthetic prediction requests.
-- Understand how to interpret the statistics, visualizations, other data reported by the model monitoring feature.
-
-### Vertex AI Pipelines 
-
-
-[Lightweight Python function-based components, and component I/O](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb)
-
-Learn to use the KFP SDK to build lightweight Python function-based components, and then you learn to use `Vertex AI Pipelines` to execute the pipeline.
-
-The steps performed include:
-
-- Build Python function-based KFP components.
-- Construct a KFP pipeline.
-- Pass *Artifacts* and *parameters* between components, both by path reference and by value.
-- Use the `kfp.dsl.importer` method.
-- Compile the KFP pipeline.
-- Execute the KFP pipeline using `Vertex AI Pipelines`
-
-### Vertex AI Pipelines Image data 
-
-
-[AutoML image classification pipelines using google-cloud-pipeline-components](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.ipynb)
-
-Learn how to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` image classification model.
-
-The steps performed include:
-
-- Create a KFP pipeline:
-    - Create a `Dataset` resource.
-    - Train an AutoML image classification `Model` resource.
-    - Create an `Endpoint` resource.
-    - Deploys the `Model` resource to the `Endpoint` resource.
-- Compile the KFP pipeline.
-- Execute the KFP pipeline using `Vertex AI Pipelines`
-
-
-
-### Vertex AI Pipelines  Tabular data 
-
-
-[AutoML Tabular pipelines using google-cloud-pipeline-components](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/automl_tabular_classification_beans.ipynb)
-
-Learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` tabular classification model.
-
-The steps performed include:
-
-- Create a KFP pipeline:
-    - Create a `Dataset` resource.
-    - Train an AutoML tabular classification `Model` resource.
-    - Create an `Endpoint` resource.
-    - Deploys the `Model` resource to the `Endpoint` resource.
-- Compile the KFP pipeline.
-- Execute the KFP pipeline using `Vertex AI Pipelines`
-
-
-
-[AutoML tabular regression pipelines using google-cloud-pipeline-components](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb)
-
-Learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` tabular regression model.
-
-The steps performed include:
-
-- Create a KFP pipeline:
-    - Create a `Dataset` resource.
-    - Train an AutoML tabular regression `Model` resource.
-    - Create an `Endpoint` resource.
-    - Deploys the `Model` resource to the `Endpoint` resource.
-- Compile the KFP pipeline.
-- Execute the KFP pipeline using `Vertex AI Pipelines`
-
-
-
-### Vertex AI Pipelines  Text data 
-
-
-[AutoML text classification pipelines using google-cloud-pipeline-components](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb)
-
-Learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` text classification model.
-
-The steps performed include:
-
-- Create a KFP pipeline:
-    - Create a `Dataset` resource.
-    - Train an AutoML text classification `Model` resource.
-    - Create an `Endpoint` resource.
-    - Deploys the `Model` resource to the `Endpoint` resource.
-- Compile the KFP pipeline.
-- Execute the KFP pipeline using `Vertex AI Pipelines`
-
-
-
-### Vertex AI Pipelines 
-
-
-[Custom training with pre-built Google Cloud Pipeline Components](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/custom_model_training_and_batch_prediction.ipynb)
-
-Learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build a custom model.
-
-The steps performed include:
-
-- Create a KFP pipeline:
-    - Train a custom model.
-    - Upload the trained model as a `Model` resource.
-    - Create an `Endpoint` resource.
-    - Deploy the `Model` resource to the `Endpoint` resource.
-    - Make a batch prediction request.
-
-
-
-[Pipeline control structures using the KFP SDK](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/control_flow_kfp.ipynb)
-
-Learn how to use the KFP SDK to build pipelines that use loops and conditionals, including nested examples.
-
-The steps performed include:
-
-- Create a KFP pipeline:
-    - Use control flow components
-- Compile the KFP pipeline.
-- Execute the KFP pipeline using `Vertex AI Pipelines`
-
-[Metrics visualization and run comparison using the KFP SDK](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/metrics_viz_run_compare_kfp.ipynb)
-
-Learn how to use the KFP SDK to build pipelines that generate evaluation metrics.
-
-The steps performed include:
-
-- Create KFP components:
-    - Generate ROC curve and confusion matrix visualizations for classification results
-    - Write metrics
-- Create KFP pipelines.
-- Execute KFP pipelines
-- Compare metrics across pipeline runs
-
-[Pipelines introduction for KFP](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/pipelines_intro_kfp.ipynb)
-
-Learn how to use the KFP SDK to build pipelines that generate evaluation metrics.
-
-The steps performed include:
-
-- Define and compile a `Vertex AI` pipeline.
-- Specify which service account to use for a pipeline run.
-
-### Vertex AI Vizier 
-
-
-[Optimizing multiple objectives with Vertex AI Vizier](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb)
-
-Learn how to use `Vertex AI Vizier` to optimize a multi-objective study.
-
-
-
-### Vertex Explainable AI  Tabular data 
-
-
-[AutoML training tabular binary classification model for batch explanation](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb)
-
-Learn to use `AutoML` to create a tabular binary classification model from a Python script, and then learn to use `Vertex AI Batch Prediction` to make predictions with explanations.
-
-The steps performed include:
-
-- Create a `Vertex Dataset` resource.
-- Train an `AutoML` tabular binary classification model.
-- View the model evaluation metrics for the trained model.
-- Make a batch prediction request with explainability.
-
-
-* Prediction Service: Does an on-demand prediction for the entire set of instances (i.e., one or more data items) and returns the results in real-time.
-
-* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready.
-
-[AutoML training tabular classification model for online explanation](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_automl_tabular_classification_online_explain.ipynb)
-
-Learn how to use `AutoML` to create a tabular binary classification model from a Python script, and then learn to use `Vertex AI Online Prediction` to make online predictions with explanations.
-
-The steps performed include:
-
-- Create a `Vertex Dataset` resource.
-- Train an `AutoML` tabular binary classification model.
-- View the model evaluation metrics for the trained model.
-- Create a serving `Endpoint` resource.
-- Deploy the `Model` resource to a serving `Endpoint` resource.
-- Make an online prediction request with explainability.
-- Undeploy the `Model` resource.
-
-### Vertex Explainable AI  Image data 
-
-
-[Custom training image classification model for batch prediction with explainabilty](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb)
-
-Learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Batch Prediction` to make a batch prediction request with explanations.
-
-The steps performed include:
-
-- Create a `Vertex AI` custom job for training a TensorFlow model.
-- View the model evaluation for the trained model.
-- Set explanation parameters for when the model is deployed.
-- Upload the trained model artifacts and explanation parameters as a `Model` resource.
-- Make a batch prediction with explanations.
-
-[Custom training image classification model for online prediction with explainabilty](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_image_classification_online_explain.ipynb)
-
-Learn how to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Prediction` to make an online prediction request with explanations.
-
-The steps performed include:
-
-- Create a `Vertex AI` custom job for training a TensorFlow model.
-- View the model evaluation for the trained model.
-- Set explanation parameters for when the model is deployed.
-- Upload the trained model artifacts and explanations as a `Model` resource.
-- Create a serving `Endpoint` resource.
-- Deploy the `Model` resource to a serving `Endpoint` resource.
-- Make a prediction with explanation.
-- Undeploy the `Model` resource.
-
-### Vertex Explainable AI  Tabular data 
-
-
-[Custom training tabular regression model for batch prediction with explainabilty](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_tabular_regression_batch_explain.ipynb)
-
-Learn how to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Batch Prediction` to make a batch prediction request with explanations.
-
-The steps performed include:
-
-- Create a `Vertex AI` custom job for training a TensorFlow model.
-- View the model evaluation for the trained model.
-- Set explanation parameters for when the model is deployed.
-- Upload the trained model artifacts and explanations as a `Model` resource.
-- Make a batch prediction with explanations.
-
-### Vertex ML Metadata 
-
-
-[Track parameters and metrics for custom training jobs](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb)
-
-Learn how to use Vertex AI SDK for Python to:
-
-The steps performed include:
-- Track training parameters and prediction metrics for a custom training job.
-- Extract and perform analysis for all parameters and metrics within an Experiment.
-
-
-
-
- 

notebooks/official/automl/README.md

@@ -14,7 +14,7 @@ The steps performed include the following:
 
 ```
 
-   Learn more about [Tabular classification](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/overview).
+   Learn more about [Classification for tabular data](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/overview).
 
 
 [Create, train, and deploy an AutoML text classification model](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl-text-classification.ipynb)
@@ -34,13 +34,13 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Text classification](https://cloud.google.com/vertex-ai/docs/text-data/classification/train-model).
+   Learn more about [Classification for text data](https://cloud.google.com/vertex-ai/docs/training-overview#classification_for_text).
 
 
 [Compare Vertex AI Forecasting and BigQuery ML ARIMA_PLUS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb)
 
 ```
-Learn how to create an BigQuery ML ARIMA_PLUS model using a training [Vertex AI Pipeline](https://cloud.
+Learn how to create an BigQuery ML ARIMA_PLUS model using a training Vertex AI Pipeline from Google Cloud Pipeline Components , and then do a batch prediction using the corresponding prediction pipeline.
 
 The steps performed are:
 
@@ -54,15 +54,84 @@ The steps performed are:
 
 ```
 
-   Learn more about [AutoML Forecasting](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/overview).
+   Learn more about [BQML ARIMA+ forecasting for tabular data](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting-arima/overview).
 
-   Learn more about [BQML Forecasting](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting-arima/overview).
+
+[AutoML training image classification model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_classification_batch_prediction.ipynb)
+
+```
+In this tutorial, you create an AutoML image classification model from a Python script, and then do a batch prediction using the Vertex SDK.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Make a batch prediction.
+
+```
+
+   Learn more about [Get predictions from an image classification model](https://cloud.google.com/vertex-ai/docs/image-data/classification/get-predictions).
+
+
+[AutoML training image classification model for online prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_classification_online_prediction.ipynb)
+
+```
+In this tutorial, you create an AutoML image classification model and deploy for online prediction from a Python script using the Vertex SDK.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Deploy the `Model` resource to a serving `Endpoint` resource.
+- Make a prediction.
+- Undeploy the `Model`.
+
+```
+
+   Learn more about [Get predictions from an image classification model](https://cloud.google.com/vertex-ai/docs/image-data/classification/get-predictions).
+
+
+[AutoML training image object detection model for export to edge](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_object_detection_export_edge.ipynb)
+
+```
+In this tutorial, you create an AutoML image object detection model from a Python script using the Vertex SDK, and then export the model as an Edge model in TFLite format.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train the model.
+- Export the `Edge` model from the `Model` resource to Cloud Storage.
+- Download the model locally.
+- Make a local prediction.
+
+```
+
+
+[AutoML training image object detection model for online prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_object_detection_online_prediction.ipynb)
+
+```
+In this tutorial, you create an AutoML image object detection model and deploy for online prediction from a Python script using the Vertex AI SDK.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Deploy the `Model` resource to a serving `Endpoint` resource.
+- Make a prediction.
+- Undeploy the `Model`.
+
+```
+
+   Learn more about [Object detection for image data](https://cloud.google.com/vertex-ai/docs/training-overview#object_detection_for_images).
 
 
 [AutoML Tabular Workflow pipelines](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb)
 
 ```
-Learn how to create two regression models using [Vertex AI Pipelines](https://cloud.
+Learn how to create two regression models using Vertex AI Pipelines downloaded from Google Cloud Pipeline Components .
 
 The steps performed are:
 
@@ -71,7 +140,58 @@ The steps performed are:
 
 ```
 
-   Learn more about [AutoML Tabular Workflows](https://cloud.google.com/vertex-ai/docs/tabular-data/tabular-workflows/e2e-automl).
+   Learn more about [Tabular Workflow for E2E AutoML](https://cloud.google.com/vertex-ai/docs/tabular-data/tabular-workflows/e2e-automl).
+
+
+[AutoML training text entity extraction model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_text_entity_extraction_batch_prediction.ipynb)
+
+```
+In this tutorial, you create an AutoML text entity extraction model from a Python script, and then do a batch prediction using the Vertex AI SDK.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Make a batch prediction.
+
+```
+
+   Learn more about [Entity extraction for text data](https://cloud.google.com/vertex-ai/docs/training-overview#entity_extraction_for_text).
+
+
+[AutoML training text sentiment analysis model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_text_sentiment_analysis_batch_prediction.ipynb)
+
+```
+In this tutorial, you create an AutoML text sentiment analysis model from a Python script, and then do a batch prediction using the Vertex SDK.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Make a batch prediction.
+
+```
+
+
+[Get started with AutoML Training](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/get_started_automl_training.ipynb)
+
+```
+Learn how to use `AutoML` for training with `Vertex AI`.
+
+The steps performed include:
+
+- Train an image model
+- Export the image model as an edge model
+- Train a tabular model
+- Export the tabular model as a cloud model
+- Train a text model
+- Train a video model
+
+```
+
+   Learn more about [AutoML training](https://cloud.google.com/vertex-ai/docs/training-overview).
 
 
 [AutoML training hierarchical forecasting for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_forecasting_hierarchical_batch.ipynb)
@@ -84,13 +204,11 @@ The steps performed include:
 - Create a Vertex AI `TimeSeriesDataset` resource.
 - Train the model.
 - View the model evaluation.
-- Deploy the `Model` resource to a serving `Endpoint` resource.
-- Make a prediction.
-- Undeploy the `Model`.
+- Make a batch prediction.
 
 ```
 
-   Learn more about [AutoML Forecasting](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/overview).
+   Learn more about [Hierarchical forecasting for tabular data](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/hierarchical).
 
 
 [AutoML training image object detection model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb)
@@ -107,7 +225,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Image](https://cloud.google.com/vertex-ai/docs/image-data/object-detection/train-model).
+   Learn more about [Object detection for image data](https://cloud.google.com/vertex-ai/docs/training-overview#object_detection_for_images).
 
 
 [AutoML tabular forecasting model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb)
@@ -124,7 +242,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Forecasting](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/tutorials-samples).
+   Learn more about [Forecasting for tabular data](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/overview).
 
 
 [AutoML training tabular regression model for batch prediction using BigQuery](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb)
@@ -143,7 +261,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Tabular](https://cloud.google.com/vertex-ai/docs/training-overview#tabular_data).
+   Learn more about [Regression for tabular data](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/overview).
 
 
 [AutoML training tabular regression model for online prediction using BigQuery](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb)
@@ -162,7 +280,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Tabular](https://cloud.google.com/vertex-ai/docs/training-overview#tabular_data).
+   Learn more about [Regression for tabular data](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/overview).
 
 
 [AutoML training text entity extraction model for online prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_text_entity_extraction_online.ipynb)
@@ -181,7 +299,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Text](https://cloud.google.com/vertex-ai/docs/text-data/entity-extraction/train-model).
+   Learn more about [Entity extraction for text data](https://cloud.google.com/vertex-ai/docs/training-overview#entity_extraction_for_text).
 
 
 [Training an AutoML text sentiment analysis model for online predictions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_text_sentiment_analysis_online.ipynb)
@@ -201,7 +319,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Text](https://cloud.google.com/vertex-ai/docs/text-data/sentiment-analysis/train-model).
+   Learn more about [Sentiment analysis for text data](https://cloud.google.com/vertex-ai/docs/training-overview#sentiment_analysis_for_text).
 
 
 [AutoML training video action recognition model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb)
@@ -218,7 +336,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Video](https://cloud.google.com/vertex-ai/docs/video-data/action-recognition/train-model).
+   Learn more about [Action recognition for video data](https://cloud.google.com/vertex-ai/docs/training-overview#action_recognition_for_videos).
 
 
 [AutoML training video classification model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_classification_batch.ipynb)
@@ -235,7 +353,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Video](https://cloud.google.com/vertex-ai/docs/video-data/classification/train-model).
+   Learn more about [Classification for video data](https://cloud.google.com/vertex-ai/docs/training-overview#classification_for_videos).
 
