fix: typo

.cloud-build/cleanup/cleanup.py

@@ -1,30 +1,10 @@
 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,
     EndpointResourceCleanupManager,
     ResourceCleanupManager,
-    MatchingEngineIndexEndpointResourceCleanupManager,
-    MatchingEngineIndexResourceCleanupManager,
-    FeatureStoreLegacyCleanupManager,
-    FeatureStoreCleanupManager,
-    PipelineJobCleanupManager,
-    TrainingJobCleanupManager,
-    HyperparameterTuningCleanupManager,
-    BatchPredictionJobCleanupManager,
-    ExperimentCleanupManager,
-    BucketCleanupManager,
-    ArtifactRegistryCleanupManager
 )
 
 rate_limit = RateLimit(max_count=25, per=60, greedy=False)
@@ -36,14 +16,12 @@ def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: boo
 
         print(f"Fetching {type_name}'s...")
         resources = manager.list()
-        try:
-            print(f"Found {len(resources)} {type_name}'s")
-        except Exception as e:
-            print(f"{type_name} {e}")
+        print(f"Found {len(resources)} {type_name}'s")
         for resource in resources:
             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}")
@@ -56,25 +34,16 @@ def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: boo
         print("")
 
 
-if args.dry_run:
+is_dry_run = False
+
+if is_dry_run:
     print("Starting cleanup in dry run mode...")
 
 # List of all cleanup managers
-managers: List[ResourceCleanupManager] = [
+managers = [
     DatasetResourceCleanupManager(),
     EndpointResourceCleanupManager(),
     ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
-    MatchingEngineIndexEndpointResourceCleanupManager(),
-    MatchingEngineIndexResourceCleanupManager(),
-    FeatureStoreLegacyCleanupManager(),
-    FeatureStoreCleanupManager(),
-    PipelineJobCleanupManager(),
-    TrainingJobCleanupManager(),
-    HyperparameterTuningCleanupManager(),
-    BatchPredictionJobCleanupManager(),
-    ExperimentCleanupManager(), # Experiment missing _resource_noun
-    BucketCleanupManager(),
-    ArtifactRegistryCleanupManager()
 ]
 
-run_cleanup_managers(managers=managers, is_dry_run=args.dry_run)
+run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -1,26 +1,10 @@
-'''
-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.aiplatform_v1beta1 import (FeatureOnlineStoreAdminServiceClient,
-                                             FeatureOnlineStore)
-from google.cloud import storage
 from proto.datetime_helpers import DatetimeWithNanoseconds
 
-PROJECT_ID = "python-docs-samples-tests"
-REGION = "us-central1"
-API_ENDPOINT = f"{REGION}-aiplatform.googleapis.com"
-
 # If a resource was updated within this number of seconds, do not delete.
 RESOURCE_UPDATE_BUFFER_IN_SECONDS = 60 * 60 * 8
 
@@ -85,7 +69,7 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
     def delete(self, resource):
         resource.delete()
 
-    def get_seconds_since_modification(self, resource: Any) -> float:
+    def get_seconds_since_modification(self, resource: Any) -> bool:
         update_time = resource.update_time
         current_time = DatetimeWithNanoseconds.now(tz=update_time.tzinfo)
         return (current_time - update_time).total_seconds()
@@ -113,193 +97,15 @@ 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)
 
 
 class ModelResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Model
-
-
-class MatchingEngineIndexResourceCleanupManager(VertexAIResourceCleanupManager):
-    vertex_ai_resource = aiplatform.MatchingEngineIndex
-
-
-class MatchingEngineIndexEndpointResourceCleanupManager(VertexAIResourceCleanupManager):
-    vertex_ai_resource = aiplatform.MatchingEngineIndexEndpoint
-
-    def delete(self, resource):
-        resource.undeploy_all()
-        resource.delete(force=True)
-
-class FeatureStoreLegacyCleanupManager(VertexAIResourceCleanupManager):
-    # TODO: only deleting legacy
-    #    not deleting ingestions jobs
-    #       ingest_from_xxx methods do not return a job ID, there is no list command, aka no python way to delete
-    #    not deleting batch serving jobs
-    #       batch_serve_to_xxx methods do not return a job ID, there is no list command, aka no python way to delete
-    vertex_ai_resource = aiplatform.Featurestore
-
-    def resource_name(self, resource: Any) -> str:
-        return resource.name
-
-    def delete(self, resource):
-        resource.delete(force=True)
-
-
-class FeatureStoreCleanupManager(VertexAIResourceCleanupManager):
-    # for FS 2.0
-    # TODO: use _v1beta1, and gapic clients
-    #    delete features, feature groups, feature views, feature online stores
-    vertex_ai_resource = FeatureOnlineStore
-
-    admin_client = FeatureOnlineStoreAdminServiceClient(
-        client_options={"api_endpoint": API_ENDPOINT}
-    )
-
-    def resource_name(self, resource: Any) -> str:
-        return resource.name
-
-    def type_name(self) -> str:
-        return "FeatureOnlineStore"
-
-    def list(self) -> Any:
-        try:
-            return self.admin_client.list_feature_online_stores(parent=f"projects/{PROJECT_ID}/locations/{REGION}")
-        except Exception as e:
-            print(e)
-            return []
-
-    def delete(self, resource):
-        try:
-            self.admin_client.delete_feature_online_store(name=resource.name, force=True)
-        except Exception as e:
-            print(e)
-
-
-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:
-        import subprocess
-
-        result = subprocess.run(["gcloud artifacts repositories list --location=us-central1"], 
-                                shell=True, capture_output=True, text=True)
-
-        ret = []
-        lines = result.stdout.split('\n')[2:]
-        for line in lines:
-            repo = line.split(' ')[0]
-            if repo.startswith("my-docker-repo"):
-                ret.append(repo)
-
-        return ret
-
-    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

@@ -17,8 +17,6 @@
 
 import argparse
 import pathlib
-import os
-import csv
 
 import execute_changed_notebooks_helper
 
@@ -38,22 +36,9 @@ parser = argparse.ArgumentParser(description="Run changed notebooks.")
 parser.add_argument(
     "--test_paths_file",
     type=pathlib.Path,
-    help="The path to the file that has newline-delimited folders of notebooks that should be tested.",
+    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.",
@@ -122,98 +107,24 @@ parser.add_argument(
     default=True,
     help="Should run notebooks in parallel.",
 )
-parser.add_argument(
-    "--concurrent_notebooks",
-    type=int,
-    help="Maximum number of parallel notebook executions per minute",
-    default=10,
-    required=False,
-)
-parser.add_argument(
-    "--run_first_file",
-    type=pathlib.Path,
-    help="The path to the file that has newline-delimited of notebooks to run in the first batch",
-    default=None,
-    required=False,
-)
-parser.add_argument(
-    "--aiplatform_whl",
-    type=str,
-    help="The GCS path to a whl version google-cloud-aiplatform",
-    default=None,
-    required=False,
-)
-parser.add_argument(
-    "--dry_run",
-    type=str2bool,
-    default=False,
-    help="Dry run for testing - no execution",
-)
 
 args = parser.parse_args()
 