 
 [AutoML training video object tracking model for batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_object_tracking_batch.ipynb)
@@ -252,5 +370,5 @@ The steps performed include:
 
 ```
 
-   Learn more about [AutoML Video](https://cloud.google.com/vertex-ai/docs/video-data/object-tracking/train-model).
+   Learn more about [Object tracking for video data](https://cloud.google.com/vertex-ai/docs/training-overview#object_tracking_for_videos).
 

notebooks/official/automl/automl-tabular-classification.ipynb

@@ -142,284 +142,171 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "# Install the packagesimport os\n",
-        "! pip3 install {USER_FLAG} -q --upgrade google-cloud-aiplatform \\\n",
-        "                                        google-cloud-storage"
+        "# Install the packages\n",
+        "! pip3 install --quiet --upgrade google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "d3a26cb9b19d"
+        "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "EzrelQZ22IZj"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "0e3cab0cc491"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
-        "## Before you begin"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "BF1j6f9HApxa"
-      },
-      "source": [
-        "### Set up your Google Cloud project\n",
+        "## Before you begin\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
-        "\n",
-        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "source": [
         "### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "oM1iC_MfAts1"
+        "id": "set_project_id"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"\"\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
         "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "qJYoRfYng0XZ"
+        "id": "region"
       },
       "source": [
-        "Otherwise, set your project ID here."
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "riG_qUokg0XZ"
+        "id": "region"
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "06571eb4063b"
-      },
-      "source": [
-        "### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "697568e92bd6"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dr--iN2kAylZ"
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "sBCra4QMA2wR"
-      },
-      "source": [
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "535223fa4b84"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
-        "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "zgPO1eR3CYjk"
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "This notebook demonstrates how to use Vertex AI SDK for Python to create an AutoML model based on a tabular dataset. You will need to provide a Cloud Storage bucket where the dataset will be stored.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all of your \n",
-        "Cloud Storage buckets.\n",
-        "\n",
-        "You may also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook. Make sure to [choose a region where Vertex AI services are\n",
-        "available](https://cloud.google.com/vertex-ai/docs/general/locations). You may\n",
-        "not use a Multi-Regional Storage bucket for training with Vertex AI."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "MzGDU7TWdts_"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cf221059d072"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "-EcIXiGsCePi"
+        "id": "create_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -429,31 +316,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "NIq7R4HZCfIc"
+        "id": "create_bucket"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ucvCsknMCims"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "vhOb7YnwClBb"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -474,9 +341,9 @@
       "outputs": [],
       "source": [
         "IMPORT_FILE = \"petfinder-tabular-classification.csv\"\n",
-        "! gsutil cp gs://cloud-samples-data/ai-platform-unified/datasets/tabular/{IMPORT_FILE} {BUCKET_NAME}/data/\n",
+        "! gsutil cp gs://cloud-samples-data/ai-platform-unified/datasets/tabular/{IMPORT_FILE} {BUCKET_URI}/data/\n",
         "\n",
-        "gcs_source = f\"{BUCKET_NAME}/data/{IMPORT_FILE}\""
+        "gcs_source = f\"{BUCKET_URI}/data/{IMPORT_FILE}\""
       ]
     },
     {
@@ -485,9 +352,9 @@
         "id": "Y9Uo3tifg1kx"
       },
       "source": [
-        "### Import Vertex SDK for Python\n",
+        "### Import Vertex AI SDK for Python\n",
         "\n",
-        "Import the Vertex SDK into your Python environment and initialize it."
+        "Import the Vertex AI SDK into your Python environment and initialize it."
       ]
     },
     {
@@ -549,7 +416,7 @@
         "id": "ba5011d50ac7"
       },
       "source": [
-        "### Launch a Training Job to Create a Model\n",
+        "### Launch a training job to create a Model\n",
         "\n",
         "Once we have defined your training script, we will create a model. The `run` function creates a training pipeline that trains and creates a `Model` object. After the training pipeline completes, the `run` function returns the `Model` object."
       ]
@@ -726,10 +593,6 @@
       },
       "outputs": [],
       "source": [
-        "delete_training_job = True\n",
-        "delete_model = True\n",
-        "delete_endpoint = True\n",
-        "\n",
         "# Warning: Setting this to true will delete everything in your bucket\n",
         "delete_bucket = False\n",
         "\n",
@@ -742,8 +605,8 @@
         "# Delete the endpoint\n",
         "endpoint.delete()\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil -m rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb

@@ -124,38 +124,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements. You need the following:\n",
-        "\n",
-        "- The Cloud Storage SDK\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
-        "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
-        "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
-        "\n",
-        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
-        "\n",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
-        "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -175,21 +143,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
-        "\n",
-        "! (pip3 install --upgrade $USER_FLAG \\\n",
+        "! (pip3 install --upgrade --quiet \\\n",
         "    google-cloud-bigquery[pandas]==2.34.4 \\\n",
         "    google-cloud-aiplatform==1.16.1 \\\n",
         "    google-cloud-pipeline-components==1.0.23)"
@@ -201,29 +155,22 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages.\n",
-        "\n",
-        "**Note: You may get a message saying \"Your session crashed for an unknown reason.\", this is expected. Once this cell has finished running, continue on. You do not need to re-run any of the cells above.**"
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "PMiYln_IQEH5"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -234,39 +181,12 @@
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
-        "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "6. (optional) You may also specify a service account to use to run Vertex AI Pipelines in the project.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "JDzPOakHF1d2"
-      },
-      "source": [
         "### Set your project ID\n",
         "\n",
-        "Set your project ID below. If you know know your project ID, leave the field blank and the following cells may be able to find it. Optionally, you may also set a service account in the cell below."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -277,33 +197,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -313,18 +210,8 @@
       },
       "source": [
         "#### Region\n",
-        "All BigQuery operations (`DATA_REGION`) are set to run in the `US` multi-region. This is required by the ARIMA pipeline because the data you use is stored in this region. All destination tables will also be stored in this region.\n",
         "\n",
-        "You may change the `REGION` variable, which is used for Vertex AI Forecasting operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -335,42 +222,8 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "DATA_REGION = \"US\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "84Vdv7R-QEH6"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "REGION = \"us-central1\"\n",
+        "DATA_REGION = \"US\""
       ]
     },
     {
@@ -381,56 +234,54 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "- In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "- **Click Create service account**.\n",
-        "\n",
-        "- In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "- In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "- Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "- Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "ssKjl9KrQEH6"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -441,11 +292,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -456,21 +303,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4FxNxXwW3inJ"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -493,26 +326,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "9axiWxVBQEH7"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -603,7 +416,9 @@
       "outputs": [],
       "source": [
         "import json\n",
+        "import os\n",
         "import urllib\n",
+        "import uuid\n",
         "\n",
         "import pandas as pd\n",
         "from google.cloud import aiplatform, bigquery\n",
@@ -661,8 +476,8 @@
       },
       "outputs": [],
       "source": [
-        "arima_dataset_name = f\"forecasting_demo_arima_{UUID}\"\n",
-        "vertex_dataset_name = f\"forecasting_demo_vertex_{UUID}\"\n",
+        "arima_dataset_name = \"forecasting_demo_arima\"\n",
+        "vertex_dataset_name = \"forecasting_demo_vertex\"\n",
         "\n",
         "arima_dataset_path = \".\".join([PROJECT_ID, arima_dataset_name])\n",
         "vertex_dataset_path = \".\".join([PROJECT_ID, vertex_dataset_name])\n",
@@ -1007,7 +822,7 @@
       "outputs": [],
       "source": [
         "# The display name should be unique even if this cell is rerun.\n",
-        "DISPLAY_NAME = f\"forecasting-demo-train-{generate_uuid()}\"\n",
+        "DISPLAY_NAME = f\"forecasting-demo-train-{str(uuid.uuid1())}\"\n",
         "\n",
         "job = aiplatform.PipelineJob(\n",
         "    job_id=DISPLAY_NAME,\n",
@@ -1141,7 +956,7 @@
       "outputs": [],
       "source": [
         "# The display name should be unique even if this cell is rerun.\n",
-        "DISPLAY_NAME = f\"forecasting-demo-predict-{generate_uuid()}\"\n",
+        "DISPLAY_NAME = \"forecasting-demo-predict\"\n",
         "\n",
         "job = aiplatform.PipelineJob(\n",
         "    job_id=DISPLAY_NAME,\n",
@@ -1327,7 +1142,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TimeSeriesDataset.create(\n",
-        "    display_name=\"forecasting_demo_train\" + \"_\" + UUID,\n",
+        "    display_name=\"forecasting_demo_train\",\n",
         "    bq_source=[TRAINING_DATASET_BQ_PATH],\n",
         ")\n",
         "print(dataset.resource_name)"
@@ -1394,7 +1209,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DISPLAY_NAME = f\"forecasting-demo-model_{UUID}\"\n",
+        "MODEL_DISPLAY_NAME = \"forecasting-demo-model\"\n",
         "\n",
         "training_job = aiplatform.AutoMLForecastingTrainingJob(\n",
         "    display_name=MODEL_DISPLAY_NAME,\n",
@@ -1568,7 +1383,7 @@
       "outputs": [],
       "source": [
         "batch_prediction_job = model.batch_predict(\n",
-        "    job_display_name=f\"forecasting_demo_predictions_{UUID}\",\n",
+        "    job_display_name=\"forecasting_demo_predictions\",\n",
         "    bigquery_source=PREDICTION_DATASET_BQ_PATH,\n",
         "    instances_format=\"bigquery\",\n",
         "    bigquery_destination_prefix=f\"bq://{vertex_dataset_path}\",\n",

notebooks/official/automl/automl_image_classification_batch_prediction.ipynb

@@ -0,0 +1,882 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2021 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title"
+      },
+      "source": [
+        "# AutoML training image classification model for batch prediction\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_classification_batch_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_classification_batch_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/automl_image_classification_online_prediction.ipynb\">\n",
+        "       <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create image classification models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model.\n",
+        "\n",
+        "Learn more about [Get predictions from an image classification model](https://cloud.google.com/vertex-ai/docs/image-data/classification/get-predictions)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,batch_prediction"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML image classification model from a Python script, and then do a batch prediction using the Vertex SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- View the model evaluation.\n",
+        "- Make a batch prediction.\n",
+        "\n",
+        "There is one key difference between using batch prediction and using online prediction:\n",
+        "\n",
+        "* Prediction Service: Does an on-demand prediction for the entire set of instances (i.e., one or more data items) and returns the results in real-time.\n",
+        "\n",
+        "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:flowers,icn"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower an image is from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the latest version of Vertex AI SDK for Python."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform\n",
+        "\n",
+        "if os.environ[\"IS_TESTING\"]:\n",
+        "    ! pip3 install --upgrade --quiet tensorflow"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1138a125ea"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "## Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML image classification model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,csv"
+      },
+      "source": [
+        "#### Location of Cloud Storage training data.\n",
+        "\n",
+        "Now set the variable `IMPORT_FILE` to the location of the CSV index file in Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:flowers,csv,icn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = (\n",
+        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "source": [
+        "#### Quick peek at your data\n",
+        "\n",
+        "This tutorial uses a version of the Flowers dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "\n",
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "outputs": [],
+      "source": [
+        "if \"IMPORT_FILES\" in globals():\n",
+        "    FILE = IMPORT_FILES[0]\n",
+        "else:\n",
+        "    FILE = IMPORT_FILE\n",
+        "\n",
+        "count = ! gsutil cat $FILE | wc -l\n",
+        "print(\"Number of Examples\", int(count[0]))\n",
+        "\n",
+        "print(\"First 10 rows\")\n",
+        "! gsutil cat $FILE | head"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:image,icn"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:image,icn"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.ImageDataset.create(\n",
+        "    display_name=\"Flowers\",\n",
+        "    gcs_source=[IMPORT_FILE],\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:image,icn"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "An AutoML training pipeline is created with the `AutoMLImageTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: An image classification model.\n",
+        "  - `object_detection`: An image object detection model.\n",
+        "- `multi_label`: If a classification task, whether single (`False`) or multi-labeled (`True`).\n",
+        "- `model_type`: The type of model for deployment.\n",
+        "  - `CLOUD`: Deployment on Google Cloud\n",
+        "  - `CLOUD_HIGH_ACCURACY_1`: Optimized for accuracy over latency for deployment on Google Cloud.\n",
+        "  - `CLOUD_LOW_LATENCY_`: Optimized for latency over accuracy for deployment on Google Cloud.\n",
+        "  - `MOBILE_TF_VERSATILE_1`: Deployment on an edge device.\n",
+        "  - `MOBILE_TF_HIGH_ACCURACY_1`:Optimized for accuracy over latency for deployment on an edge device.\n",
+        "  - `MOBILE_TF_LOW_LATENCY_1`: Optimized for latency over accuracy for deployment on an edge device.\n",
+        "- `base_model`: (optional) Transfer learning from existing `Model` resource -- supported for image classification only.\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:image,icn"
+      },
+      "outputs": [],
+      "source": [
+        "dag = aiplatform.AutoMLImageTrainingJob(\n",
+        "    display_name=\"flowers\",\n",
+        "    prediction_type=\"classification\",\n",
+        "    multi_label=False,\n",
+        "    model_type=\"CLOUD\",\n",
+        "    base_model=None,\n",
+        ")\n",
+        "\n",
+        "print(dag)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 20 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "outputs": [],
+      "source": [
+        "model = dag.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"flowers\",\n",
+        "    training_fraction_split=0.8,\n",
+        "    validation_fraction_split=0.1,\n",
+        "    test_fraction_split=0.1,\n",
+        "    budget_milli_node_hours=8000,\n",
+        "    disable_early_stopping=False,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "\n",
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Send a batch prediction request\n",
+        "\n",
+        "Send a batch prediction to your deployed model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_items:batch_prediction"
+      },
+      "source": [
+        "### Get test item(s)\n",
+        "\n",
+        "Now do a batch prediction to your Vertex model. You will use arbitrary examples out of the dataset as a test items. Don't be concerned that the examples were likely used in training the model -- we just want to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_test_items:automl,icn,csv"
+      },
+      "outputs": [],
+      "source": [
+        "test_items = !gsutil cat $IMPORT_FILE | head -n2\n",
+        "if len(str(test_items[0]).split(\",\")) == 3:\n",
+        "    _, test_item_1, test_label_1 = str(test_items[0]).split(\",\")\n",
+        "    _, test_item_2, test_label_2 = str(test_items[1]).split(\",\")\n",
+        "else:\n",
+        "    test_item_1, test_label_1 = str(test_items[0]).split(\",\")\n",
+        "    test_item_2, test_label_2 = str(test_items[1]).split(\",\")\n",
+        "\n",
+        "print(test_item_1, test_label_1)\n",
+        "print(test_item_2, test_label_2)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "copy_test_items:batch_prediction"
+      },
+      "source": [
+        "### Copy test item(s)\n",
+        "\n",
+        "For the batch prediction, copy the test items over to your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copy_test_items:batch_prediction"
+      },
+      "outputs": [],
+      "source": [
+        "file_1 = test_item_1.split(\"/\")[-1]\n",
+        "file_2 = test_item_2.split(\"/\")[-1]\n",
+        "\n",
+        "! gsutil cp $test_item_1 $BUCKET_URI/$file_1\n",
+        "! gsutil cp $test_item_2 $BUCKET_URI/$file_2\n",
+        "\n",
+        "test_item_1 = BUCKET_URI + \"/\" + file_1\n",
+        "test_item_2 = BUCKET_URI + \"/\" + file_2"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_batch_file:automl,image"
+      },
+      "source": [
+        "### Make the batch input file\n",
+        "\n",
+        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can be either CSV or JSONL. You will use JSONL in this tutorial. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains the key/value pairs:\n",
+        "\n",
+        "- `content`: The Cloud Storage path to the image.\n",
+        "- `mime_type`: The content type. In our example, it is a `jpeg` file.\n",
+        "\n",
+        "For example:\n",
+        "\n",
+        "                        {'content': '[your-bucket]/file1.jpg', 'mime_type': 'jpeg'}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "make_batch_file:automl,image"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
+        "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
+        "    data = {\"content\": test_item_1, \"mime_type\": \"image/jpeg\"}\n",
+        "    f.write(json.dumps(data) + \"\\n\")\n",
+        "    data = {\"content\": test_item_2, \"mime_type\": \"image/jpeg\"}\n",
+        "    f.write(json.dumps(data) + \"\\n\")\n",
+        "\n",
+        "print(gcs_input_uri)\n",
+        "! gsutil cat $gcs_input_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request:mbsdk"
+      },
+      "source": [
+        "### Make the batch prediction request\n",
+        "\n",
+        "Now that your Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
+        "\n",
+        "- `job_display_name`: The human readable name for the batch prediction job.\n",
+        "- `gcs_source`: A list of one or more batch request input files.\n",
+        "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
+        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job = model.batch_predict(\n",
+        "    job_display_name=\"flowers\",\n",
+        "    gcs_source=gcs_input_uri,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    sync=False,\n",
+        ")\n",
+        "\n",
+        "print(batch_predict_job)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "source": [
+        "### Wait for completion of batch prediction job\n",
+        "\n",
+        "Next, wait for the batch job to complete. Alternatively, one can set the parameter `sync` to `True` in the `batch_predict()` method to block until the batch prediction job is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job.wait()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,icn"
+      },
+      "source": [
+        "### Get the predictions\n",
+        "\n",
+        "Next, get the results from the completed batch prediction job.\n",
+        "\n",
+        "The results are written to the Cloud Storage output bucket you specified in the batch prediction request. You call the method iter_outputs() to get a list of each Cloud Storage file generated with the results. Each file contains one or more prediction requests in a JSON format:\n",
+        "\n",
+        "- `content`: The prediction request.\n",
+        "- `prediction`: The prediction response.\n",
+        " - `ids`: The internal assigned unique identifiers for each prediction request.\n",
+        " - `displayNames`: The class names for each class label.\n",
+        " - `confidences`: The predicted confidence, between 0 and 1, per class label."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,icn"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
+        "\n",
+        "prediction_results = list()\n",
+        "for blob in bp_iter_outputs:\n",
+        "    if blob.name.split(\"/\")[-1].startswith(\"prediction\"):\n",
+        "        prediction_results.append(blob.name)\n",
+        "\n",
+        "tags = list()\n",
+        "for prediction_result in prediction_results:\n",
+        "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{prediction_result}\"\n",
+        "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
+        "        for line in gfile.readlines():\n",
+        "            line = json.loads(line)\n",
+        "            print(line)\n",
+        "            break"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "delete_bucket = False\n",
+        "\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
+        "\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete the AutoML trainig job\n",
+        "dag.delete()\n",
+        "\n",
+        "# Delete the batch prediction job\n",
+        "batch_predict_job.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "automl_image_classification_batch_prediction.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/automl/automl_image_classification_online_online_prediction.ipynb

@@ -0,0 +1,799 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2020 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title"
+      },
+      "source": [
+        "# AutoML training image classification model for online prediction\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_classification_online_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_classification_online_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl//automl_image_classification_online_prediction.ipynb\">\n",
+        "       <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create image classification models and do online prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model.\n",
+        "\n",
+        "Learn more about [Get predictions from an image classification model](https://cloud.google.com/vertex-ai/docs/image-data/classification/get-predictions)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,online_prediction"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML image classification model and deploy for online prediction from a Python script using the Vertex SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- View the model evaluation.\n",
+        "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
+        "- Make a prediction.\n",
+        "- Undeploy the `Model`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:flowers,icn"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower an image is from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the latest version of Vertex AI SDK for Python."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 tensorflow"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1138a125ea"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "09kHSsKmv5mT"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "## Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML image classification model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,csv"
+      },
+      "source": [
+        "#### Location of Cloud Storage training data.\n",
+        "\n",
+        "Now set the variable `IMPORT_FILE` to the location of the CSV index file in Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:flowers,csv,icn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = (\n",
+        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "source": [
+        "#### Quick peek at your data\n",
+        "\n",
+        "This tutorial uses a version of the Flowers dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "\n",
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "outputs": [],
+      "source": [
+        "if \"IMPORT_FILES\" in globals():\n",
+        "    FILE = IMPORT_FILES[0]\n",
+        "else:\n",
+        "    FILE = IMPORT_FILE\n",
+        "\n",
+        "count = ! gsutil cat $FILE | wc -l\n",
+        "print(\"Number of Examples\", int(count[0]))\n",
+        "\n",
+        "print(\"First 10 rows\")\n",
+        "! gsutil cat $FILE | head"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:image,icn"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:image,icn"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.ImageDataset.create(\n",
+        "    display_name=\"Flowers\",\n",
+        "    gcs_source=[IMPORT_FILE],\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:image,icn"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "An AutoML training pipeline is created with the `AutoMLImageTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: An image classification model.\n",
+        "  - `object_detection`: An image object detection model.\n",
+        "- `multi_label`: If a classification task, whether single (`False`) or multi-labeled (`True`).\n",
+        "- `model_type`: The type of model for deployment.\n",
+        "  - `CLOUD`: Deployment on Google Cloud\n",
+        "  - `CLOUD_HIGH_ACCURACY_1`: Optimized for accuracy over latency for deployment on Google Cloud.\n",
+        "  - `CLOUD_LOW_LATENCY_`: Optimized for latency over accuracy for deployment on Google Cloud.\n",
+        "  - `MOBILE_TF_VERSATILE_1`: Deployment on an edge device.\n",
+        "  - `MOBILE_TF_HIGH_ACCURACY_1`:Optimized for accuracy over latency for deployment on an edge device.\n",
+        "  - `MOBILE_TF_LOW_LATENCY_1`: Optimized for latency over accuracy for deployment on an edge device.\n",
+        "- `base_model`: (optional) Transfer learning from existing `Model` resource -- supported for image classification only.\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:image,icn"
+      },
+      "outputs": [],
+      "source": [
+        "dag = aiplatform.AutoMLImageTrainingJob(\n",
+        "    display_name=\"flowers\",\n",
+        "    prediction_type=\"classification\",\n",
+        "    multi_label=False,\n",
+        "    model_type=\"CLOUD\",\n",
+        "    base_model=None,\n",
+        ")\n",
+        "\n",
+        "print(dag)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 20 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "outputs": [],
+      "source": [
+        "model = dag.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"flowers\",\n",
+        "    training_fraction_split=0.8,\n",
+        "    validation_fraction_split=0.1,\n",
+        "    test_fraction_split=0.1,\n",
+        "    budget_milli_node_hours=8000,\n",
+        "    disable_early_stopping=False,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "\n",
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "deploy_model:mbsdk,automatic"
+      },
+      "source": [
+        "## Deploy the model\n",
+        "\n",
+        "Next, deploy your model for online prediction. To deploy the model, you invoke the `deploy` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "deploy_model:mbsdk,automatic"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint = model.deploy()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Send an online prediction request\n",
+        "\n",
+        "Send an online prediction to your deployed model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_item"
+      },
+      "source": [
+        "### Get test item\n",
+        "\n",
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_test_item:automl,icn,csv"
+      },
+      "outputs": [],
+      "source": [
+        "test_item = !gsutil cat $IMPORT_FILE | head -n1\n",
+        "if len(str(test_item[0]).split(\",\")) == 3:\n",
+        "    _, test_item, test_label = str(test_item[0]).split(\",\")\n",
+        "else:\n",
+        "    test_item, test_label = str(test_item[0]).split(\",\")\n",
+        "\n",
+        "print(test_item, test_label)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "predict_request:mbsdk,icn"
+      },
+      "source": [
+        "### Make the prediction\n",
+        "\n",
+        "Now that your `Model` resource is deployed to an `Endpoint` resource, you can do online predictions by sending prediction requests to the Endpoint resource.\n",
+        "\n",
+        "#### Request\n",
+        "\n",
+        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 -- which makes the content safe from modification while transmitting binary data over the network.\n",
+        "\n",
+        "The format of each instance is:\n",
+        "\n",
+        "    { 'content': { 'b64': base64_encoded_bytes } }\n",
+        "\n",
+        "Since the `predict()` method can take multiple items (instances), send your single test item as a list of one test item.\n",
+        "\n",
+        "#### Response\n",
+        "\n",
+        "The response from the `predict()` call is a Python dictionary with the following entries:\n",
+        "\n",
+        "- `ids`: The internal assigned unique identifiers for each prediction request.\n",
+        "- `displayNames`: The class names for each class label.\n",
+        "- `confidences`: The predicted confidence, between 0 and 1, per class label.\n",
+        "- `deployed_model_id`: The Vertex AI identifier for the deployed Model resource which did the predictions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "predict_request:mbsdk,icn"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
+        "    content = f.read()\n",
+        "\n",
+        "# The format of each instance should conform to the deployed model's prediction input schema.\n",
+        "instances = [{\"content\": base64.b64encode(content).decode(\"utf-8\")}]\n",
+        "\n",
+        "prediction = endpoint.predict(instances=instances)\n",
+        "\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "undeploy_model:mbsdk"
+      },
+      "source": [
+        "## Undeploy the model\n",
+        "\n",
+        "When you are done doing predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "undeploy_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.undeploy_all()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "delete_bucket = False\n",
+        "\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
+        "\n",
+        "try:\n",
+        "    endpoint.undeploy_all()\n",
+        "    endpoint.delete()\n",
+        "except Exception as e:\n",
+        "    print(e)\n",
+        "\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete the AutoML trainig job\n",
+        "dag.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "automl_image_classification_online_online_prediction.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/automl/automl_image_object_detection_export_edge.ipynb

@@ -0,0 +1,831 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2021 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title"
+      },
+      "source": [
+        "# AutoML training image object detection model for export to edge\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_object_detection_export_edge.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_object_detection_export_edge.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl//automl_image_object_detection_export_edge.ipynb\">\n",
+        "       <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl,export_edge"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create image object detection models to export as an Edge model using an AutoML model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,export_edge"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML image object detection model from a Python script using the Vertex SDK, and then export the model as an Edge model in TFLite format. You can alternatively create models with AutoML using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- Vertex AI `Datasets`\n",
+        "- AutoML Image\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- Export the `Edge` model from the `Model` resource to Cloud Storage.\n",
+        "- Download the model locally.\n",
+        "- Make a local prediction."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:salads,iod"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the latest version of Vertex AI SDK for Python."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform\n",
+        "\n",
+        "if os.environ[\"IS_TESTING\"]:\n",
+        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1138a125ea"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "## Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML image object detection model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,csv"
+      },
+      "source": [
+        "#### Location of Cloud Storage training data.\n",
+        "\n",
+        "Now set the variable `IMPORT_FILE` to the location of the CSV index file in Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:salads,csv,iod"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/vision/salads.csv\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "source": [
+        "#### Quick peek at your data\n",
+        "\n",
+        "This tutorial uses a version of the Salads dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "\n",
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "outputs": [],
+      "source": [
+        "if \"IMPORT_FILES\" in globals():\n",
+        "    FILE = IMPORT_FILES[0]\n",
+        "else:\n",
+        "    FILE = IMPORT_FILE\n",
+        "\n",
+        "count = ! gsutil cat $FILE | wc -l\n",
+        "print(\"Number of Examples\", int(count[0]))\n",
+        "\n",
+        "print(\"First 10 rows\")\n",
+        "! gsutil cat $FILE | head"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:image,iod"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:image,iod"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.ImageDataset.create(\n",
+        "    display_name=\"Salads\",\n",
+        "    gcs_source=[IMPORT_FILE],\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.bounding_box,\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:image,edge,iod"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "An AutoML training pipeline is created with the `AutoMLImageTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: An image classification model.\n",
+        "  - `object_detection`: An image object detection model.\n",
+        "- `multi_label`: If a classification task, whether single (`False`) or multi-labeled (`True`).\n",
+        "- `model_type`: The type of model for deployment.\n",
+        "  - `CLOUD`: Deployment on Google Cloud\n",
+        "  - `CLOUD_HIGH_ACCURACY_1`: Optimized for accuracy over latency for deployment on Google Cloud.\n",
+        "  - `CLOUD_LOW_LATENCY_`: Optimized for latency over accuracy for deployment on Google Cloud.\n",
+        "  - `MOBILE_TF_VERSATILE_1`: Deployment on an edge device.\n",
+        "  - `MOBILE_TF_HIGH_ACCURACY_1`:Optimized for accuracy over latency for deployment on an edge device.\n",
+        "  - `MOBILE_TF_LOW_LATENCY_1`: Optimized for latency over accuracy for deployment on an edge device.\n",
+        "- `base_model`: (optional) Transfer learning from existing `Model` resource -- supported for image classification only.\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:image,edge,iod"
+      },
+      "outputs": [],
+      "source": [
+        "dag = aiplatform.AutoMLImageTrainingJob(\n",
+        "    display_name=\"salads\",\n",
+        "    prediction_type=\"object_detection\",\n",
+        "    multi_label=False,\n",
+        "    model_type=\"MOBILE_TF_LOW_LATENCY_1\",\n",
+        "    base_model=None,\n",
+        ")\n",
+        "\n",
+        "print(dag)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 60 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "outputs": [],
+      "source": [
+        "model = dag.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"salads\",\n",
+        "    training_fraction_split=0.8,\n",
+        "    validation_fraction_split=0.1,\n",
+        "    test_fraction_split=0.1,\n",
+        "    budget_milli_node_hours=20000,\n",
+        "    disable_early_stopping=False,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "\n",
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "export_model:mbsdk,image"
+      },
+      "source": [
+        "## Export as Edge model\n",
+        "\n",
+        "You can export an AutoML image object detection model as a `Edge` model which you can then custom deploy to an edge device or download locally. Use the method `export_model()` to export the model to Cloud Storage, which takes the following parameters:\n",
+        "\n",
+        "- `artifact_destination`: The Cloud Storage location to store the SavedFormat model artifacts to.\n",
+        "- `export_format_id`: The format to save the model format as. For AutoML image object detection there is just one option:\n",
+        "   - `tf-saved-model`: TensorFlow SavedFormat for deployment to a container.\n",
+        "   - `tflite`: TensorFlow Lite for deployment to an edge or mobile device.\n",
+        "   - `edgetpu-tflite`: TensorFlow Lite for TPU\n",
+        "   - `tf-js`: TensorFlow for web client\n",
+        "   - `coral-ml`: for Coral devices\n",
+        "\n",
+        "- `sync`: Whether to perform operational sychronously or asynchronously."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "export_model:mbsdk,image"
+      },
+      "outputs": [],
+      "source": [
+        "response = model.export_model(\n",
+        "    artifact_destination=BUCKET_URI, export_format_id=\"tflite\", sync=True\n",
+        ")\n",
+        "\n",
+        "model_package = response[\"artifactOutputUri\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "download_model_artifacts:tflite"
+      },
+      "source": [
+        "#### Download the TFLite model artifacts\n",
+        "\n",
+        "Now that you have an exported TFLite version of your model, you can test the exported model locally, but first downloading it from Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "download_model_artifacts:tflite"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls $model_package\n",
+        "# Download the model artifacts\n",
+        "! gsutil cp -r $model_package tflite\n",
+        "\n",
+        "tflite_path = \"tflite/model.tflite\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "instantiate_tflite_interpreter"
+      },
+      "source": [
+        "#### Instantiate a TFLite interpreter\n",
+        "\n",
+        "The TFLite version of the model is not a TensorFlow SavedModel format. You cannot directly use methods like predict(). Instead, one uses the TFLite interpreter. You must first setup the interpreter for the TFLite model as follows:\n",
+        "\n",
+        "- Instantiate an TFLite interpreter for the TFLite model.\n",
+        "- Instruct the interpreter to allocate input and output tensors for the model.\n",
+        "- Get detail information about the models input and output tensors that will need to be known for prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "instantiate_tflite_interpreter"
+      },
+      "outputs": [],
+      "source": [
+        "import tensorflow as tf\n",
+        "\n",
+        "interpreter = tf.lite.Interpreter(model_path=tflite_path)\n",
+        "interpreter.allocate_tensors()\n",
+        "\n",
+        "input_details = interpreter.get_input_details()\n",
+        "output_details = interpreter.get_output_details()\n",
+        "input_shape = input_details[0][\"shape\"]\n",
+        "\n",
+        "print(\"input tensor shape\", input_shape)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_item"
+      },
+      "source": [
+        "### Get test item\n",
+        "\n",
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_test_item:image,224x224"
+      },
+      "outputs": [],
+      "source": [
+        "test_items = ! gsutil cat $IMPORT_FILE | head -n1\n",
+        "test_item = test_items[0].split(\",\")[0]\n",
+        "\n",
+        "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
+        "    content = f.read()\n",
+        "test_image = tf.io.decode_jpeg(content)\n",
+        "print(\"test image shape\", test_image.shape)\n",
+        "\n",
+        "test_image = tf.image.resize(test_image, (192, 192))\n",
+        "print(\"test image shape\", test_image.shape, test_image.dtype)\n",
+        "\n",
+        "test_image = tf.cast(test_image, dtype=tf.uint8).numpy()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "invoke_tflite_interpreter"
+      },
+      "source": [
+        "#### Make a prediction with TFLite model\n",
+        "\n",
+        "Finally, you do a prediction using your TFLite model, as follows:\n",
+        "\n",
+        "- Convert the test image into a batch of a single image (`np.expand_dims`)\n",
+        "- Set the input tensor for the interpreter to your batch of a single image (`data`).\n",
+        "- Invoke the interpreter.\n",
+        "- Retrieve the softmax probabilities for the prediction (`get_tensor`).\n",
+        "- Determine which label had the highest probability (`np.argmax`)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "invoke_tflite_interpreter"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "data = np.expand_dims(test_image, axis=0)\n",
+        "\n",
+        "interpreter.set_tensor(input_details[0][\"index\"], data)\n",
+        "\n",
+        "interpreter.invoke()\n",
+        "\n",
+        "softmax = interpreter.get_tensor(output_details[0][\"index\"])\n",
+        "\n",
+        "label = np.argmax(softmax)\n",
+        "\n",
+        "print(label)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "delete_bucket = False\n",
+        "\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
+        "\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete the AutoML trainig job\n",
+        "dag.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "automl_image_object_detection_export_edge.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/automl/automl_image_object_detection_online_prediction.ipynb