-changed_notebooks = execute_changed_notebooks_helper.get_changed_notebooks(
+notebooks = execute_changed_notebooks_helper.get_changed_notebooks(
     test_paths_file=args.test_paths_file,
     base_branch=args.base_branch,
 )
 
-
-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)]
-    # cap the number of notebooks to the specified percentage
-    max_notebooks = int((len(changed_notebooks) * (args.test_percent/100)))
-    if (len(notebooks) > max_notebooks):
-        notebooks = notebooks[:max_notebooks]
-
-run_first = []
-if args.run_first_file:
-    if not os.path.isfile(args.run_first_file):
-        print("Error: file does not exist", args.run_first_file)
-    else:
-        with open(args.run_first_file, 'r') as csvfile:
-            reader = csv.reader(csvfile)
-            for row in reader:
-                notebook = row[0]
-                run_first.append(notebook)
-
-    for notebook in run_first:
-        if notebook in notebooks:
-            # remove from existing list
-            notebooks.remove(notebook)
-            # add back to the front of the list
-            notebooks.insert(0, notebook)
-            print(f"Run first: {notebook}")
-
-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,
-        concurrent_notebooks=args.concurrent_notebooks,
-        aiplatform_whl=args.aiplatform_whl
+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,
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -21,33 +21,24 @@ 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, Dict, Any
+from typing import List, Optional
 from utils import util
 
 import execute_notebook_helper
 import execute_notebook_remote
 import nbformat
 from google.cloud.devtools.cloudbuild_v1.types import BuildOperationMetadata
+from ratemate import RateLimit
 from tabulate import tabulate
 from utils import NotebookProcessors, util
 
 # A buffer so that workers finish before the orchestrating job
 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
-# maximum time since last run to force a run on the current build
-MAX_AGE_BEFORE_FORCE_RUN: int = (60 * 60) * 24 * 30
+PYTHON_VERSION = "3.9" # Set default python version
 
 
 def format_timedelta(delta: datetime.timedelta) -> str:
@@ -74,9 +65,7 @@ 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
@@ -92,97 +81,6 @@ 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']
-                    if accumulative_results[notebook]['last_time_ran'] < time_created:
-                        accumulative_results[notebook]['last_time_ran'] = time_created
-                else:
-                    accumulative_results[notebook] = build_results[notebook]
-                    accumulative_results[notebook]['failed_on_latest_run'] = build_results[notebook]['failed']
-                    accumulative_results[notebook]['last_time_ran'] = time_created
-
-        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']
-        failed_on_latest_run = accumulative_results[changed_notebook]['failed_on_latest_run']
-        last_time_ran = accumulative_results[changed_notebook]['last_time_ran']
-    else:
-        pass_count = 1
-        fail_count = 0
-        failed_on_latest_run = 0
-        last_time_ran = datetime.datetime.now().replace(tzinfo=None)
-
-    # If notebook has not been ran in a long time, force running it
-    if (datetime.datetime.now().replace(tzinfo=None) - last_time_ran).total_seconds() > MAX_AGE_BEFORE_FORCE_RUN:
-        should_test_do_to_age = True
-    else:
-        should_test_do_to_age  = False
-
-
-    # if failed on the last time it was ran, select the notebook
-    if failed_on_latest_run:
-        inferred_failure_rate = 1
-    # otherwise, calculate the frequency of failure
-    else:
-        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
-
-    #if accumulative_resultsi[changed_notebook]['latest_date_ran']
-
-    # 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 or should_test_do_to_age:
-        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,
@@ -204,7 +102,6 @@ def _process_notebook(
             "VPC_NETWORK": variable_vpc_network,
         },
     )
-    unique_strings_preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
 
     # Use no-execute preprocessor
     (
@@ -213,7 +110,6 @@ def _process_notebook(
     ) = remove_no_execute_cells_preprocessor.preprocess(nb)
 
     (nb, resources) = update_variables_preprocessor.preprocess(nb, resources)
-    (nb, resources) = unique_strings_preprocessor.preprocess(nb, resources)
 
     with open(notebook_path, mode="w", encoding="utf-8") as new_file:
         nbformat.write(nb, new_file)
@@ -231,15 +127,13 @@ def _get_notebook_python_version(notebook_path: str) -> str:
     src = file.read()
     nb_json = json.loads(src)
 
-    # Iterate over the cells in the ipynb
-    for cell in nb_json["cells"]:
-        if cell["cell_type"] == "markdown":
-            markdown = str.join("", cell["source"])
+    #Iterate over the cells in the ipynb
+    for cell in nb_json['cells']:
+        if cell['cell_type'] == 'markdown':
+            markdown = str.join('', cell['source'])
 
             # Look for the python version specification pattern
-            re_match = re.search(
-                r"python version = (\d+\.\d+)", markdown, flags=re.IGNORECASE
-            )
+            re_match = re.search('python version = (\d\.\d)', markdown, flags=re.IGNORECASE)
             if re_match:
                 # get the version number
                 python_version = re_match.group(1)
@@ -258,6 +152,7 @@ def _create_tag(filepath: str) -> str:
     return tag
 
 
+rate_limit = RateLimit(max_count=50, per=60, greedy=True)
 
 
 def process_and_execute_notebook(
@@ -271,8 +166,9 @@ def process_and_execute_notebook(
     private_pool_id: Optional[str],
     deadline: datetime.datetime,
     notebook: str,
-    should_get_tail_logs: bool = True,
+    should_get_tail_logs: bool = False,
 ) -> NotebookExecutionResult:
+    rate_limit.wait()  # wait before creating the task
 
     print(f"Running notebook: {notebook}")
 
@@ -291,9 +187,7 @@ 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="",
@@ -303,12 +197,11 @@ 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
-        notebook_exec_python_version = _get_notebook_python_version(
-            notebook_path=notebook
-        )
+        notebook_exec_python_version = _get_notebook_python_version(notebook_path=notebook)
         print(f"Running notebook with python {notebook_exec_python_version}")
 
         # Pre-process notebook by substituting variable names
@@ -337,7 +230,7 @@ def process_and_execute_notebook(
             private_pool_id=private_pool_id,
             private_pool_region=variable_region,
             timeout_in_seconds=timeout_in_seconds,
-            python_version=notebook_exec_python_version,
+            python_version=notebook_exec_python_version
         )
 
         operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
@@ -346,12 +239,11 @@ def process_and_execute_notebook(
         result.logs_bucket = operation_metadata.build.logs_bucket
 
         # Block and wait for the result
-        operation_result = operation.result(timeout=timeout_in_seconds)
+        operation_result = operation.result()
 
-        result.duration = datetime.datetime.now() - result.start_time
+        result.duration = datetime.datetime.now() - time_start
         result.is_pass = True
         print(f"{notebook} PASSED in {format_timedelta(result.duration)}.")
-
     except Exception as error:
         result.error_message = str(error)
 
@@ -365,12 +257,12 @@ def process_and_execute_notebook(
             # Use gcloud to get tail
             try:
                 result.error_message = subprocess.check_output(
-                    ["gcloud", "storage", "cat", "--range", "-1000", log_file_uri], encoding="UTF-8"
+                    ["gsutil", "cat", "-r", "-1000", log_file_uri], encoding="UTF-8"
                 )
             except Exception as error:
                 result.error_message = str(error)
 
-        result.duration = datetime.datetime.now() - result.start_time
+        result.duration = datetime.datetime.now() - time_start
         result.is_pass = False
 
         print(
@@ -438,68 +330,12 @@ 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
-        if result.error_message is None:
-            error_type = ''
-        elif '500 Internal' in result.error_message or 'INTERNAL' in result.error_message or 'internal error' in result.error_message:
-            error_type = 'INTERNAL'
-        elif 'context deadline exceeded' in result.error_message or 'TIMEOUT' in result.error_message:
-            error_type = 'TIMEOUT'
-        elif 'Quota' in result.error_message or 'quotas are exceeded' in result.error_message:
-            error_type = 'QUOTA'
-        elif 'ServiceUnavailable' in result.error_message:
-            error_type = 'SERVICEUNAVAILABLE'
-        elif 'ModuleNotFoundError' in result.error_message:
-            error_type = 'IMPORT'
-        elif result.is_pass:
-            error_type = ''
-        else:
-            error_type = 'undetermined'
-
-        if error_type != '':
-            log_url = result.log_url
-        else:
-            log_url = ''
-
-        build_results[result.path] = {
-                'duration': result.duration.total_seconds(),
-                'start_time': str(result.start_time),
-                'passed': pass_count,
-                'failed': fail_count,
-                'error_type': error_type,
-                'log_url': log_url
-        }
-        print(f"adding {result.path}")
-
-    print(f"Saving accumulative results to {results_file}, nentries {len(build_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,
@@ -507,8 +343,6 @@ def process_and_execute_notebooks(
     variable_service_account: str,
     variable_vpc_network: Optional[str] = None,
     private_pool_id: Optional[str] = None,
-    concurrent_notebooks: Optional[int] = 10,
-    aiplatform_whl: Optional[str] = None,
 ):
     """
     Run the notebooks that exist under the folders defined in the test_paths_file.
@@ -529,8 +363,6 @@ 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):
@@ -539,8 +371,6 @@ def process_and_execute_notebooks(
             Required. Should run notebooks in parallel using a thread pool as opposed to in sequence.
         timeout (str):
             Required. Timeout string according to https://cloud.google.com/build/docs/build-config-file-schema#timeout.
-        concurrent_notebooks (int): Max number of notebooks per minute to run in parallel.
-        aiplatform_whl: alternate whl version of Vertex AI SDK to install
     """
 
     # Calculate deadline
@@ -557,9 +387,7 @@ def process_and_execute_notebooks(
             print(
                 "Running notebooks in parallel, so no logs will be displayed. Please wait..."
             )
-
-
-            with concurrent.futures.ThreadPoolExecutor(max_workers=concurrent_notebooks) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
                 print(f"Max workers: {executor._max_workers}")
 
                 notebook_execution_results = list(
@@ -615,7 +443,7 @@ def process_and_execute_notebooks(
                         result.log_url,
                         result.output_uri,
                         result.output_uri_web,
-                        result.logs_bucket,
+                        result.logs_bucket
                     ]
                     for result in results_sorted
                 ],
@@ -626,38 +454,34 @@ def process_and_execute_notebooks(
                     "log_url",
                     "output_uri",
                     "output_uri_web",
-                    "logs_bucket",
+                    "logs_bucket"
                 ],
             )
         )
 
         if len(notebooks) == 1:
-            print("=" * 100)
-            print("The notebook execution build log:\n")
-            print("=" * 100)
+          print("="*100)
+          print("The notebook execution build log:\n")
+          print("="*100)
 
-            build_id = results_sorted[0].build_id
-            logs_bucket_name = (results_sorted[0].logs_bucket).replace("gs://", "")
-            log_file_name = f"log-{build_id}.txt"
+          build_id = results_sorted[0].build_id
+          logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
+          log_file_name = f"log-{build_id}.txt"
 
-            log_contents = util.download_blob_into_memory(
-                bucket_name=logs_bucket_name,
-                blob_name=log_file_name,
-                download_as_text=True,
+          log_contents = util.download_blob_into_memory(
+            bucket_name=logs_bucket_name,
+            blob_name=log_file_name,
+            download_as_text=True
             )
 
-            # Remove extra steps from the log
-            match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
+          # Remove extra steps from the log
+          match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
 
-            if match is not None:
-                match_index = match.span()[0]
-                print(log_contents[match_index:])
-            else:
-                print(log_contents)
-
-        _save_results(results_sorted, 
-                      artifacts_bucket, 
-                      results_file)
+          if match is not None:
+            match_index = match.span()[0]
+            print(log_contents[match_index:])
+          else:
+            print(log_contents)
 
         print("\n=== END RESULTS===\n")
 

.cloud-build/execute_notebook_helper.py

@@ -56,8 +56,8 @@ def execute_notebook(
     print("\n=== DOWNLOAD EXECUTED NOTEBOOK ===\n")
     print(f"Please debug the executed notebook by downloading the executed notebook:")
 
-    print("Option 1. Using gcloud storage. Run the following command in your terminal.")
-    print(f'\tgcloud storage cp "{output_file_or_uri}" .')
+    print("Option 1. Using gsutil. Run the following command in your terminal.")
+    print(f'\tgsutil cp "{output_file_or_uri}" .')
 
     print("Option 2. Using this link.")
     print(f"\thttps://storage.googleapis.com/{output_file_or_uri[5:]}")

.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 ${_GCP_SERVICE_ACCOUNT} --variable_vpc_network "${_GCP_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} --concurrent_notebooks=${_CONCURRENT_NOTEBOOKS} --run_first_file=${_RUN_FIRST_FILE}
+      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`
     env:
     - 'IS_TESTING=1'
 timeout: 86400s

.cloud-build/requirements.txt

@@ -3,15 +3,11 @@ numpy
 jupyter
 nbconvert
 papermill
+pandas
 matplotlib
 tabulate
 google-cloud-aiplatform
 google-cloud-storage
 google-cloud-build
-google-cloud-storage
 ratemate
-GitPython
-tqdm
-fsspec
-pandas
-
+GitPython

.cloud-build/run_first.csv

@@ -1,8 +0,0 @@
-notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb
-notebooks/official/generative_ai/rlhf_tune_llm.ipynb
-notebooks/official/generative_ai/tune_peft.ipynb
-notebooks/official/prediction/llm_streaming_prediction.ipynb
-notebooks/official/migration/sdk-automl-text-classification-batch-prediction.ipynb
-notebooks/official/vizier/get_started_vertex_vizier.ipynb
-notebooks/official/workbench/sentiment_analysis/Sentiment_Analysis.ipynb
-notebooks/official/model_monitoring/get_started_with_model_monitoring_automl.ipynb