@@ -0,0 +1,813 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2021 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title"
+      },
+      "source": [
+        "# AutoML training image object detection model for online prediction\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_object_detection_online_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_image_object_detection_online_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/automl_image_object_detection_online_prediction.ipynb\">\n",
+        "       <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create image object detection models and do online prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model.\n",
+        "\n",
+        "Learn more about [Object detection for image data](https://cloud.google.com/vertex-ai/docs/training-overview#object_detection_for_images)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,online_prediction"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML image object detection model and deploy for online prediction from a Python script using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- Vertex AI `Datasets`\n",
+        "- AutoML Image\n",
+        "- Vertex AI `Model Registry`\n",
+        "- Vertex AI `Predictions`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- View the model evaluation.\n",
+        "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
+        "- Make a prediction.\n",
+        "- Undeploy the `Model`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:salads,iod"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the latest version of Vertex AI SDK for Python."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 tensorflow\n",
+        "\n",
+        "if os.environ[\"IS_TESTING\"]:\n",
+        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1138a125ea"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "## Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML image object detection model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,csv"
+      },
+      "source": [
+        "#### Location of Cloud Storage training data.\n",
+        "\n",
+        "Now set the variable `IMPORT_FILE` to the location of the CSV index file in Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:salads,csv,iod"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/vision/salads.csv\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "source": [
+        "#### Quick peek at your data\n",
+        "\n",
+        "This tutorial uses a version of the Salads dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "\n",
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "outputs": [],
+      "source": [
+        "if \"IMPORT_FILES\" in globals():\n",
+        "    FILE = IMPORT_FILES[0]\n",
+        "else:\n",
+        "    FILE = IMPORT_FILE\n",
+        "\n",
+        "count = ! gsutil cat $FILE | wc -l\n",
+        "print(\"Number of Examples\", int(count[0]))\n",
+        "\n",
+        "print(\"First 10 rows\")\n",
+        "! gsutil cat $FILE | head"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:image,iod"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:image,iod"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.ImageDataset.create(\n",
+        "    display_name=\"Salads\",\n",
+        "    gcs_source=[IMPORT_FILE],\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.bounding_box,\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:image,iod"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "An AutoML training pipeline is created with the `AutoMLImageTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: An image classification model.\n",
+        "  - `object_detection`: An image object detection model.\n",
+        "- `multi_label`: If a classification task, whether single (`False`) or multi-labeled (`True`).\n",
+        "- `model_type`: The type of model for deployment.\n",
+        "  - `CLOUD`: Deployment on Google Cloud\n",
+        "  - `CLOUD_HIGH_ACCURACY_1`: Optimized for accuracy over latency for deployment on Google Cloud.\n",
+        "  - `CLOUD_LOW_LATENCY_`: Optimized for latency over accuracy for deployment on Google Cloud.\n",
+        "  - `MOBILE_TF_VERSATILE_1`: Deployment on an edge device.\n",
+        "  - `MOBILE_TF_HIGH_ACCURACY_1`:Optimized for accuracy over latency for deployment on an edge device.\n",
+        "  - `MOBILE_TF_LOW_LATENCY_1`: Optimized for latency over accuracy for deployment on an edge device.\n",
+        "- `base_model`: (optional) Transfer learning from existing `Model` resource -- supported for image classification only.\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:image,iod"
+      },
+      "outputs": [],
+      "source": [
+        "dag = aiplatform.AutoMLImageTrainingJob(\n",
+        "    display_name=\"salads\",\n",
+        "    prediction_type=\"object_detection\",\n",
+        "    multi_label=False,\n",
+        "    model_type=\"CLOUD\",\n",
+        "    base_model=None,\n",
+        ")\n",
+        "\n",
+        "print(dag)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 60 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:image"
+      },
+      "outputs": [],
+      "source": [
+        "model = dag.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"salads\",\n",
+        "    training_fraction_split=0.8,\n",
+        "    validation_fraction_split=0.1,\n",
+        "    test_fraction_split=0.1,\n",
+        "    budget_milli_node_hours=20000,\n",
+        "    disable_early_stopping=False,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "\n",
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "deploy_model:mbsdk,automatic"
+      },
+      "source": [
+        "## Deploy the model\n",
+        "\n",
+        "Next, deploy your model for online prediction. To deploy the model, you invoke the `deploy` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "deploy_model:mbsdk,automatic"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint = model.deploy()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Send an online prediction request\n",
+        "\n",
+        "Send an online prediction to your deployed model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_item"
+      },
+      "source": [
+        "### Get test item\n",
+        "\n",
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_test_item:automl,iod,csv"
+      },
+      "outputs": [],
+      "source": [
+        "test_items = !gsutil cat $IMPORT_FILE | head -n1\n",
+        "cols = str(test_items[0]).split(\",\")\n",
+        "if len(cols) == 11:\n",
+        "    test_item = str(cols[1])\n",
+        "    test_label = str(cols[2])\n",
+        "else:\n",
+        "    test_item = str(cols[0])\n",
+        "    test_label = str(cols[1])\n",
+        "\n",
+        "print(test_item, test_label)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "predict_request:mbsdk,iod"
+      },
+      "source": [
+        "### Make the prediction\n",
+        "\n",
+        "Now that your `Model` resource is deployed to an `Endpoint` resource, you can do online predictions by sending prediction requests to the Endpoint resource.\n",
+        "\n",
+        "#### Request\n",
+        "\n",
+        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 -- which makes the content safe from modification while transmitting binary data over the network.\n",
+        "\n",
+        "The format of each instance is:\n",
+        "\n",
+        "    { 'content': { 'b64': base64_encoded_bytes } }\n",
+        "\n",
+        "Since the `predict()` method can take multiple items (instances), send your single test item as a list of one test item.\n",
+        "\n",
+        "#### Response\n",
+        "\n",
+        "The response from the `predict()` call is a Python dictionary with the following entries:\n",
+        "\n",
+        "- `ids`: The internal assigned unique identifiers for each prediction request.\n",
+        "- `displayNames`: The class names for each class label.\n",
+        "- `confidences`: The predicted confidence, between 0 and 1, per class label.\n",
+        "- `bboxes`: The bounding box of each detected object.\n",
+        "- `deployed_model_id`: The Vertex AI identifier for the deployed Model resource which did the predictions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "predict_request:mbsdk,iod"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
+        "    content = f.read()\n",
+        "\n",
+        "# The format of each instance should conform to the deployed model's prediction input schema.\n",
+        "instances = [{\"content\": base64.b64encode(content).decode(\"utf-8\")}]\n",
+        "\n",
+        "prediction = endpoint.predict(instances=instances)\n",
+        "\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "undeploy_model:mbsdk"
+      },
+      "source": [
+        "## Undeploy the model\n",
+        "\n",
+        "When you are done doing predictions, you undeploy the model from the `Endpoint` resource. This deprovisions all compute resources and ends billing for the deployed model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "undeploy_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.undeploy_all()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "delete_bucket = False\n",
+        "\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
+        "\n",
+        "try:\n",
+        "    endpoint.undeploy_all()\n",
+        "    endpoint.delete()\n",
+        "except Exception as e:\n",
+        "    print(e)\n",
+        "\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete the AutoML trainig job\n",
+        "dag.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "automl_image_object_detection_online_prediction.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb

@@ -122,44 +122,12 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tuOonx6suOb7"
+        "id": "install_aip:mbsdk"
       },
       "source": [
-        "### Set up your local development environment\n",
+        "## Installation\n",
         "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements. You need the following:\n",
-        "\n",
-        "- The Cloud Storage SDK\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
-        "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
-        "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
-        "\n",
-        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
-        "\n",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
-        "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e85f0288a6df"
-      },
-      "source": [
-        "## Install additional packages\n",
-        "\n",
-        "Install the latest version of the Google Cloud Pipeline Components (GCPC) SDK."
+        "Install the latest version of Vertex AI SDK for Python."
       ]
     },
     {
@@ -170,38 +138,32 @@
       },
       "outputs": [],
       "source": [
-        "!pip install -U google-cloud-pipeline-components -q"
+        "!pip3 install --upgrade --quiet google-cloud-pipeline-components==1.0.25 \\\n",
+        "                                google-cloud-aiplatform"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "Bj5O0S5RTxzY"
+        "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages.\n",
-        "\n",
-        "\n",
-        "**Note: Once this cell has finished running, continue on. You do not need to re-run any of the cells above.**\n"
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "023DMKUaTypt"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -212,26 +174,26 @@
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
+        "### Set your project ID\n",
         "\n",
-        "This tutorial does not require a GPU runtime.\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
         "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Dataflow APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,dataflow.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -242,240 +204,200 @@
       "source": [
         "## Notes about service account and permission\n",
         "\n",
-        "**By default no configuration is required**, if you run into any permission related issue, please make sure the service accounts above have the required roles:\n",
-        "\n",
-        "|Service account email|Description|Roles|\n",
-        "|---|---|---|\n",
-        "|PROJECT_NUMBER-compute@developer.gserviceaccount.com|Compute Engine default service account|Dataflow Developer, Dataflow Worker, Storage Admin, BigQuery Data Editor, Vertex AI User, Service Account User|\n",
-        "|service-PROJECT_NUMBER@gcp-sa-aiplatform.iam.gserviceaccount.com|AI Platform Service Agent|Vertex AI Service Agent|\n",
-        "\n",
-        "\n",
-        "1. Goto https://console.cloud.google.com/iam-admin/iam.\n",
-        "2. Check the \"Include Google-provided role grants\" checkbox.\n",
-        "3. Find the above emails.\n",
-        "4. Grant the corresponding roles.\n",
-        "\n",
-        "### Using data source from a different project\n",
-        "- For the BQ data source, grant both service accounts the \"BigQuery Data Viewer\" role.\n",
-        "- For the CSV data source, grant both service accounts the \"Storage Object Viewer\" role.\n"
+        "**By default no configuration is required**, if you run into any permission related issue, please make sure the service accounts have the required roles listed in the [Service accounts for Tabular Workflow for End-to-End AutoML documentation](https://cloud.google.com/vertex-ai/docs/tabular-data/tabular-workflows/service-accounts#e2e-automl)."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "95cb7ffd6895"
+        "id": "region"
       },
       "source": [
-        "### Set your project ID\n",
+        "#### Region\n",
         "\n",
-        "Set your project ID below. If you know know your project ID, leave the field blank and the following cells may be able to find it. Optionally, you may also set a service account in the cell below."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cd85f5c794e5"
+        "id": "region"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "5a604eeffc32"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "30e64c0eda41"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "b12f508d97c6"
-      },
-      "source": [
-        "### Region\n",
-        "You may change the `REGION` variable, which is used for Vertex Forecasting operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8e8b7997de7a"
-      },
-      "outputs": [],
-      "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "eu0e2TRVxjHb"
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "- In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "- **Click Create service account**.\n",
-        "\n",
-        "- In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "- In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "- Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "- Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "_nJ1VqdTxosw"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account. Alternatively, you may edit this notebook to authenticate using\n",
-        "    # gcloud.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "OUfwWir9yPNV"
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "All training related files (TF model checkpoint, TensorBoard file, etc) will be saved to the GCS bucket. The pipeline will not clean up the files since some of them might be useful for you, **please make sure to clean up the files**. For easy cleanup, you can set [GCS bucket level TTL](https://cloud.google.com/storage/docs/lifecycle).\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization.\n"
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "5325f437b46a"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "GENERATE_BUCKET_URI = True  # @param {type:\"boolean\"}"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "a30ea8551126"
+        "id": "create_bucket"
       },
       "source": [
-        "Create the bucket if it doesn't already exist."
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "0217c63ed87f"
+        "id": "create_bucket"
       },
       "outputs": [],
       "source": [
-        "import uuid\n",
-        "\n",
-        "if GENERATE_BUCKET_URI:\n",
-        "    bucket_name = \"gs://test-{}\".format(uuid.uuid4())\n",
-        "    !gsutil mb -p {PROJECT_ID} -l {REGION} {bucket_name}\n",
-        "\n",
-        "    # set GCS bucket object TTL to 7 days\n",
-        "    !echo '{\"rule\":[{\"action\": {\"type\": \"Delete\"},\"condition\": {\"age\": 7}}]}' > gcs_lifecycle.tmp\n",
-        "    !gsutil lifecycle set gcs_lifecycle.tmp {bucket_name}\n",
-        "    !rm gcs_lifecycle.tmp\n",
-        "\n",
-        "    BUCKET_URI = bucket_name\n",
-        "    print(f\"changed BUCKET_URI to {BUCKET_URI} due to GENERATE_BUCKET_URI is True\")\n",
-        "\n",
-        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + uuid.uuid4()\n",
-        "\n",
-        "! gsutil ls -b $BUCKET_URI || gsutil mb -l $DATA_REGION $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "c4cf2cdebb50"
+        "id": "44accda192d5"
       },
       "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+        "#### Service Account\n",
+        "\n",
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "96ad3d416327"
+        "id": "e0c9c4f84849"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "SERVICE_ACCOUNT = \"[your-service-account]\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "604ae09ab6d3"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    else:  # IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d1ecb60964d5"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step. You only need to run this step once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a592f0a380c2"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -495,8 +417,10 @@
       },
       "outputs": [],
       "source": [
-        "# Import required modules\n",
         "import json\n",
+        "# Import required modules\n",
+        "import os\n",
+        "import uuid\n",
         "from typing import Any, Dict, List\n",
         "\n",
         "from google.cloud import aiplatform, storage\n",
@@ -510,9 +434,9 @@
         "id": "c0423f260423"
       },
       "source": [
-        "## Initialize Vertex SDK for Python\n",
+        "## Initialize Vertex AI SDK for Python\n",
         "\n",
-        "Initialize the Vertex SDK for Python for your project."
+        "Initialize the Vertex AI SDK for Python for your project."
       ]
     },
     {
@@ -836,6 +760,7 @@
         "\n",
         "job.run()\n",
         "\n",
+        "\n",
         "pipeline_task_details = job.gca_resource.job_detail.task_details\n",
         "\n",
         "if export_additional_model_without_custom_ops:\n",
@@ -877,6 +802,7 @@
         "stage_1_tuner_task = get_task_detail(\n",
         "    pipeline_task_details, \"automl-tabular-stage-1-tuner\"\n",
         ")\n",
+        "\n",
         "stage_1_tuning_result_artifact_uri = (\n",
         "    stage_1_tuner_task.outputs[\"tuning_result_output\"].artifacts[0].uri\n",
         ")"

notebooks/official/automl/automl_text_entity_extraction_batch_prediction.ipynb

@@ -0,0 +1,818 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2021 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title"
+      },
+      "source": [
+        "# AutoML training text entity extraction model for batch prediction\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_text_entity_extraction_batch_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_text_entity_extraction_batch_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/automl_text_entity_extraction_batch_prediction.ipynb\">\n",
+        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create text entity extraction models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model.\n",
+        "\n",
+        "Learn more about [Entity extraction for text data](https://cloud.google.com/vertex-ai/docs/training-overview#entity_extraction_for_text)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,batch_prediction"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML text entity extraction model from a Python script, and then do a batch prediction using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- View the model evaluation.\n",
+        "- Make a batch prediction.\n",
+        "\n",
+        "There is one key difference between using batch prediction and using online prediction:\n",
+        "\n",
+        "* Prediction Service: Does an on-demand prediction for the entire set of instances (i.e., one or more data items) and returns the results in real-time.\n",
+        "\n",
+        "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:biomedical,ten"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [NCBI Disease Research Abstracts dataset](https://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/DISEASE/) from [National Center for Biotechnology Information](https://www.ncbi.nlm.nih.gov/). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db52a0a61fca"
+      },
+      "source": [
+        "### Installation\n",
+        "\n",
+        "Install the following packages for executing this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b75757581291"
+      },
+      "outputs": [],
+      "source": [
+        "# install packages\n",
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                    jsonlines -q\n",
+        "! pip3 install --upgrade tensorflow -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e9255e3b156f"
+      },
+      "source": [
+        "### Colab Only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0c0b2427998a"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "435b8e413535"
+      },
+      "source": [
+        "### Before you begin\n",
+        "\n",
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "-  Run `gcloud config list`\n",
+        "-  Run `gcloud projects list`\n",
+        "-  See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "be175254a715"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# set the project id\n",
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2e6b8b324ce1"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. \n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c43a8673066"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "\n",
+        "**1. Vertex AI Workbench** \n",
+        "- Do nothing as you are already authenticated.\n",
+        "\n",