.cloud-build/test_notebook_vm.txt

@@ -1,3 +1,6 @@
+notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb
+notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb
 notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb
 notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb
+notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb
 .cloud-build/tests/python_version_test.ipynb

.cloud-build/tests/flaky.py

@@ -1,46 +0,0 @@
-# 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

@@ -1,33 +0,0 @@
-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/NotebookProcessors.py

@@ -14,8 +14,6 @@
 # limitations under the License.
 
 from typing import Dict
-import random
-import string
 
 from nbconvert.preprocessors import Preprocessor
 
@@ -35,7 +33,7 @@ class RemoveNoExecuteCells(Preprocessor):
 
 
 class UpdateVariablesPreprocessor(Preprocessor):
-    def __init__(self, replacement_map: Dict[str, str]):
+    def __init__(self, replacement_map: Dict):
         self._replacement_map = replacement_map
 
     @staticmethod
@@ -65,61 +63,3 @@ class UpdateVariablesPreprocessor(Preprocessor):
             executable_cells.append(cell)
         notebook.cells = executable_cells
         return notebook, resources
-
-
-# Generate a uuid of a specifed length
-def generate_uuid(length: int = 8) -> str:
-    return "".join(random.choices(string.ascii_lowercase + string.digits, k=length))
-
-
-class UniqueStringsPreprocessor(Preprocessor):
-    # A preprocessor that replaces strings that end with "-unique" or "_unique" with a uuid.
-
-    @staticmethod
-    def update_unique_strings(content: str):
-        # Replace strings that end with "-unique" or "_unique" with a uuid.
-
-        unique_id = generate_uuid()
-        return (
-            content.replace('-unique"', f'-{unique_id}"')
-            .replace("-unique'", f'-{unique_id}"')
-            .replace('_unique"', f'_{unique_id}"')
-            .replace("_unique'", f'_{unique_id}"')
-        )
-
-    def preprocess(self, notebook, resources=None):
-        executable_cells = []
-        for cell in notebook.cells:
-            if cell.cell_type == "code":
-                cell.source = self.update_unique_strings(
-                    content=cell.source,
-                )
-
-            executable_cells.append(cell)
-        notebook.cells = executable_cells
-        return notebook, resources
-
-class VertexAIInstallProprocessor(Preprocessor):
-    def __init__(self, vertex_ai_wheel):
-        self.vertex_ai_wheel = vertex_ai_wheel
-
-    @staticmethod
-    def update_vertex_ai_install(content: str):
-        if "google-cloud-aiplatform" not in content:
-            return content
-        return (
-            f"gcloud storage cp {self.vertex_ai_wheel} google-cloud-aiplatform.whl\n" + 
-            content.replace("google-cloud-aiplatform\n", "google-cloud-aiplatform.whl\n")
-            .replace("google-cloud-aiplatform ", "google-cloud-aiplatform.whl ")
-        )
-
-    def preprocess(self, notebook, resources=None):
-        executable_cells = []
-        for cell in notebook.cells:
-            if cell.cell_type == "code":
-                cell.source = self.update_vertex_ai_install(
-                    content=cell.source,
-                )
-
-            executable_cells.append(cell)
-        notebook.cells = executable_cells

.cloud-build/utils/UpdateNotebookVariables.py

@@ -40,3 +40,65 @@ def get_updated_value(content: str, variable_name: str, variable_value: str) ->
         content,
         flags=re.M,
     )
+
+
+def test_update_value():
+    new_content = get_updated_value(
+        content='asdf\nPROJECT_ID = "[your-project-id]" #@param {type:"string"} \nasdf',
+        variable_name="PROJECT_ID",
+        variable_value="sample-project",
+    )
+    assert (
+        new_content
+        == 'asdf\nPROJECT_ID = "sample-project" #@param {type:"string"} \nasdf'
+    )
+
+
+def test_update_value_single_quotes():
+    new_content = get_updated_value(
+        content="PROJECT_ID = '[your-project-id]'",
+        variable_name="PROJECT_ID",
+        variable_value="sample-project",
+    )
+    assert new_content == "PROJECT_ID = 'sample-project'"
+
+
+def test_update_value_avoidance():
+    new_content = get_updated_value(
+        content="PROJECT_ID = shell_output[0] ",
+        variable_name="PROJECT_ID",
+        variable_value="sample-project",
+    )
+    assert new_content == "PROJECT_ID = shell_output[0] "
+
+
+def test_region():
+    new_content = get_updated_value(
+        content='REGION = "[your-region]"  # @param {type:"string"}',
+        variable_name="REGION",
+        variable_value="us-central1",
+    )
+    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'
+
+
+def test_region_equal_equals_ignore():
+    # Tests that == is ignored
+    new_content = get_updated_value(
+        content='REGION == "[your-region]"  # @param {type:"string"}',
+        variable_name="REGION",
+        variable_value="us-central1",
+    )
+    assert new_content == 'REGION == "[your-region]"  # @param {type:"string"}'
+
+
+def test_service_account():
+    # Tests that == is ignored
+    new_content = get_updated_value(
+        content='SERVICE_ACCOUNT = "[your-service-account]"  # @param {type:"string"}',
+        variable_name="SERVICE_ACCOUNT",
+        variable_value="12345-compute@developer.gserviceaccount.com",
+    )
+    assert (
+        new_content
+        == 'SERVICE_ACCOUNT = "12345-compute@developer.gserviceaccount.com"  # @param {type:"string"}'
+    )

.cloud-build/utils/build_results_viewer.py

@@ -1,73 +0,0 @@
-'''
-Viewer for the weekly regression testing of the official notebooks
-
-Cloud Storage location: gs://cloud-build-notebooks-presubmit/build_results/
-'''
-import argparse
-import json
-from  util import download_file
-import csv
-import datetime
-from google.cloud import storage
-
-BUILD_BUCKET = "cloud-build-notebooks-presubmit"
-BUILD_FOLDER = "build_results"
-
-
-parser = argparse.ArgumentParser()
-parser.add_argument('--file', dest='file',
-                    default=None, type=str, help='build results filei (local or GCS)')
-args = parser.parse_args()
-
-investigate = {}
-with open('investigate.csv', 'r') as csvfile:
-    reader = csv.reader(csvfile)
-    for row in reader:
-        investigate[row[0][:-6]] = row[1]
-
-if not args.file:
-    client = storage.Client()
-    blobs = client.list_blobs(BUILD_BUCKET, prefix=BUILD_FOLDER)
-    newest_time = datetime.datetime(2000, 1, 1)
-    for blob in blobs:
-        # individual PR
-        if blob.size < 2000:
-            continue
-        time_created = blob.time_created.replace(tzinfo=None)
-        if time_created > newest_time:
-            newest_time = time_created
-            args.file = f"gs://{BUILD_BUCKET}/{blob.name}"
-
-if args.file.startswith("gs://"):
-    path = args.file[5:]
-    bucket = path.split('/')[0]
-    file   = path[len(bucket)+1:]
-    download_file(bucket, file, "build.json")
-    args.file = "build.json"
-
-with open(args.file, 'r') as f:
-    results = json.load(f)
-
-for item in results.items():
-    notebook = item[0][len("/notebooks/official/")-1:-6]
-    if item[1]['passed']:
-        passed = "PASS"
-    else:
-        if notebook in investigate:
-            passed = "INVG"
-        else:
-            passed = "FAIL"
-      
-    error = item[1]['error_type']
-  
-    if passed == "FAIL":
-        if error == '':
-            error = "undetermined"
-        if 'log_url' in item[1]:
-            log_url = item[1]['log_url']
-        else:
-            log_url = ''
-    else:
-        log_url = ''
-
-    print(f"{notebook:75} {passed} {error:10} {log_url}")