+        "**2. Local JupyterLab Instance,** uncomment and run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fbc9cd30cc4b"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd0da2c26879"
+      },
+      "source": [
+        "**3. Colab,** uncomment and run:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a336a05c6149"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0461097edfa5"
+      },
+      "source": [
+        "**4. Service Account or other**\n",
+        "- See all the authentication options here: [Google Cloud Platform Jupyter Notebook Authentication Guide](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_authentication_guide.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e5755d1a554f"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d2de92accb67"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b72bfdf29dae"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "## Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML text entity extraction model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,jsonl"
+      },
+      "source": [
+        "#### Location of Cloud Storage training data.\n",
+        "\n",
+        "Now set the variable `IMPORT_FILE` to the location of the JSONL index file in Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:biomedical,jsonl,ten"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/language/ucaip_ten_dataset.jsonl\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "quick_peek:jsonl"
+      },
+      "source": [
+        "#### Quick peek at your data\n",
+        "\n",
+        "This tutorial uses a version of the NCBI Biomedical dataset that is stored in a public Cloud Storage bucket, using a JSONL index file.\n",
+        "\n",
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of objects in a JSONL index file  (`wc -l`) and then peek at the first few rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "quick_peek:jsonl"
+      },
+      "outputs": [],
+      "source": [
+        "if \"IMPORT_FILES\" in globals():\n",
+        "    FILE = IMPORT_FILES[0]\n",
+        "else:\n",
+        "    FILE = IMPORT_FILE\n",
+        "\n",
+        "count = ! gsutil cat $FILE | wc -l\n",
+        "print(\"Number of Examples\", int(count[0]))\n",
+        "\n",
+        "print(\"First 10 rows\")\n",
+        "! gsutil cat $FILE | head"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:text,ten"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:text,ten"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.TextDataset.create(\n",
+        "    display_name=\"NCBI Biomedical\",\n",
+        "    gcs_source=[IMPORT_FILE],\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.extraction,\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:text,ten"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "An AutoML training pipeline is created with the `AutoMLTextTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: A text classification model.\n",
+        "  - `sentiment`: A text sentiment analysis model.\n",
+        "  - `extraction`: A text entity extraction model.\n",
+        "- `multi_label`: If a classification task, whether single (False) or multi-labeled (True).\n",
+        "- `sentiment_max`: If a sentiment analysis task, the maximum sentiment value.\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:text,ten"
+      },
+      "outputs": [],
+      "source": [
+        "dag = aiplatform.AutoMLTextTrainingJob(\n",
+        "    display_name=\"biomedical\", prediction_type=\"extraction\"\n",
+        ")\n",
+        "\n",
+        "print(dag)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:text"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 20 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:text"
+      },
+      "outputs": [],
+      "source": [
+        "model = dag.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"biomedical\",\n",
+        "    training_fraction_split=0.8,\n",
+        "    validation_fraction_split=0.1,\n",
+        "    test_fraction_split=0.1,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "caaa3f32b12e"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "\n",
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b0bb6be8621a"
+      },
+      "outputs": [],
+      "source": [
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Send a batch prediction request\n",
+        "\n",
+        "Send a batch prediction to deployed model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_test_items:automl,batch_prediction"
+      },
+      "source": [
+        "### Make test items\n",
+        "\n",
+        "You use synthetic data as a test data items. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "make_test_items:automl,text,biomedical"
+      },
+      "outputs": [],
+      "source": [
+        "test_item_1 = 'Molecular basis of hexosaminidase A deficiency and pseudodeficiency in the Berks County Pennsylvania Dutch.\\tFollowing the birth of two infants with Tay-Sachs disease ( TSD ) , a non-Jewish , Pennsylvania Dutch kindred was screened for TSD carriers using the biochemical assay . A high frequency of individuals who appeared to be TSD heterozygotes was detected ( Kelly et al . , 1975 ) . Clinical and biochemical evidence suggested that the increased carrier frequency was due to at least two altered alleles for the hexosaminidase A alpha-subunit . We now report two mutant alleles in this Pennsylvania Dutch kindred , and one polymorphism . One allele , reported originally in a French TSD patient ( Akli et al . , 1991 ) , is a GT-- > AT transition at the donor splice-site of intron 9 . The second , a C-- > T transition at nucleotide 739 ( Arg247Trp ) , has been shown by Triggs-Raine et al . ( 1992 ) to be a clinically benign \" pseudodeficient \" allele associated with reduced enzyme activity against artificial substrate . Finally , a polymorphism [ G-- > A ( 759 ) ] , which leaves valine at codon 253 unchanged , is described'\n",
+        "test_item_2 = \"Analysis of alkaptonuria (AKU) mutations and polymorphisms reveals that the CCC sequence motif is a mutational hot spot in the homogentisate 1,2 dioxygenase gene (HGO).\tWe recently showed that alkaptonuria ( AKU ) is caused by loss-of-function mutations in the homogentisate 1 , 2 dioxygenase gene ( HGO ) . Herein we describe haplotype and mutational analyses of HGO in seven new AKU pedigrees . These analyses identified two novel single-nucleotide polymorphisms ( INV4 + 31A-- > G and INV11 + 18A-- > G ) and six novel AKU mutations ( INV1-1G-- > A , W60G , Y62C , A122D , P230T , and D291E ) , which further illustrates the remarkable allelic heterogeneity found in AKU . Reexamination of all 29 mutations and polymorphisms thus far described in HGO shows that these nucleotide changes are not randomly distributed ; the CCC sequence motif and its inverted complement , GGG , are preferentially mutated . These analyses also demonstrated that the nucleotide substitutions in HGO do not involve CpG dinucleotides , which illustrates important differences between HGO and other genes for the occurrence of mutation at specific short-sequence motifs . Because the CCC sequence motifs comprise a significant proportion ( 34 . 5 % ) of all mutated bases that have been observed in HGO , we conclude that the CCC triplet is a mutational hot spot in HGO .\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_batch_file:automl,text"
+      },
+      "source": [
+        "### Make the batch input file\n",
+        "\n",
+        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can only be in JSONL format. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains the key/value pairs:\n",
+        "\n",
+        "- `content`: The Cloud Storage path to the file with the text item.\n",
+        "- `mime_type`: The content type. In our example, it is a `text` file.\n",
+        "\n",
+        "For example:\n",
+        "\n",
+        "                        {'content': '[your-bucket]/file1.txt', 'mime_type': 'text'}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "make_batch_file:automl,text"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "gcs_test_item_1 = BUCKET_URI + \"/test1.txt\"\n",
+        "with tf.io.gfile.GFile(gcs_test_item_1, \"w\") as f:\n",
+        "    f.write(test_item_1 + \"\\n\")\n",
+        "gcs_test_item_2 = BUCKET_URI + \"/test2.txt\"\n",
+        "with tf.io.gfile.GFile(gcs_test_item_2, \"w\") as f:\n",
+        "    f.write(test_item_2 + \"\\n\")\n",
+        "\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
+        "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
+        "    data = {\"content\": gcs_test_item_1, \"mime_type\": \"text/plain\"}\n",
+        "    f.write(json.dumps(data) + \"\\n\")\n",
+        "    data = {\"content\": gcs_test_item_2, \"mime_type\": \"text/plain\"}\n",
+        "    f.write(json.dumps(data) + \"\\n\")\n",
+        "\n",
+        "print(gcs_input_uri)\n",
+        "! gsutil cat $gcs_input_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request:mbsdk"
+      },
+      "source": [
+        "### Make the batch prediction request\n",
+        "\n",
+        "Now that your Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
+        "\n",
+        "- `job_display_name`: The human readable name for the batch prediction job.\n",
+        "- `gcs_source`: A list of one or more batch request input files.\n",
+        "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
+        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job = model.batch_predict(\n",
+        "    job_display_name=\"biomedical\",\n",
+        "    gcs_source=gcs_input_uri,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    sync=False,\n",
+        ")\n",
+        "\n",
+        "print(batch_predict_job)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "source": [
+        "### Wait for completion of batch prediction job\n",
+        "\n",
+        "Next, wait for the batch job to complete. Alternatively, one can set the parameter `sync` to `True` in the `batch_predict()` method to block until the batch prediction job is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job.wait()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,ten"
+      },
+      "source": [
+        "### Get the predictions\n",
+        "\n",
+        "Next, get the results from the completed batch prediction job.\n",
+        "\n",
+        "The results are written to the Cloud Storage output bucket you specified in the batch prediction request. You call the method iter_outputs() to get a list of each Cloud Storage file generated with the results. Each file contains one or more prediction requests in a JSON format:\n",
+        "\n",
+        "- `content`: The prediction request.\n",
+        "- `prediction`: The prediction response.\n",
+        " - `ids`: The internal assigned unique identifiers for each prediction request.\n",
+        " - `displayNames`: The class names for each class label.\n",
+        " - `confidences`: The predicted confidence, between 0 and 1, per class label.\n",
+        " - `textSegmentStartOffsets`: The character offset in the text to the start of the entity.\n",
+        " - `textSegmentEndOffsets`: The character offset in the text to the end of the entity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,ten"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
+        "\n",
+        "prediction_results = list()\n",
+        "for blob in bp_iter_outputs:\n",
+        "    if blob.name.split(\"/\")[-1].startswith(\"prediction\"):\n",
+        "        prediction_results.append(blob.name)\n",
+        "\n",
+        "tags = list()\n",
+        "for prediction_result in prediction_results:\n",
+        "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{prediction_result}\"\n",
+        "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
+        "        for line in gfile.readlines():\n",
+        "            line = json.loads(line)\n",
+        "            print(line)\n",
+        "            break"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI\n",
+        "\n",
+        "# Delete batch\n",
+        "batch_predict_job.delete()\n",
+        "\n",
+        "# Delete model\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete text dataset\n",
+        "dataset.delete()\n",
+        "\n",
+        "# Delete training job\n",
+        "dag.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "automl_text_entity_extraction_batch_prediction.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/automl/automl_text_sentiment_analysis_batch_prediction.ipynb

@@ -0,0 +1,824 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2021 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title"
+      },
+      "source": [
+        "# AutoML training text sentiment analysis model for batch prediction\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_text_sentiment_analysis_batch_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl_text_sentiment_analysis_batch_prediction.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/automl_text_sentiment_analysis_batch_prediction.ipynb\">\n",
+        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create text sentiment analysis models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,batch_prediction"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML text sentiment analysis model from a Python script, and then do a batch prediction using the Vertex SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- View the model evaluation.\n",
+        "- Make a batch prediction.\n",
+        "\n",
+        "There is one key difference between using batch prediction and using online prediction:\n",
+        "\n",
+        "* Prediction Service: Does an on-demand prediction for the entire set of instances (i.e., one or more data items) and returns the results in real-time.\n",
+        "\n",
+        "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:claritin,tst"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Crowdflower Claritin-Twitter dataset](https://data.world/crowdflower/claritin-twitter) from [data.world Datasets](https://data.world). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "db52a0a61fca"
+      },
+      "source": [
+        "### Installation\n",
+        "\n",
+        "Install the following packages for executing this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install --upgrade google-cloud-aiplatform -q\n",
+        "\n",
+        "! pip3 install --upgrade tensorflow -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e9255e3b156f"
+      },
+      "source": [
+        "### Colab Only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0c0b2427998a"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "435b8e413535"
+      },
+      "source": [
+        "### Before you begin\n",
+        "\n",
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "-  Run `gcloud config list`\n",
+        "-  Run `gcloud projects list`\n",
+        "-  See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# set the project id\n",
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2e6b8b324ce1"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. \n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c43a8673066"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "\n",
+        "**1. Vertex AI Workbench** \n",
+        "- Do nothing as you are already authenticated.\n",
+        "\n",
+        "**2. Local JupyterLab Instance,** uncomment and run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fbc9cd30cc4b"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd0da2c26879"
+      },
+      "source": [
+        "**3. Colab,** uncomment and run:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a336a05c6149"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0461097edfa5"
+      },
+      "source": [
+        "**4. Service Account or other**\n",
+        "- See all the authentication options here: [Google Cloud Platform Jupyter Notebook Authentication Guide](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_authentication_guide.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e5755d1a554f"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d2de92accb67"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "## Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML text sentiment analysis model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,csv"
+      },
+      "source": [
+        "#### Location of Cloud Storage training data.\n",
+        "\n",
+        "Now set the variable `IMPORT_FILE` to the location of the CSV index file in Cloud Storage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:claritin,csv,tst"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/language/claritin.csv\"\n",
+        "SENTIMENT_MAX = 4"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "source": [
+        "#### Quick peek at your data\n",
+        "\n",
+        "This tutorial uses a version of the Crowdflower Claritin-Twitter dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "\n",
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "quick_peek:csv"
+      },
+      "outputs": [],
+      "source": [
+        "if \"IMPORT_FILES\" in globals():\n",
+        "    FILE = IMPORT_FILES[0]\n",
+        "else:\n",
+        "    FILE = IMPORT_FILE\n",
+        "\n",
+        "count = ! gsutil cat $FILE | wc -l\n",
+        "print(\"Number of Examples\", int(count[0]))\n",
+        "\n",
+        "print(\"First 10 rows\")\n",
+        "! gsutil cat $FILE | head"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:text,tst"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:text,tst"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.TextDataset.create(\n",
+        "    display_name=\"Crowdflower Claritin-Twitter\",\n",
+        "    gcs_source=[IMPORT_FILE],\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.sentiment,\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:text,tst"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "An AutoML training pipeline is created with the `AutoMLTextTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: A text classification model.\n",
+        "  - `sentiment`: A text sentiment analysis model.\n",
+        "  - `extraction`: A text entity extraction model.\n",
+        "- `multi_label`: If a classification task, whether single (False) or multi-labeled (True).\n",
+        "- `sentiment_max`: If a sentiment analysis task, the maximum sentiment value.\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:text,tst"
+      },
+      "outputs": [],
+      "source": [
+        "dag = aiplatform.AutoMLTextTrainingJob(\n",
+        "    display_name=\"claritin\",\n",
+        "    prediction_type=\"sentiment\",\n",
+        "    sentiment_max=SENTIMENT_MAX,\n",
+        ")\n",
+        "\n",
+        "print(dag)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:text"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 20 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:text"
+      },
+      "outputs": [],
+      "source": [
+        "model = dag.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"claritin\",\n",
+        "    training_fraction_split=0.8,\n",
+        "    validation_fraction_split=0.1,\n",
+        "    test_fraction_split=0.1,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "caaa3f32b12e"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "\n",
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b0bb6be8621a"
+      },
+      "outputs": [],
+      "source": [
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Send a batch prediction request\n",
+        "\n",
+        "Send a batch prediction to your model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_items:batch_prediction"
+      },
+      "source": [
+        "### Get test item(s)\n",
+        "\n",
+        "Now do a batch prediction to your Vertex model. You will use arbitrary examples out of the dataset as a test items. Don't be concerned that the examples were likely used in training the model -- we just want to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_test_items:automl,tst,csv"
+      },
+      "outputs": [],
+      "source": [
+        "test_items = ! gsutil cat $IMPORT_FILE | head -n2\n",
+        "\n",
+        "if len(test_items[0]) == 4:\n",
+        "    _, test_item_1, test_label_1, _ = str(test_items[0]).split(\",\")\n",
+        "    _, test_item_2, test_label_2, _ = str(test_items[1]).split(\",\")\n",
+        "else:\n",
+        "    test_item_1, test_label_1, _ = str(test_items[0]).split(\",\")\n",
+        "    test_item_2, test_label_2, _ = str(test_items[1]).split(\",\")\n",
+        "\n",
+        "\n",
+        "print(test_item_1, test_label_1)\n",
+        "print(test_item_2, test_label_2)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_batch_file:automl,text"
+      },
+      "source": [
+        "### Make the batch input file\n",
+        "\n",
+        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can only be in JSONL format. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains the key/value pairs:\n",
+        "\n",
+        "- `content`: The Cloud Storage path to the file with the text item.\n",
+        "- `mime_type`: The content type. In our example, it is a `text` file.\n",
+        "\n",
+        "For example:\n",
+        "\n",
+        "                        {'content': '[your-bucket]/file1.txt', 'mime_type': 'text'}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "make_batch_file:automl,text"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "gcs_test_item_1 = BUCKET_URI + \"/test1.txt\"\n",
+        "with tf.io.gfile.GFile(gcs_test_item_1, \"w\") as f:\n",
+        "    f.write(test_item_1 + \"\\n\")\n",
+        "gcs_test_item_2 = BUCKET_URI + \"/test2.txt\"\n",
+        "with tf.io.gfile.GFile(gcs_test_item_2, \"w\") as f:\n",
+        "    f.write(test_item_2 + \"\\n\")\n",
+        "\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
+        "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
+        "    data = {\"content\": gcs_test_item_1, \"mime_type\": \"text/plain\"}\n",
+        "    f.write(json.dumps(data) + \"\\n\")\n",
+        "    data = {\"content\": gcs_test_item_2, \"mime_type\": \"text/plain\"}\n",
+        "    f.write(json.dumps(data) + \"\\n\")\n",
+        "\n",
+        "print(gcs_input_uri)\n",
+        "! gsutil cat $gcs_input_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request:mbsdk"
+      },
+      "source": [
+        "### Make the batch prediction request\n",
+        "\n",