.cloud-build/utils/investigate.csv

@@ -1,19 +0,0 @@
-notebook,status
-prediction/llm_streaming_prediction.ipynb,wait_for_fix
-custom/get_started_with_vertex_endpoint_and_shared_vm.ipynb,issue 2527
-feature_store/online_feature_serving_and_fetching_bigquery_data_with_feature_store.ipynb,wait_for_reaper
-feature_store/online_feature_serving_and_vector_retrieval_bigquery_data_with_feature_store.ipynb,wait_for_reaper
-pipelines/google_cloud_pipeline_components_TPU_model_train_upload_deploy.ipynb,wait_for_fix
-explainable_ai/sdk_custom_image_classification_batch_explain.ipynb,issue 2528
-explainable_ai/sdk_custom_image_classification_online_explain.ipynb,issue 2528
-explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb,issue 2528
-explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb,issue 2528
-explainable_ai/xai_image_classification_feature_attributions.ipynb,issue 2528
-matching_engine,sdk_matching_engine_create_stack_overflow_embeddings.ipynb,issue 2530
-automl/automl_forecasting_bqml_arima_plus_comparison.ipynb,flaky
-model_evaluation/custom_tabular_regression_model_evaluation.ipynb,regr
-experiments/get_started_with_vertex_experiments.ipynb,regr
-experiments/comparing_local_trained_models.ipynb,regr
-generative_ai/tune_peft.ipynb,internal
-pipelines/custom_model_training_and_batch_prediction.ipynb,regr
-feature_store/online_feature_serving_and_fetching_bigquery_data_with_feature_store_optimized.ipynb,wait_for_reaper

.cloud-build/utils/tests/test_preprocessors.py

@@ -1,14 +0,0 @@
-from utils import NotebookProcessors
-
-
-def test_update_value():
-    # Test that the content was updated
-    preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
-
-    content = 'PROJECT_ID = "your-project-id-unique"'
-
-    new_content = preprocessor.update_unique_strings(content)
-
-    assert new_content != content
-    assert new_content.startswith('PROJECT_ID = "your-project-id-')
-    assert new_content.endswith('"')

.cloud-build/utils/tests/test_update_notebook_variables.py

@@ -1,63 +0,0 @@
-from utils import UpdateNotebookVariables
-
-
-def test_update_value():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='asdf\nPROJECT_ID = "[your-project-id]" #@param {type:"string"} \nasdf',
-        variable_name="PROJECT_ID",
-        variable_value="sample-project",
-    )
-    assert (
-        new_content
-        == 'asdf\nPROJECT_ID = "sample-project" #@param {type:"string"} \nasdf'
-    )
-
-
-def test_update_value_single_quotes():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content="PROJECT_ID = '[your-project-id]'",
-        variable_name="PROJECT_ID",
-        variable_value="sample-project",
-    )
-    assert new_content == "PROJECT_ID = 'sample-project'"
-
-
-def test_update_value_avoidance():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content="PROJECT_ID = shell_output[0] ",
-        variable_name="PROJECT_ID",
-        variable_value="sample-project",
-    )
-    assert new_content == "PROJECT_ID = shell_output[0] "
-
-
-def test_region():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='REGION = "[your-region]"  # @param {type:"string"}',
-        variable_name="REGION",
-        variable_value="us-central1",
-    )
-    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'
-
-
-def test_region_equal_equals_ignore():
-    # Tests that == is ignored
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='REGION == "[your-region]"  # @param {type:"string"}',
-        variable_name="REGION",
-        variable_value="us-central1",
-    )
-    assert new_content == 'REGION == "[your-region]"  # @param {type:"string"}'
-
-
-def test_service_account():
-    # Tests that == is ignored
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='SERVICE_ACCOUNT = "[your-service-account]"  # @param {type:"string"}',
-        variable_name="SERVICE_ACCOUNT",
-        variable_value="12345-compute@developer.gserviceaccount.com",
-    )
-    assert (
-        new_content
-        == 'SERVICE_ACCOUNT = "12345-compute@developer.gserviceaccount.com"  # @param {type:"string"}'
-    )

.cloud-build/utils/util.py

@@ -15,7 +15,7 @@ def download_file(bucket_name: str, blob_name: str, destination_file: str) -> st
     remote_file_path = "".join(["gs://", "/".join([bucket_name, blob_name])])
 
     subprocess.check_output(
-        ["gcloud", "storage", "cp", remote_file_path, destination_file], encoding="UTF-8"
+        ["gsutil", "cp", remote_file_path, destination_file], encoding="UTF-8"
     )
 
     return destination_file
@@ -27,7 +27,7 @@ def upload_file(
 ) -> str:
     """Copies a local file to a GCS path"""
     subprocess.check_output(
-        ["gcloud", "storage", "cp", local_file_path, remote_file_path], encoding="UTF-8"
+        ["gsutil", "cp", local_file_path, remote_file_path], encoding="UTF-8"
     )
 
     return remote_file_path
@@ -61,7 +61,9 @@ def archive_code_and_upload(staging_bucket: str):
 
 
 def download_blob_into_memory(
-    bucket_name: str, blob_name: str, download_as_text: Optional[bool] = False
+  bucket_name: str,
+  blob_name: str,
+  download_as_text: Optional[bool]=False
 ) -> Union[bytes, str]:
     """
     Downloads a blob into memory as byte or as text if
@@ -77,10 +79,13 @@ def download_blob_into_memory(
 
     # Download the blob content
     if download_as_text:
-        contents = blob.download_as_text()
+      contents = blob.download_as_text()
     else:
-        contents = blob.download_as_bytes()
+      contents = blob.download_as_bytes()
 
-    print(f"Downloaded storage object {blob_name} from bucket {bucket_name}.")
+    print(
+        f"Downloaded storage object {blob_name} from bucket {bucket_name}."
+    )
 
     return contents
+

.cloud-build/web-index/do_not_index.txt

@@ -1,11 +0,0 @@
-sdk2_remote_tabnet_training.ipynb
-remote_hyperparameter_tuning.ipynb
-remote_prediction.ipynb
-remote_training_bigframes_pytorch.ipynb
-remote_training_bigframes_sklearn.ipynb
-remote_training_bigframes_tensorflow.ipynb
-remote_training_lightning.ipynb
-remote_training_pytorch.ipynb
-remote_training_sklearn.ipynb
-remote_training_tensorflow_with_autologging.ipynb
-