+        "Now that your Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
+        "\n",
+        "- `job_display_name`: The human readable name for the batch prediction job.\n",
+        "- `gcs_source`: A list of one or more batch request input files.\n",
+        "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
+        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job = model.batch_predict(\n",
+        "    job_display_name=\"claritin\",\n",
+        "    gcs_source=gcs_input_uri,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    sync=False,\n",
+        ")\n",
+        "\n",
+        "print(batch_predict_job)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "source": [
+        "### Wait for completion of batch prediction job\n",
+        "\n",
+        "Next, wait for the batch job to complete. Alternatively, one can set the parameter `sync` to `True` in the `batch_predict()` method to block until the batch prediction job is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job.wait()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,tst"
+      },
+      "source": [
+        "### Get the predictions\n",
+        "\n",
+        "Next, get the results from the completed batch prediction job.\n",
+        "\n",
+        "The results are written to the Cloud Storage output bucket you specified in the batch prediction request. You call the method iter_outputs() to get a list of each Cloud Storage file generated with the results. Each file contains one or more prediction requests in a JSON format:\n",
+        "\n",
+        "- `content`: The prediction request.\n",
+        "- `prediction`: The prediction response.\n",
+        " - `sentiment`: The sentiment."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,tst"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
+        "\n",
+        "prediction_results = list()\n",
+        "for blob in bp_iter_outputs:\n",
+        "    if blob.name.split(\"/\")[-1].startswith(\"prediction\"):\n",
+        "        prediction_results.append(blob.name)\n",
+        "\n",
+        "tags = list()\n",
+        "for prediction_result in prediction_results:\n",
+        "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{prediction_result}\"\n",
+        "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
+        "        for line in gfile.readlines():\n",
+        "            line = json.loads(line)\n",
+        "            print(line)\n",
+        "            break"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI\n",
+        "\n",
+        "# Delete batch\n",
+        "batch_predict_job.delete()\n",
+        "\n",
+        "# Delete model\n",
+        "model.delete()\n",
+        "\n",
+        "# Delete text dataset\n",
+        "dataset.delete()\n",
+        "\n",
+        "# Delete training job\n",
+        "dag.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "automl_text_sentiment_analysis_batch_prediction.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/automl/sdk_automl_forecasting_hierarchical_batch.ipynb

@@ -87,9 +87,7 @@
         "- Create a Vertex AI `TimeSeriesDataset` resource.\n",
         "- Train the model.\n",
         "- View the model evaluation.\n",
-        "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
-        "- Make a prediction.\n",
-        "- Undeploy the `Model`."
+        "- Make a batch prediction."
       ]
     },
     {

notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb

@@ -122,48 +122,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
-        "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
-        "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -185,18 +143,7 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform"
       ]
     },
     {
@@ -205,72 +152,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "0e3cab0cc491"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
-        "## Before you begin"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "before_you_begin:nogpu"
-      },
-      "source": [
-        "### Set up your Google Cloud project\n",
+        "## Before you begin\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
+        "### Set your project ID\n",
         "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "1460fd744366"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -281,33 +194,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -318,16 +208,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -338,41 +219,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -383,64 +230,54 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell.\n"
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -451,11 +288,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -466,21 +299,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -503,26 +322,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -629,7 +428,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TimeSeriesDataset.create(\n",
-        "    display_name=\"iowa_liquor_sales_train\" + \"_\" + UUID,\n",
+        "    display_name=\"iowa_liquor_sales_train\",\n",
         "    bq_source=[TRAINING_DATASET_BQ_PATH],\n",
         ")\n",
         "\n",
@@ -689,7 +488,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DISPLAY_NAME = f\"iowa-liquor-sales-forecast-model_{UUID}\"\n",
+        "MODEL_DISPLAY_NAME = \"iowa-liquor-sales-forecast-model\"\n",
         "\n",
         "training_job = aiplatform.AutoMLForecastingTrainingJob(\n",
         "    display_name=MODEL_DISPLAY_NAME,\n",
@@ -812,7 +611,7 @@
       },
       "outputs": [],
       "source": [
-        "batch_predict_bq_output_dataset_name = f\"iowa_liquor_sales_predictions_{UUID}\"\n",
+        "batch_predict_bq_output_dataset_name = \"iowa_liquor_sales_predictions\"\n",
         "batch_predict_bq_output_dataset_path = \"{}.{}\".format(\n",
         "    PROJECT_ID, batch_predict_bq_output_dataset_name\n",
         ")\n",
@@ -840,7 +639,7 @@
       "source": [
         "For AutoML models, manual scaling can be adjusted by setting both min and max nodes i.e., `starting_replica_count` and `max_replica_count` as the same value(in this example, set to 1). The node count can be increased or decreased as required by load.\n",
         " \n",
-        "`batch_predict` can export predictions either to BigQuery or GCS. The BigQuery options are commented out below and the predictions will be exported to the BUCKET_URI."
+        "`batch_predict` can export predictions either to BigQuery or GCS. This example exports to BigQuery."
       ]
     },
     {
@@ -856,7 +655,7 @@
         ")\n",
         "\n",
         "batch_prediction_job = model.batch_predict(\n",
-        "    job_display_name=f\"iowa_liquor_sales_forecasting_predictions_{UUID}\",\n",
+        "    job_display_name=\"iowa_liquor_sales_forecasting_predictions\",\n",
         "    bigquery_source=PREDICTION_DATASET_BQ_PATH,\n",
         "    instances_format=\"bigquery\",\n",
         "    bigquery_destination_prefix=batch_predict_bq_output_uri_prefix,\n",

notebooks/official/automl/sdk_automl_text_entity_extraction_online.ipynb

@@ -123,39 +123,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
-        "\n",
-        "- The Cloud Storage SDK\n",
-        "- Git\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
-        "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
-        "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
-        "\n",
-        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
-        "\n",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
-        "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -164,7 +131,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the latest version of Vertex AI SDK for Python."
       ]
     },
     {
@@ -177,33 +144,8 @@
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_storage"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-storage* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_storage"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage"
       ]
     },
     {
@@ -212,57 +154,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
+        "### Set your project ID\n",
         "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -273,33 +196,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -310,16 +210,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -330,33 +221,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -367,53 +232,54 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "**Click Create service account**.\n",
-        "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -424,11 +290,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -439,19 +301,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -471,27 +321,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
@@ -538,7 +368,7 @@
       },
       "outputs": [],
       "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -630,7 +460,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TextDataset.create(\n",
-        "    display_name=\"NCBI Biomedical\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"NCBI Biomedical\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.extraction,\n",
         ")\n",
@@ -670,7 +500,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLTextTrainingJob(\n",
-        "    display_name=\"biomedical_\" + TIMESTAMP, prediction_type=\"extraction\"\n",
+        "    display_name=\"biomedical\", prediction_type=\"extraction\"\n",
         ")\n",
         "\n",
         "print(job)"
@@ -707,7 +537,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"biomedical_\" + TIMESTAMP,\n",
+        "    model_display_name=\"biomedical\",\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -735,7 +565,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=\"display_name=biomedical_\" + TIMESTAMP)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=biomedical\")\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -916,7 +746,7 @@
         "job.delete()\n",
         "\n",
         "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil -m rm -r $BUCKET_NAME"
+        "    ! gsutil -m rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/automl/sdk_automl_text_sentiment_analysis_online.ipynb

@@ -124,44 +124,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
-        "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
-        "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -183,19 +145,8 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
-        "! pip3 install -U google-cloud-storage $USER_FLAG -q"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage"
       ]
     },
     {
@@ -204,65 +155,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### Set up your Google Cloud project\n",
+        "### Set your project ID\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, Compute Engine, and Cloud Storage APIs.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "af794e75b7e3"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -273,33 +197,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -310,16 +211,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -330,41 +222,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -375,64 +233,54 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -443,11 +291,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize your Vertex AI SDK, you provide a Cloud Storage bucket to the SDK to serve as a staging bucket for the session. \n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -458,21 +302,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -495,26 +325,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -638,7 +448,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TextDataset.create(\n",
-        "    display_name=\"Crowdflower Claritin-Twitter\" + \"_\" + UUID,\n",
+        "    display_name=\"Crowdflower Claritin-Twitter\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.sentiment,\n",
         ")\n",
@@ -681,7 +491,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLTextTrainingJob(\n",
-        "    display_name=\"claritin_\" + UUID,\n",
+        "    display_name=\"claritin\",\n",
         "    prediction_type=\"sentiment\",\n",
         "    sentiment_max=SENTIMENT_MAX,\n",
         ")\n",
@@ -720,7 +530,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"claritin_\" + UUID,\n",
+        "    model_display_name=\"claritin\",\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -749,7 +559,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=\"display_name=claritin_\" + UUID)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=claritin\")\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",

notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb

@@ -130,48 +130,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook.\n",
-        "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
-        "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
-        "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -193,17 +151,8 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade --quiet {USER_FLAG} google-cloud-aiplatform google-cloud-storage"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                google-cloud-storage"
       ]
     },
     {
@@ -212,65 +161,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### Set up your Google Cloud project\n",
+        "### Set your project ID\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5aee4379e8e5"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -281,33 +203,10 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -318,16 +217,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -338,41 +228,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -383,64 +239,54 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -451,11 +297,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you run a Vertex AI pipeline job using the Cloud SDK, your job stores the pipeline artifacts to a Cloud Storage bucket. In this tutorial, you create a Vertex AI Pipeline job that saves the artifacts like evaluation metrics and feature attributes to a Cloud Storage bucket.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -466,27 +308,13 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "create_bucket"
+        "id": "autoset_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -496,33 +324,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "91c46850b49b"
       },
       "outputs": [],
       "source": [
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -653,7 +461,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"Golf Swings\" + \"_\" + UUID,\n",
+        "    display_name=\"Golf Swings\",\n",
         "    gcs_source=IMPORT_FILES,\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.action_recognition,\n",
         ")\n",
@@ -693,7 +501,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"golf_\" + UUID,\n",
+        "    display_name=\"golf\",\n",
         "    prediction_type=\"action_recognition\",\n",
         ")\n",
         "\n",
@@ -730,7 +538,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"golf_\" + UUID,\n",
+        "    model_display_name=\"golf\",\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -876,7 +684,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"golf_\" + UUID,\n",
+        "    job_display_name=\"golf\",\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    sync=False,\n",

notebooks/official/automl/sdk_automl_video_classification_batch.ipynb

@@ -128,55 +128,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "384b53dfdb54"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
-        "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
-        "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard.\n"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -198,19 +149,8 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
-        "! pip3 install -U google-cloud-storage {USER_FLAG} -q"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage"
       ]
     },
     {
@@ -219,79 +159,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
+        "### Set your project ID\n",
         "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these conmmands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "1460fd744366"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cd85f5c794e5"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -302,22 +201,10 @@
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -328,16 +215,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -348,116 +226,65 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "79055ac4078d"
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gcp_authenticate"
-      },
-      "source": [
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -468,12 +295,7 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you create a model in Vertex AI using the Cloud SDK, you give a Cloud Storage path where the trained model is saved. In this tutorial, you create a batch prediction job using the Vertex AI model. For this purpose, you need to save your test instances to a Cloud Storage bucket and give a destination Cloud Storage path to write the batch predictions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
-        "Cloud Storage buckets."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -484,21 +306,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -521,26 +329,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -669,7 +457,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"MIT Human Motion\" + \"_\" + UUID,\n",
+        "    display_name=\"MIT Human Motion\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
         ")\n",
@@ -707,7 +495,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"hmdb_\" + UUID,\n",
+        "    display_name=\"hmdb\",\n",
         "    prediction_type=\"classification\",\n",
         ")\n",
         "\n",
@@ -744,7 +532,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"hmdb_\" + UUID,\n",
+        "    model_display_name=\"hmdb\",\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -773,7 +561,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID using the display_name\n",
-        "models = aiplatform.Model.list(filter=\"display_name=hmdb_\" + UUID)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=hmdb\")\n",
         "\n",
         "if len(models) != 0:\n",
         "\n",
@@ -876,7 +664,7 @@
         "}\n",
         "\n",
         "\n",
-        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_NAME)\n",
+        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_URI[5:])\n",
         "blob = bucket.blob(blob_name=test_filename)\n",
         "data = json.dumps(data_1) + \"\\n\" + json.dumps(data_2) + \"\\n\"\n",
         "blob.upload_from_string(data)\n",
@@ -929,7 +717,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"hmdb_\" + UUID,\n",
+        "    job_display_name=\"hmdb\",\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    sync=False,\n",

notebooks/official/automl/sdk_automl_video_object_tracking_batch.ipynb

@@ -126,38 +126,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements. You need the following:\n",
-        "\n",
-        "- The Cloud Storage SDK\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
-        "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
-        "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
-        "\n",
-        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
-        "\n",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
-        "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -179,19 +147,8 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform google-cloud-storage $USER_FLAG -q"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage"
       ]
     },
     {
@@ -200,109 +157,52 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages.\n",
-        "\n",
-        "**Note: You may get a message saying \"Your session crashed for an unknown reason.\", this is expected. Once this cell has finished running, continue on. You do not need to re-run any of the cells above.**"
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
+        "### Set your project ID\n",
         "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "6. (optional) You may also specify a service account to use to run Vertex AI Pipelines in the project.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5aee4379e8e5"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "dcdfccf50581"
+        "id": "set_project_id"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "5bf9979b96ff"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "09021c90b34c"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -313,16 +213,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -333,40 +224,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -377,56 +235,54 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "- In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "- **Click Create service account**.\n",
-        "\n",
-        "- In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "- In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "- Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "- Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -437,42 +293,24 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "f78cf4290843"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "219a24ea078b"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "a8a62bec0259"
+        "id": "create_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -489,26 +327,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "4e69d430073b"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "835eaacd691f"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -642,7 +460,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"Traffic\" + \"_\" + UUID,\n",
+        "    display_name=\"Traffic\",\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.object_tracking,\n",
         ")\n",
@@ -680,7 +498,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"traffic_\" + UUID,\n",
+        "    display_name=\"traffic\",\n",
         "    prediction_type=\"object_tracking\",\n",
         ")\n",
         "\n",
@@ -717,7 +535,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"traffic_\" + UUID,\n",
+        "    model_display_name=\"traffic\",\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -895,7 +713,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"traffic_\" + UUID,\n",
+        "    job_display_name=\"traffic\",\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    sync=False,\n",

notebooks/official/bigquery_ml/README.md

@@ -15,5 +15,25 @@ The steps performed include:
 
 ```
 
-   Learn more about [BigQuery ML](https://cloud.google.com/bigquery-ml/docs/introduction).
+   Learn more about [BigQuery ML](https://cloud.google.com/vertex-ai/docs/beginner/bqml).
+
+
+[Get started with BigQuery ML Training](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/bigquery_ml/get_started_with_bqml_training.ipynb)
+
+```
+Learn how to use `BigQueryML` for training with `Vertex AI`.
+
+The steps performed include:
+
+- Create a local BigQuery table in your project
+- Train a BigQuery ML model
+- Evaluate the BigQuery ML model
+- Export the BigQuery ML model as a cloud model
+- Upload the exported model as a `Vertex AI Model` resource
+- Hyperparameter tune a BigQuery ML model with `Vertex AI Vizier`
+- Automatically register a BigQuery ML model to `Vertex AI Model Registry`
+
+```
+
+   Learn more about [BigQuery ML](https://cloud.google.com/vertex-ai/docs/beginner/bqml).
 

notebooks/official/bigquery_ml/bqml-online-prediction.ipynb

@@ -63,7 +63,7 @@
         "\n",
         "This notebook is aimed at data analysts and data scientists who have data in BigQuery, want to train a model using BigQuery ML, register the model to Vertex AI Model Registry, and deploy it to an endpoint for real-time prediction. \n",
         "\n",
-        "Learn more about [BigQuery ML](https://cloud.google.com/bigquery-ml/docs/introduction)."
+        "Learn more about [BigQuery ML](https://cloud.google.com/vertex-ai/docs/beginner/bqml)."
       ]
     },
     {
@@ -126,55 +126,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ze4-nDLfK4pw"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gCuSR8GkAgzl"
-      },
-      "source": [
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to <a href=\"https://cloud.google.com/python/setup\" target=\"_blank\">Setting up a Python development\n",
-        "environment</a> and the <a href=\"https://jupyter.org/install\" target=\"_blank\">Jupyter\n",
-        "installation guide</a> provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. <a href=\"https://cloud.google.com/sdk/docs/\" target=\"_blank\">Install and initialize the Cloud SDK.</a>\n",
-        "\n",
-        "1. <a href=\"https://cloud.google.com/python/setup#installing_python\" target=\"_blank\">Install Python 3.</a>\n",
-        "\n",
-        "1. <a href=\"https://cloud.google.com/python/setup#installing_and_using_virtualenv\" target=\"_blank\">Install\n",
-        "   virtualenv</a>\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -194,140 +145,63 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q google-cloud-bigquery db-dtypes"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-bigquery \\\n",
+        "                                 db-dtypes"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "hhq5zEbGg0XX"
+        "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "EzrelQZ22IZj"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "lWEdiXsJg0XY"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
-        "## Before you begin"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "BF1j6f9HApxa"
-      },
-      "source": [
-        "### Set up your Google Cloud project\n",
+        "## Before you begin\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
+        "### Set your project ID\n",
         "\n",
-        "1. <a href=\"https://console.cloud.google.com/cloud-resource-manager\" target=\"_blank\">Select or create a Google Cloud project</a>. When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. <a href=\"https://cloud.google.com/billing/docs/how-to/modify-project\" target=\"_blank\">Make sure that billing is enabled for your project</a>.\n",
-        "\n",
-        "1. <a href=\"https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com\" target=\"_blank\">Enable the Vertex AI API</a>.\n",
-        "\n",
-        "1. If you are running this notebook locally, you will need to install the <a href=\"https://cloud.google.com/sdk\" target=\"_blank\">Cloud SDK</a>.\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "3c8049930470"
+        "id": "set_project_id"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "oM1iC_MfAts1"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "riG_qUokg0XZ"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -338,16 +212,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You might not be able to use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about <a href=\"https://cloud.google.com/vertex-ai/docs/general/locations\" target=\"_blank\">Vertex AI regions</a>."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -358,115 +223,118 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "06571eb4063b"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "697568e92bd6"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dr--iN2kAylZ"
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "sBCra4QMA2wR"
-      },
-      "source": [
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "1. In the Cloud Console, go to the <a href=\"https://console.cloud.google.com/apis/credentials/serviceaccountkey\" target=\"_blank\">**Create service account key** page</a>.\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "PyQmSRbKA8r-"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
         "\n",
-        "import os\n",
-        "import sys\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bucket"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "44accda192d5"
+      },
+      "source": [
+        "#### Service Account\n",
         "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
       ]
     },
     {
@@ -569,7 +437,7 @@
       },
       "outputs": [],
       "source": [
-        "bq_client = bigquery.Client(project=PROJECT_ID)"
+        "bq_client = bigquery.Client(project=PROJECT_ID, location=REGION)"
       ]
     },
     {
@@ -633,7 +501,7 @@
       },
       "outputs": [],
       "source": [
-        "BQ_DATASET_NAME = f\"ga4_churnprediction_{UUID}\"\n",
+        "BQ_DATASET_NAME = \"ga4_churnprediction\"\n",
         "\n",
         "sql_create_dataset = f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\"\n",
         "\n",
@@ -714,7 +582,7 @@
       "source": [
         "# this cell may take ~1 min to run\n",
         "\n",
-        "BQML_MODEL_NAME = f\"bqml_model_churn_{UUID}\"\n",
+        "BQML_MODEL_NAME = \"bqml_model_churn\"\n",
         "\n",
         "sql_train_model_bqml = f\"\"\"\n",
         "CREATE OR REPLACE MODEL {BQ_DATASET_NAME}.{BQML_MODEL_NAME}    \n",

notebooks/official/custom/README.md

@@ -14,7 +14,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
+   Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
 
    Learn more about [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions).
 
@@ -37,7 +37,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
+   Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
 
    Learn more about [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions).
 
@@ -60,6 +60,22 @@ The steps performed include:
    Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
 
 
+[Custom training with custom training container and automatic registering of the model](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/custom_training_container_and_model_registry.ipynb)
+
+```
+In this tutorial, you create a custom model from a Python script in a custom Docker container using the Vertex AI SDK, and automatically register the model in the Vertex AI Model Registry.
+
+The steps performed include:
+
+- Create a Vertex AI custom job for training a model.
+- Train and register a TensorFlow model using a custom container,
+- List the registered model from the Vertex AI Model Registry.
+
+```
+
+   Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
+
+
 [Profile model training performance using Profiler](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/custom_training_tensorboard_profiler.ipynb)
 
 ```
@@ -77,6 +93,45 @@ The steps performed include:
    Learn more about [Vertex AI TensorBoard Profiler](https://cloud.google.com/vertex-ai/docs/experiments/tensorboard-profiler).
 
 
+[Get started with Vertex AI Training for XGBoost](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/get_started_vertex_training.ipynb)
+
+```
+Learn how to use `Vertex AI Training` for training a XGBoost custom model.
+
+The steps performed include:
+
+- Training using a Python package.
+- Report accuracy when hyperparameter tuning.
+- Save the model artifacts to Cloud Storage using GCSFuse.
+- Create a `Vertex AI Model` resource.
+
+```
+
+   Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
+
+
+[Get started with Endpoint and shared VM](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/get_started_with_vertex_endpoint_and_shared_vm.ipynb)
+
+```
+Learn how to use deployment resource pools for deploying models.
+
+The steps performed include:
+
+- Upload a pre-trained image classification model as a `Model` resource (model A).
+- Upload a pre-trained text sentence encoder model as a `Model` resource (model B).
+- Create a shared VM deployment resource pool.
+- List shared VM deployment resource pools.
+- Create two `Endpoint` resources.
+- Deploy first model (model A) to first `Endpoint` resource using deployment resource pool.
+- Deploy second model (model B) to second `Endpoint` resource using deployment resource pool.
+- Make a prediction request with first deployed model (model A).
+- Make a prediction request with second deployed model (model B).
+
+```
+
+   Learn more about [Shared resources across deployments](https://cloud.google.com/vertex-ai/docs/predictions/model-co-hosting).
+
+
 [Custom training and batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-batch.ipynb)
 
 ```
@@ -90,7 +145,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
+   Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
 
    Learn more about [Vertex AI Batch Prediction](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions).
 