.cloud-build/web-index/notebook-index-cloudbuild.yaml

@@ -1,23 +0,0 @@
-steps:
-  # Fetch full repo for diff purposes
-  - name: gcr.io/cloud-builders/git
-    args: [fetch, --unshallow, --quiet]
-  # Create a virtual environment
-  - name: ${_PYTHON_IMAGE}
-    entrypoint: /bin/sh
-    args:
-    - -c
-    - python3 -m venv workspace/env
-  # Install Python dependencies and run testing script
-  - name: ${_PYTHON_IMAGE}
-    entrypoint: /bin/sh
-    args:
-    - -c
-    - |
-      . workspace/env/bin/activate &&
-      python3 notebooks/notebook_template_review.py --web --title --steps --desc --linkback --notebook-dir=notebooks/official --skip-file=${_DO_NOT_INDEX_FILE} >web.html
-artifacts:
-  objects:
-          location: gs://${_GCS_ARTIFACTS_BUCKET}/webdoc
-          paths: ['web.html']
-timeout: 86400s

.github/dependabot.yml

@@ -1,10 +0,0 @@
-version: 2
-updates:
-
-  # Ignore model garden dockerfiles:
-  - package-ecosystem: "npm"
-    directory: "/community-content/vertex_model_garden"
-    schedule:
-      interval: "monthly"
-    ignore:
-      - dependency-name: "*"

.github/workflows/ci.yaml

@@ -7,11 +7,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Set up Python
-      uses: actions/setup-python@v6
+      uses: actions/setup-python@v4
       with:
-        python-version: '3.12'      
+        python-version: '3.x'      
     - name: Fetch pull request branch
-      uses: actions/checkout@v6
+      uses: actions/checkout@v3
       with:
         fetch-depth: 0      
     - name: Fetch base main branch

.github/workflows/linter/Dockerfile

@@ -4,7 +4,7 @@
 # 2. To lint specific notebooks:
 # docker run -v ${PWD}:/setup/app gcr.io/python-docs-samples-tests/notebook_linter:latest notebooks/1.ipynb notebooks/2.ipynb
 
-FROM python:3.14
+FROM python:3.10
 
 WORKDIR setup
 

.github/workflows/linter/requirements.txt

@@ -2,9 +2,9 @@ git+https://github.com/tensorflow/docs
 ipython
 jupyter
 nbconvert
-black==25.12.0
-pyupgrade==3.21.2
-isort==7.0.0
-flake8==7.3.0
-nbqa==1.9.1
+black==22.6.0
+pyupgrade==2.34.0
+isort==5.10.1
+flake8==4.0.1
+nbqa==1.4.0
 

.github/workflows/linter/run_linter.sh

@@ -58,7 +58,7 @@ done
 # Only check notebooks in test folders modified in this pull request.
 # Note: Use process substitution to persist the data in the array
 if [ ${#notebooks[@]} -eq 0 ]; then
-    echo "Checking for changed notebooks using git"
+    echo "Checking for changed notebooked using git"
     while read -r file || [ -n "$line" ]; do
         notebooks+=("$file")
     done < <(git diff --name-only main... | grep '\.ipynb$')
@@ -84,7 +84,7 @@ if [ ${#notebooks[@]} -gt 0 ]; then
                 # python3 -m nbqa black "$notebook" --check
                 # BLACK_RTN=$?
                 echo "Running pyupgrade..."
-                python3 -m nbqa pyupgrade --exit-zero-even-if-changed "$notebook"
+                python3 -m nbqa pyupgrade "$notebook"
                 PYUPGRADE_RTN=$?
                 echo "Running isort..."
                 python3 -m nbqa isort "$notebook" --check
@@ -97,7 +97,7 @@ if [ ${#notebooks[@]} -gt 0 ]; then
                 python3 -m nbqa black "$notebook"
                 BLACK_RTN=$?
                 echo "Running pyupgrade..."
-                python3 -m nbqa pyupgrade --exit-zero-even-if-changed "$notebook"
+                python3 -m nbqa pyupgrade "$notebook"
                 PYUPGRADE_RTN=$?
                 echo "Running isort..."
                 python3 -m nbqa isort "$notebook"

CONTRIBUTING.md

@@ -44,10 +44,12 @@ 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
-docker run -v ${PWD}:/setup/app gcr.io/cloud-devrel-public-resources/notebook_linter:latest your_notebook
+nbqa black "$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"
 ```
 
 ## Code Reviews

README.md

@@ -1,176 +1,37 @@
-# ![Google Cloud](https://avatars.githubusercontent.com/u/2810941?s=60&v=4) Google Cloud Vertex AI Samples
+# Google Cloud Vertex AI Samples
 
-This repository contains notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage machine learning and generative AI workflows using Google Cloud Vertex AI.
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
+
+Welcome to the Google Cloud [Vertex AI](https://cloud.google.com/vertex-ai/docs/) sample repository.
 
 ## Overview
 
-[Vertex AI](https://cloud.google.com/vertex-ai) is a fully-managed, unified AI development platform for building and using generative AI. This repository is designed to help you get started with Vertex AI. Whether you're new to Vertex AI or an experienced ML practitioner, you'll find valuable resources here.
-
-For more Vertex AI Generative AI notebook samples, please visit the Vertex AI [Generative AI](https://github.com/GoogleCloudPlatform/generative-ai) GitHub repository.
-
-## Explore, learn and contribute
-
-You can explore, learn, and contribute to this repository to unleash the full potential of machine learning on Vertex AI! 
-
-### Explore and learn
-
-Explore this repository, follow the links in the header section of each of the notebooks to -
-
-![Colab](https://cloud.google.com/ml-engine/images/colab-logo-32px.png)  Open and run the notebook in [Colab](https://colab.google/)\
-![Colab Enterprise](https://cloud.google.com/ml-engine/images/colab-enterprise-logo-32px.png)  Open and run the notebook in [Colab Enterprise](https://cloud.google.com/colab/docs/introduction)\
-![Workbench](https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32)  Open and run the notebook in [Vertex AI Workbench](https://cloud.google.com/vertex-ai/docs/workbench/introduction)\
-![Github](https://cloud.google.com/ml-engine/images/github-logo-32px.png)  View the notebook on Github
-
-### Contribute
-
-See the [Contributing Guide](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/CONTRIBUTING.md).
-
-## Get started
-
-To get started using Vertex AI, you must have a Google Cloud project. 
-
-- If you don't have a Google Cloud project, you can learn and build on GCP for free using [Free Trail](https://cloud.google.com/free).
-- Once you have a Google Cloud project, you can learn more about [setting up a project and a development environment](https://cloud.google.com/vertex-ai/docs/start/cloud-environment).
-
+The repository contains [notebooks](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks) and [community content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/community-content) that demonstrate how to develop and manage ML workflows using Google Cloud Vertex AI.
 
 ## Repository structure
 