@@ -111,7 +166,7 @@ The steps performed include:
 
 ```
 
-   Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
+   Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training).
 
    Learn more about [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions).
 

notebooks/official/custom/SDK_Custom_Container_Prediction.ipynb

@@ -60,7 +60,7 @@
         "\n",
         "This tutorial walks you through building a custom container to serve a scikit-learn model on Vertex AI. You use the FastAPI Python web server framework to create a prediction and health endpoint. You also incorporate a pre-processor from training pipeline into your online serving application.\n",
         "\n",
-        "Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training)  and [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions)."
+        "Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training) and [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions)."
       ]
     },
     {

notebooks/official/custom/SDK_FBProphet_Forecasting_Online.ipynb

@@ -64,7 +64,7 @@
         "\n",
         "Learn more about serving an FBProphet model from this [article on testdriven.io: Deploying and Hosting a Machine Learning Model with FastAPI and Heroku](https://testdriven.io/blog/fastapi-machine-learning/).\n",
         "\n",
-        "Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training) and [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions).\n"
+        "Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training) and [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions).\n"
       ]
     },
     {

notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb

@@ -147,8 +147,7 @@
         "# Install the packages\n",
         "! pip3 install --upgrade google-cloud-aiplatform \\\n",
         "                        google-cloud-storage \\\n",
-        "                        google-cloud-bigquery \\\n",
-        "                        pyarrow"
+        "                        'google-cloud-bigquery[pandas]'"
       ]
     },
     {
@@ -632,12 +631,12 @@
         "    df_train_x, df_train_y = df_train, df_train.pop(LABEL_COLUMN)\n",
         "    df_validation_x, df_validation_y = df_validation, df_validation.pop(LABEL_COLUMN)\n",
         "\n",
-        "    y_train = np.asarray(df_train_y).astype(\"float32\")\n",
-        "    y_validation = np.asarray(df_validation_y).astype(\"float32\")\n",
+        "    y_train = tf.convert_to_tensor(np.asarray(df_train_y).astype(\"float32\"))\n",
+        "    y_validation = tf.convert_to_tensor(np.asarray(df_validation_y).astype(\"float32\"))\n",
         "\n",
         "    # Convert to numpy representation\n",
-        "    x_train = np.asarray(df_train_x) \n",
-        "    x_test = np.asarray(df_validation_x)\n",
+        "    x_train = tf.convert_to_tensor(np.asarray(df_train_x).astype(\"float32\"))\n",
+        "    x_test = tf.convert_to_tensor(np.asarray(df_validation_x).astype(\"float32\"))\n",
         "\n",
         "    # Convert to one-hot representation\n",
         "    num_species = len(df_train_y.unique())\n",
@@ -735,7 +734,7 @@
         "    display_name=JOB_NAME,\n",
         "    script_path=\"task.py\",\n",
         "    container_uri=\"us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8:latest\",\n",
-        "    requirements=[\"google-cloud-bigquery>=2.20.0\", \"db-dtypes\"],\n",
+        "    requirements=[\"google-cloud-bigquery[pandas]\", \"protobuf<3.20.0\"],\n",
         "    model_serving_container_image_uri=\"us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest\",\n",
         ")\n",
         "\n",

notebooks/official/custom/get_started_vertex_training_xgboost.ipynb

@@ -0,0 +1,994 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2022 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "title:generic,gcp"
+      },
+      "source": [
+        "# Get started with Vertex AI Training for XGBoost\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/get_started_vertex_training.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/get_started_vertex_training.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/custom/get_started_vertex_training.ipynb\">\n",
+        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:mlops"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This tutorial demonstrates how to use Vertex AI Training for XGBoost models.\n",
+        "\n",
+        "Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:mlops,stage2,get_started_vertex_training_xgboost"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to use `Vertex AI Training` for training a XGBoost custom model.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Model` resource\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Training using a Python package.\n",
+        "- Report accuracy when hyperparameter tuning.\n",
+        "- Save the model artifacts to Cloud Storage using GCSFuse.\n",
+        "- Create a `Vertex AI Model` resource."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:iris,lcn"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Iris dataset](https://www.tensorflow.org/datasets/catalog/iris) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of Iris flower species from a class of three species: setosa, virginica, or versicolor."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4fc0ad661ebb"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_mlops"
+      },
+      "source": [
+        "## Installations\n",
+        "\n",
+        "Install the following packages to execute this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ncRJ_Dfdox9L"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install --upgrade google-cloud-aiplatform  -quiet"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e9255e3b156f"
+      },
+      "source": [
+        "### Colab Only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0c0b2427998a"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "435b8e413535"
+      },
+      "source": [
+        "### Before you begin\n",
+        "\n",
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "-  Run `gcloud config list`\n",
+        "-  Run `gcloud projects list`\n",
+        "-  See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "be175254a715"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# set the project id\n",
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2e6b8b324ce1"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. \n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "region"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c43a8673066"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "\n",
+        "**1. Vertex AI Workbench** \n",
+        "- Do nothing as you are already authenticated.\n",
+        "\n",
+        "**2. Local JupyterLab Instance,** uncomment and run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fbc9cd30cc4b"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd0da2c26879"
+      },
+      "source": [
+        "**3. Colab,** uncomment and run:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a336a05c6149"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0461097edfa5"
+      },
+      "source": [
+        "**4. Service Account or other**\n",
+        "- See how to grant Cloud Storage permissions to your service account at [IAM Ch Examples](https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e5755d1a554f"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d2de92accb67"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aO4sKJfFox9R"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "yWnghzKFox9S"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_vars"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "import google.cloud.aiplatform as aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "JZg2sszQox9T"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "accelerators:training,cpu,prediction,cpu,mbsdk"
+      },
+      "source": [
+        "#### Set hardware accelerators\n",
+        "\n",
+        "You can set hardware accelerators for training and prediction.\n",
+        "\n",
+        "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 NVIDIA Tesla K80 GPUs allocated to each VM, you would specify:\n",
+        "\n",
+        "    (aiplatform.gapic..AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "\n",
+        "\n",
+        "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
+        "\n",
+        "Learn more about [hardware accelerator support for your region](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators).\n",
+        "\n",
+        "*Note*: TF releases before 2.3 for GPU support will fail to load the custom model in this tutorial. It is a known issue and fixed in TF 2.3. This is caused by static graph ops that are generated in the serving function. If you encounter this issue on your own custom models, use a container image for TF 2.3 with GPU support."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cQUrG4Mbox9T"
+      },
+      "outputs": [],
+      "source": [
+        "TRAIN_GPU, TRAIN_NGPU = (None, None)\n",
+        "\n",
+        "DEPLOY_GPU, DEPLOY_NGPU = (None, None)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "container:training,prediction,xgboost"
+      },
+      "source": [
+        "#### Set pre-built containers\n",
+        "\n",
+        "Set the pre-built Docker container image for training and prediction.\n",
+        "\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/ai-platform-unified/docs/training/pre-built-containers).\n",
+        "\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XujRA5ueox9U"
+      },
+      "outputs": [],
+      "source": [
+        "TRAIN_VERSION = \"xgboost-cpu.1-1\"\n",
+        "DEPLOY_VERSION = \"xgboost-cpu.1-1\"\n",
+        "\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "machine:training"
+      },
+      "source": [
+        "#### Set machine type\n",
+        "\n",
+        "Next, set the machine type to use for training.\n",
+        "\n",
+        "- Set the variable `TRAIN_COMPUTE` to configure  the compute resources for the VMs you will use for for training.\n",
+        " - `machine type`\n",
+        "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
+        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+        "\n",
+        "*Note: The following is not supported for training:*\n",
+        "\n",
+        " - `standard`: 2 vCPUs\n",
+        " - `highcpu`: 2, 4 and 8 vCPUs\n",
+        "\n",
+        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "UMPFgENkox9U"
+      },
+      "outputs": [],
+      "source": [
+        "TRAIN_COMPUTE = \"n1-standard-4\"\n",
+        "print(\"Train machine type\", TRAIN_COMPUTE)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "xgboost_intro"
+      },
+      "source": [
+        "## Introduction to XGBoost training\n",
+        "\n",
+        "Once you have trained a XGBoost model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource.\n",
+        "The XGBoost package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
+        "\n",
+        "1. Save the in-memory model to the local filesystem (e.g., model.bst).\n",
+        "2. Use gsutil to copy the local copy to the specified Cloud Storage location.\n",
+        "\n",
+        "*Note*: You can do hyperparameter tuning with a XGBoost model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "examine_training_package:xgboost"
+      },
+      "source": [
+        "### Examine the training package\n",
+        "\n",
+        "#### Package layout\n",
+        "\n",
+        "Before you start the training, you will look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
+        "\n",
+        "- PKG-INFO\n",
+        "- README.md\n",
+        "- setup.cfg\n",
+        "- setup.py\n",
+        "- trainer\n",
+        "  - \\_\\_init\\_\\_.py\n",
+        "  - task.py\n",
+        "\n",
+        "The files `setup.cfg` and `setup.py` are the instructions for installing the package into the operating environment of the Docker image.\n",
+        "\n",
+        "The file `trainer/task.py` is the Python script for executing the custom training job. *Note*, when we referred to it in the worker pool specification, we replace the directory slash with a dot (`trainer.task`) and dropped the file suffix (`.py`).\n",
+        "\n",
+        "#### Package Assembly\n",
+        "\n",
+        "In the following cells, you will assemble the training package."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f4wS4eISox9V"
+      },
+      "outputs": [],
+      "source": [
+        "# Make folder for Python training script\n",
+        "! rm -rf custom\n",
+        "! mkdir custom\n",
+        "\n",
+        "# Add package information\n",
+        "! touch custom/README.md\n",
+        "\n",
+        "setup_cfg = \"[egg_info]\\n\\ntag_build =\\n\\ntag_date = 0\"\n",
+        "! echo \"$setup_cfg\" > custom/setup.cfg\n",
+        "\n",
+        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'cloudml-hypertune',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
+        "! echo \"$setup_py\" > custom/setup.py\n",
+        "\n",
+        "pkg_info = \"Metadata-Version: 1.0\\n\\nName: Iris tabular classification\\n\\nVersion: 0.0.0\\n\\nSummary: Demostration training script\\n\\nHome-page: www.google.com\\n\\nAuthor: Google\\n\\nAuthor-email: aferlitsch@google.com\\n\\nLicense: Public\\n\\nDescription: Demo\\n\\nPlatform: Vertex\"\n",
+        "! echo \"$pkg_info\" > custom/PKG-INFO\n",
+        "\n",
+        "# Make the training subfolder\n",
+        "! mkdir custom/trainer\n",
+        "! touch custom/trainer/__init__.py"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "taskpy_contents:iris,xgboost"
+      },
+      "source": [
+        "### Create the task script for the Python training package\n",
+        "\n",
+        "Next, you create the `task.py` script for driving the training package. Some noteable steps include:\n",
+        "\n",
+        "- Command-line arguments:\n",
+        "    - `model-dir`: The location to save the trained model. When using Vertex AI custom training, the location will be specified in the environment variable: `AIP_MODEL_DIR`,\n",
+        "    - `dataset_data_url`: The location of the training data to download.\n",
+        "    - `dataset_labels_url`: The location of the training labels to download.\n",
+        "    - `boost-rounds`: Tunable hyperparameter\n",
+        "- Data preprocessing (`get_data()`):\n",
+        "    - Download the dataset and split into training and test.\n",
+        "- Training (`train_model()`):\n",
+        "    - Trains the model\n",
+        "- Evaluation (`evaluate_model()`):\n",
+        "    - Evaluates the model.\n",
+        "    - If hyperparameter tuning, reports the metric for accuracy.\n",
+        "- Model artifact saving\n",
+        "    - Saves the model artifacts and evaluation metrics where the Cloud Storage location specified by `model-dir`.\n",
+        "    \n",
+        "*Note:* The training script uses GCSFuse which mounts the Cloud Storage bucket as a network filesystem, allowing the script to perform filesystem operations (e.g., read and write) within a Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WiSnFuDoox9W"
+      },
+      "outputs": [],
+      "source": [
+        "%%writefile custom/trainer/task.py\n",
+        "import datetime\n",
+        "import os\n",
+        "import subprocess\n",
+        "import sys\n",
+        "import pandas as pd\n",
+        "import xgboost as xgb\n",
+        "import hypertune\n",
+        "import argparse\n",
+        "import logging\n",
+        "import numpy as np\n",
+        "\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "\n",
+        "parser = argparse.ArgumentParser()\n",
+        "parser.add_argument('--model-dir', dest='model_dir',\n",
+        "                    default=os.getenv('AIP_MODEL_DIR'), type=str, help='Model dir.')\n",
+        "parser.add_argument(\"--dataset-data-url\", dest=\"dataset_data_url\",\n",
+        "                    type=str, help=\"Download url for the training data.\")\n",
+        "parser.add_argument(\"--dataset-labels-url\", dest=\"dataset_labels_url\",\n",
+        "                    type=str, help=\"Download url for the training data labels.\")\n",
+        "parser.add_argument(\"--boost-rounds\", dest=\"boost_rounds\",\n",
+        "                    default=20, type=int, help=\"Number of boosted rounds\")\n",
+        "args = parser.parse_args()\n",
+        "\n",
+        "logging.getLogger().setLevel(logging.INFO)\n",
+        "\n",
+        "def get_data():\n",
+        "    logging.info(\"Downloading training data and labelsfrom: {}, {}\".format(args.dataset_data_url, args.dataset_labels_url))\n",
+        "    # gsutil outputs everything to stderr so we need to divert it to stdout.\n",
+        "    subprocess.check_call(['gsutil', 'cp', args.dataset_data_url, 'data.csv'], stderr=sys.stdout)\n",
+        "    # gsutil outputs everything to stderr so we need to divert it to stdout.\n",
+        "    subprocess.check_call(['gsutil', 'cp', args.dataset_labels_url, 'labels.csv'], stderr=sys.stdout)\n",
+        "\n",
+        "\n",
+        "    # Load data into pandas, then use `.values` to get NumPy arrays\n",
+        "    data = pd.read_csv('data.csv').values\n",
+        "    labels = pd.read_csv('labels.csv').values\n",
+        "\n",
+        "    # Convert one-column 2D array into 1D array for use with XGBoost\n",
+        "    labels = labels.reshape((labels.size,))\n",
+        "\n",
+        "    train_data, test_data, train_labels, test_labels = train_test_split(data, labels, test_size=0.2, random_state=7)\n",
+        "\n",
+        "    # Load data into DMatrix object\n",
+        "    dtrain = xgb.DMatrix(train_data, label=train_labels)\n",
+        "    return dtrain, test_data, test_labels\n",
+        "\n",
+        "def train_model(dtrain):\n",
+        "    logging.info(\"Start training ...\")\n",
+        "    # Train XGBoost model\n",
+        "    params = {\n",
+        "        'objective': 'multi:softprob',\n",
+        "        'num_class': 3\n",
+        "    }\n",
+        "    model = xgb.train(params, dtrain, num_boost_round=args.boost_rounds)\n",
+        "    logging.info(\"Training completed\")\n",
+        "    return model\n",
+        "\n",
+        "def evaluate_model(model, test_data, test_labels):\n",
+        "    dtest = xgb.DMatrix(test_data)\n",
+        "    pred = model.predict(dtest)\n",
+        "    predictions = [np.around(value) for value in pred]\n",
+        "    # evaluate predictions\n",
+        "    try:\n",
+        "        accuracy = accuracy_score(test_labels, predictions)\n",
+        "    except:\n",
+        "        accuracy = 0.0\n",
+        "    logging.info(f\"Evaluation completed with model accuracy: {accuracy}\")\n",
+        "\n",
+        "    # report metric for hyperparameter tuning\n",
+        "    hpt = hypertune.HyperTune()\n",
+        "    hpt.report_hyperparameter_tuning_metric(\n",
+        "        hyperparameter_metric_tag='accuracy',\n",
+        "        metric_value=accuracy\n",
+        "    )\n",
+        "    return accuracy\n",
+        "\n",
+        "\n",
+        "dtrain, test_data, test_labels = get_data()\n",
+        "model = train_model(dtrain)\n",
+        "accuracy = evaluate_model(model, test_data, test_labels)\n",
+        "\n",
+        "# GCSFuse conversion\n",
+        "gs_prefix = 'gs://'\n",
+        "gcsfuse_prefix = '/gcs/'\n",
+        "if args.model_dir.startswith(gs_prefix):\n",
+        "    args.model_dir = args.model_dir.replace(gs_prefix, gcsfuse_prefix)\n",
+        "    dirpath = os.path.split(args.model_dir)[0]\n",
+        "    if not os.path.isdir(dirpath):\n",
+        "        os.makedirs(dirpath)\n",
+        "\n",
+        "# Export the classifier to a file\n",
+        "gcs_model_path = os.path.join(args.model_dir, 'model.bst')\n",
+        "logging.info(\"Saving model artifacts to {}\". format(gcs_model_path))\n",
+        "model.save_model(gcs_model_path)\n",
+        "\n",
+        "logging.info(\"Saving metrics to {}/metrics.json\". format(args.model_dir))\n",
+        "gcs_metrics_path = os.path.join(args.model_dir, 'metrics.json')\n",
+        "with open(gcs_metrics_path, \"w\") as f:\n",
+        "    f.write(f\"{'accuracy: {accuracy}'}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tarball_training_script"
+      },
+      "source": [
+        "#### Store training script on your Cloud Storage bucket\n",
+        "\n",
+        "Next, you package the training folder into a compressed tar ball, and then store it in your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dnmdycf6ox9X"
+      },
+      "outputs": [],
+      "source": [
+        "! rm -f custom.tar custom.tar.gz\n",
+        "! tar cvf custom.tar custom\n",
+        "! gzip custom.tar\n",
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_iris.tar.gz"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_custom_pp_training_job:mbsdk"
+      },
+      "source": [
+        "### Create and run custom training job\n",
+        "\n",
+        "\n",
+        "To train a custom model, you perform two steps: 1) create a custom training job, and 2) run the job.\n",
+        "\n",
+        "#### Create custom training job\n",
+        "\n",
+        "A custom training job is created with the `CustomTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the custom training job.\n",
+        "- `container_uri`: The training container image.\n",
+        "\n",
+        "- `python_package_gcs_uri`: The location of the Python training package as a tarball.\n",
+        "- `python_module_name`: The relative path to the training script in the Python package.\n",
+        "- `model_serving_container_uri`: The container image for deploying the model.\n",
+        "\n",
+        "*Note:* There is no requirements parameter. You specify any requirements in the `setup.py` script in your Python package."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "rVEMz1xqox9X"
+      },
+      "outputs": [],
+      "source": [
+        "DISPLAY_NAME = \"iris\"\n",
+        "\n",
+        "job = aiplatform.CustomPythonPackageTrainingJob(\n",
+        "    display_name=DISPLAY_NAME,\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_iris.tar.gz\",\n",
+        "    python_module_name=\"trainer.task\",\n",
+        "    container_uri=TRAIN_IMAGE,\n",
+        "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
+        "    project=PROJECT_ID,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "prepare_custom_cmdargs:iris,xgboost"
+      },
+      "source": [
+        "### Prepare your command-line arguments\n",
+        "\n",
+        "Now define the command-line arguments for your custom training container:\n",
+        "\n",
+        "- `args`: The command-line arguments to pass to the executable that is set as the entry point into the container.\n",
+        "  - `--model-dir` : For our demonstrations, we use this command-line argument to specify where to store the model artifacts.\n",
+        "      - direct: You pass the Cloud Storage location as a command line argument to your training script (set variable `DIRECT = True`), or\n",
+        "      - indirect: The service passes the Cloud Storage location as the environment variable `AIP_MODEL_DIR` to your training script (set variable `DIRECT = False`). In this case, you tell the service the model artifact location in the job specification.\n",
+        "  - `--dataset-data-url`: The location of the training data to download.\n",
+        "  - `--dataset-labels-url`: The location of the training labels to download.\n",
+        "  - `--boost-rounds`: Tunable hyperparameter."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "AoUfpBqVox9Y"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, \"model\")\n",
+        "DATASET_DIR = \"gs://cloud-samples-data/ai-platform/iris\"\n",
+        "\n",
+        "ROUNDS = 20\n",
+        "\n",
+        "DIRECT = False\n",
+        "if DIRECT:\n",
+        "    CMDARGS = [\n",
+        "        \"--dataset-data-url=\" + DATASET_DIR + \"/iris_data.csv\",\n",
+        "        \"--dataset-labels-url=\" + DATASET_DIR + \"/iris_target.csv\",\n",
+        "        \"--boost-rounds=\" + str(ROUNDS),\n",
+        "        \"--model_dir=\" + MODEL_DIR,\n",
+        "    ]\n",
+        "else:\n",
+        "    CMDARGS = [\n",
+        "        \"--dataset-data-url=\" + DATASET_DIR + \"/iris_data.csv\",\n",
+        "        \"--dataset-labels-url=\" + DATASET_DIR + \"/iris_target.csv\",\n",
+        "        \"--boost-rounds=\" + str(ROUNDS),\n",
+        "    ]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_custom_job:mbsdk"
+      },
+      "source": [
+        "#### Run the custom training job\n",
+        "\n",
+        "Next, you run the custom job to start the training job by invoking the method `run`, with the following parameters:\n",
+        "\n",
+        "- `model_display_name`: The human readable name for the `Model` resource.\n",
+        "- `args`: The command-line arguments to pass to the training script.\n",
+        "- `replica_count`: The number of compute instances for training (replica_count = 1 is single node training).\n",
+        "- `machine_type`: The machine type for the compute instances.\n",
+        "- `accelerator_type`: The hardware accelerator type.\n",
+        "- `accelerator_count`: The number of accelerators to attach to a worker replica.\n",
+        "- `base_output_dir`: The Cloud Storage location to write the model artifacts to.\n",
+        "- `sync`: Whether to block until completion of the job."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "JCruQq1aox9Y"
+      },
+      "outputs": [],
+      "source": [
+        "if TRAIN_GPU:\n",
+        "    model = job.run(\n",
+        "        model_display_name=\"iris\",\n",
+        "        args=CMDARGS,\n",
+        "        replica_count=1,\n",
+        "        machine_type=TRAIN_COMPUTE,\n",
+        "        accelerator_type=TRAIN_GPU.name,\n",
+        "        accelerator_count=TRAIN_NGPU,\n",
+        "        base_output_dir=MODEL_DIR,\n",
+        "        sync=False,\n",
+        "    )\n",
+        "else:\n",
+        "    model = job.run(\n",
+        "        model_display_name=\"iris\",\n",
+        "        args=CMDARGS,\n",
+        "        replica_count=1,\n",
+        "        machine_type=TRAIN_COMPUTE,\n",
+        "        base_output_dir=MODEL_DIR,\n",
+        "        sync=False,\n",
+        "    )\n",
+        "\n",
+        "model_path_to_deploy = MODEL_DIR"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "list_job"
+      },
+      "source": [
+        "### List a custom training job"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "KBM_KLMSox9Y"
+      },
+      "outputs": [],
+      "source": [
+        "_job = job.list(filter=f\"display_name={DISPLAY_NAME}\")\n",
+        "print(_job)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "custom_job_wait:mbsdk"
+      },
+      "source": [
+        "### Wait for completion of custom training job\n",
+        "\n",
+        "Next, wait for the custom training job to complete. Alternatively, one can set the parameter `sync` to `True` in the `run()` method to block until the custom training job is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "lHPMHbSyox9Z"
+      },
+      "outputs": [],
+      "source": [
+        "model.wait()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "delete_job"
+      },
+      "source": [
+        "### Delete a custom training job\n",
+        "\n",
+        "After a training job is completed, you can delete the training job with the method `delete()`.  Prior to completion, a training job can be canceled with the method `cancel()`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tlYg7Sp-ox9Z"
+      },
+      "outputs": [],
+      "source": [
+        "job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "\n",
+        "- Custom Job (Custome Training job is remove in previous step)\n",
+        "- Cloud Storage Bucket"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "JyWy23gDox9a"
+      },
+      "outputs": [],
+      "source": [
+        "delete_bucket = True\n",
+        "\n",
+        "model.delete()\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "get_started_vertex_training_xgboost.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/custom/sdk-custom-image-classification-batch.ipynb

@@ -64,7 +64,7 @@
         "\n",
         "This tutorial demonstrates how to use the Vertex AI SDK for Python to train and deploy a custom image classification model for batch prediction.\n",
         "\n",
-        "Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training)  and [Vertex AI Batch Prediction](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions)."
+        "Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training) and [Vertex AI Batch Prediction](https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions)."
       ]
     },
     {

notebooks/official/custom/sdk-custom-image-classification-online.ipynb

@@ -64,7 +64,7 @@
         "\n",
         "This tutorial demonstrates how to use the Vertex AI SDK for Python to train and deploy a custom image classification model for online prediction.\n",
         "\n",
-        "Learn more about [Vertex AI Training](https://cloud.google.com/vertex-ai/docs/training/custom-training)  and [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions)."
+        "Learn more about [Custom training](https://cloud.google.com/vertex-ai/docs/training/custom-training) and [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions)."
       ]
     },
     {

notebooks/official/datasets/README.md

@@ -18,6 +18,8 @@ The steps performed include:
 
    Learn more about [BigQuery Datasets](https://cloud.google.com/bigquery/docs/datasets-intro).
 
+   Learn more about [Vertex AI for BigQuery users](https://cloud.google.com/vertex-ai/docs/beginner/bqml).
+
 
 [Get started with Vertex AI Data Labeling](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/datasets/get_started_with_data_labeling.ipynb)