 ```bash
+├── community-content - Sample code and tutorials contributed by the community
 ├── notebooks
+│   ├── community - Notebooks contributed by the community
 │   ├── official - Notebooks demonstrating use of each Vertex AI service
 │   │   ├── automl
 │   │   ├── custom
 │   │   ├── ...
-│   ├── community - Notebooks contributed by the community
-│   │   ├── model_garden
-│   │   ├── ...
-├── community-content - Sample code and tutorials contributed by the community
-
 ```
-## Examples
 
-<!-- markdownlint-disable MD033 -->
-<table>
+## Contributing
 
-  <tr>
-    <th style="text-align: center;">Category</th>
-    <th style="text-align: center;">Product</th>
-    <th style="text-align: center;">Description</th>
-  </tr>
-  <tr>
-    <td>Model</td>
-    <td>
-      <a href="notebooks/community/model_garden"><code>Model Garden/</code></a>
-    </td>
-    <td>
-      Curated collection of first-party, open-source, and third-party models available on Vertex AI including Gemini, Gemma, Llama 3, Claude 3 and many more.
-    </td>
-  </tr>
-  <tr>
-    <td>Data</td>
-    <td>
-      <a href="notebooks/official/feature_store"><code>Feature Store/</code></a>
-    </td>
-    <td>
-      Set up and manage online serving using Vertex AI Feature Store.
-    </td>
-  </tr>
-  <tr>
-    <td></td>
-    <td>
-      <a href="notebooks/official/datasets"><code>datasets/</code></a>
-    </td>
-    <td>
-      Use BigQuery and Data Labeling service with Vertex AI.
-    </td>
-  </tr>
-  <tr>
-    <td>Model development</td>
-    <td>
-      <a href="notebooks/official/automl"><code>automl/</code></a>
-    </td>
-    <td>
-      Train and make predictions on AutoML models
-    </td>
-  </tr>
-  <tr>
-    <td></td>
-    <td>
-      <a href="notebooks/official/custom"><code>custom/</code></a>
-    </td>
-    <td>
-      Create, deploy and serve custom  models on Vertex AI
-    </td>
-  </tr>
-  <tr>
-    <td></td>
-    <td>
-      <a href="notebooks/official/ray_on_vertex_ai"><code>ray_on_vertex_ai/</code></a>
-    </td>
-    <td>
-      Use Colab Enterprise and Vertex AI SDK for Python to connect to the Ray Cluster.
-    </td>
-  </tr>
-  <tr>
-    <td>Deploy and use</td>
-    <td>
-      <a href="notebooks/official/prediction"><code>prediction/</code></a>
-    </td>
-    <td>
-      Build, train and deploy models using prebuilt containers for custom training and prediction.
-    </td>
-  </tr>
-  <tr>
-    <td></td>
-    <td>
-      <a href="notebooks/official/model_registry"><code>model_registry/</code></a>
-    </td>
-    <td>
-      Use Model Registry to create and register a model.
-    </td>
-  </tr>
-  <tr>
-    <td></td>
-    <td>
-      <a href="notebooks/official/explainable_ai"><code>Explainable AI/</code></a>
-    </td>
-    <td>
-      Use Vertex Explainable AI's feature-based and example-based explanations to explain how or why a model produced a specific prediction.
-    </td>
-  </tr>
-  <tr>
-    <td></td>
-    <td>
-      <a href="notebooks/official/ml_metadata"><code>ml_metadata/</code></a>
-    </td>
-    <td>
-      Record the metadata and artifacts and query that metadata to help analyze, debug, and audit the performance of your ML system.
-    </td>
-  </tr>
-  <tr>
-    <td>Tools</td>
-    <td>
-      <a href="notebooks/official/pipelines"><code>Pipelines/</code></a>
-    </td>
-    <td>
-      Use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build, tune, or deploy a custom model.
-    </td>
-  </tr>
-</table>
-<!-- markdownlint-enable MD033 -->
+Contributions welcome! See the [Contributing Guide](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/CONTRIBUTING.md).
 
+## Getting help
 
-## Get help
-
-Please use the [Issues page](https://github.com/GoogleCloudPlatform/vertex-ai-samples/issues) to provide feedback or submit a bug report.
+Please use the [issues page](https://github.com/GoogleCloudPlatform/vertex-ai-samples/issues) to provide feedback or submit a bug report.
 
 ## Disclaimer
 
 This is not an officially supported Google product. The code in this repository is for demonstrative purposes only.
 
+## Feedback
 
-## References
-- [Vertex AI Jupyter Notebook tutorials](https://cloud.google.com/vertex-ai/docs/tutorials/jupyter-notebooks)
-- Vertex AI [Generative AI](https://github.com/GoogleCloudPlatform/generative-ai) GitHub repository
-- [Vertex AI documentaton](https://cloud.google.com/vertex-ai/docs)
-  
+Please feel free to fill out our [survey](https://bit.ly/vertex-ai-samples-survey) to give us feedback on the repo and its content.

community-content/CODEOWNERS

@@ -7,27 +7,3 @@
 /pluto_on_workbench @wkharold
 /cpr-examples @samthrasher
 /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
-/vertex_model_garden/model_oss/notebook_util @minwoo33park
-/vertex_model_garden/model_oss/util @weigary
-/vertex_model_garden/model_oss/diffusers @weigary
-/vertex_model_garden/model_oss/keras @dstnluong-google
-/vertex_model_garden/model_oss/transformers @dstnluong-google
-/vertex_model_garden/model_oss/pic2word @jismailyan-google
-/vertex_model_garden/model_oss/open_clip @lydhr
-/vertex_model_garden/model_oss/movinet @KCFindstr
-/vertex_model_garden/model_oss/data_converter @KCFindstr
-/vertex_model_garden/model_oss/peft @weigary
-/vertex_model_garden/model_oss/peft/templates @rayandasoriya
-/vertex_model_garden/model_oss/lm-evaluation-harness @kathyyu-google
-/vertex_model_garden/model_oss/tfvision @dstnluong-google
-/vertex_model_garden/model_oss/fvlm @minwoo33park
-/vertex_model_garden/model_oss/imagebind @kathyyu-google
-/vertex_model_garden/model_oss/llava @py4
-/vertex_model_garden/model_oss/vllm @kathyyu-google
-/vertex_model_garden/benchmarking_reports @lavraicse
-/vertex_model_garden/model_oss/autogluon @lavraicse
-/vertex_distributed_training/a3mega/llama-3-8b-nemo-pretraining @mstyer-google @erwinh85 @mchrestkha
-

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_logistic_regression_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.py

@@ -2,13 +2,13 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-train_logistic_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+train_logistic_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/cb44b75c9c062fcc40c2b905b2024b4493dbc62b/components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml")
+upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_classification_logistic_regression_model_using_Scikit_learn_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.py

@@ -2,15 +2,15 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
+create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
+upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_classification_model_using_PyTorch_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.py

@@ -2,16 +2,16 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
+create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
+predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml")
+upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_classification_model_using_TensorFlow_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.py

@@ -2,15 +2,15 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/d5c9918850a6cc70004c4269dae066cfe2e664eb/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
+train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_classification_model_using_XGBoost_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.py

@@ -2,36 +2,36 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
 
 # TensorFlow
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
+create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
+predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml")
+upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # PyTorch
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
+create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
+upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # XGBoost
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/d5c9918850a6cc70004c4269dae066cfe2e664eb/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
+train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # Scikit-learn
-#train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
-train_logistic_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
+#train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
+train_logistic_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/cb44b75c9c062fcc40c2b905b2024b4493dbc62b/components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml")
+upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # Vertex AI
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_classification_model_using_all_frameworks_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_linear_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.py

@@ -2,12 +2,12 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
+upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_regression_linear_model_using_Scikit_learn_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.py

@@ -2,14 +2,14 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
+create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
+upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_regression_model_using_PyTorch_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.py

@@ -2,15 +2,15 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
+create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
+predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml")
+upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_regression_model_using_Tensorflow_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.py

@@ -2,14 +2,14 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/d5c9918850a6cc70004c4269dae066cfe2e664eb/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
+train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_regression_model_using_XGBoost_pipeline():

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.py

@@ -2,34 +2,34 @@
 from kfp import components
 
 # %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
+download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml")
+fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
 
 # TensorFlow
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
+create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
+predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml")
+upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # PyTorch
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
+create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
+upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # XGBoost
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/d5c9918850a6cc70004c4269dae066cfe2e664eb/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
+train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # Scikit-learn
-train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
+train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
+upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # Vertex AI
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml")
 
 # %% Pipeline definition
 def train_tabular_regression_model_using_all_frameworks_pipeline():

community-content/cpr-examples/timm_serving/requirements.txt

@@ -1,5 +1,5 @@
 absl-py==1.1.0
-fastapi==0.109.1
+fastapi==0.75.2
 uvicorn==0.18.2
 timm==0.5.4
 smart_open==6.0.0

community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml

@@ -1,64 +0,0 @@
-name: Train linear regression model using scikit learn from CSV
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml'}
-inputs:
-- {name: dataset, type: CSV}
-- {name: label_column_name, type: String}
-outputs:
-- {name: model, type: ScikitLearnPickleModel}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'scikit-learn==1.0.2' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'scikit-learn==1.0.2' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_linear_regression_model_using_scikit_learn_from_CSV(
-          dataset_path,
-          model_path,
-          label_column_name,
-      ):
-          import pandas
-          import pickle
-          from sklearn import linear_model
-
-          df = pandas.read_csv(dataset_path)
-          model = linear_model.LinearRegression()
-          model.fit(
-              X=df.drop(columns=label_column_name),
-              y=df[label_column_name],
-          )
-
-          with open(model_path, "wb") as f:
-              pickle.dump(model, f)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train linear regression model using scikit learn from CSV', description='')
-      _parser.add_argument("--dataset", dest="dataset_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_linear_regression_model_using_scikit_learn_from_CSV(**_parsed_args)
-    args:
-    - --dataset
-    - {inputPath: dataset}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - --model
-    - {outputPath: model}

community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml

@@ -1,163 +0,0 @@
-name: Train logistic regression model using scikit learn from CSV
-description: Train logistic regression model using Scikit-learn
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml'}
-inputs:
-- {name: dataset, type: CSV}
-- {name: label_column_name, type: String}
-- {name: penalty, type: String, default: l2, optional: true}
-- {name: solver, type: String, default: lbfgs, optional: true}
-- {name: max_iterations, type: Integer, default: '100', optional: true}
-- {name: multi_class_mode, type: String, default: auto, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: model, type: ScikitLearnPickleModel}
-- {name: model_parameters, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'scikit-learn==1.0.2' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'scikit-learn==1.0.2' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_logistic_regression_model_using_scikit_learn_from_CSV(
-          dataset_path,
-          model_path,
-          label_column_name,
-          penalty = "l2", # l1, l2, elasticnet, none
-          solver = "lbfgs", # newton-cg, lbfgs, liblinear, sag, saga
-          max_iterations = 100,
-          multi_class_mode = "auto", # auto, ovr, multinomial
-          random_seed = 0,
-      ):
-          """Train logistic regression model using Scikit-learn
-
-          See https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
-          """
-          import json
-          import pandas
-          import pickle
-          from sklearn import linear_model
-
-          df = pandas.read_csv(dataset_path)
-          model = linear_model.LogisticRegression(
-              penalty=penalty,
-              #dual=False,
-              #tol=1e-4,
-              #C=1.0,
-              #fit_intercept=True,
-              #intercept_scaling=1,
-              #class_weight=None,
-              random_state=random_seed,
-              solver=solver,
-              max_iter=max_iterations,
-              multi_class=multi_class_mode,
-              #l1_ratio=None,
-              verbose=1,
-          )
-
-          model_parameters = model.get_params()
-          model_parameters_json = json.dumps(model_parameters, indent=2)
-          print("Model parameters:")
-          print(model_parameters_json)
-          print()
-
-          model.fit(
-              X=df.drop(columns=label_column_name),
-              y=df[label_column_name],
-          )
-
-          with open(model_path, "wb") as f:
-              pickle.dump(model, f)
-
-          return (model_parameters_json,)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train logistic regression model using scikit learn from CSV', description='Train logistic regression model using Scikit-learn')
-      _parser.add_argument("--dataset", dest="dataset_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--penalty", dest="penalty", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--solver", dest="solver", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--max-iterations", dest="max_iterations", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--multi-class-mode", dest="multi_class_mode", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=1)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = train_logistic_regression_model_using_scikit_learn_from_CSV(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --dataset
-    - {inputPath: dataset}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: penalty}
-        then:
-        - --penalty
-        - {inputValue: penalty}
-    - if:
-        cond: {isPresent: solver}
-        then:
-        - --solver
-        - {inputValue: solver}
-    - if:
-        cond: {isPresent: max_iterations}
-        then:
-        - --max-iterations
-        - {inputValue: max_iterations}
-    - if:
-        cond: {isPresent: multi_class_mode}
-        then:
-        - --multi-class-mode
-        - {inputValue: multi_class_mode}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --model
-    - {outputPath: model}
-    - '----output-paths'
-    - {outputPath: model_parameters}

community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml

@@ -1,41 +0,0 @@
-name: Create PyTorch Model Archive with base handler
-inputs:
-- {name: Model, type: PyTorchScriptModule}
-- {name: Model name, type: String, default: model}
-- {name: Model version, type: String, default: "1.0"}
-outputs:
-- {name: Model archive, type: PyTorchModelArchive}
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml'
-implementation:
-  container:
-    image: pytorch/torchserve:0.6.0-cpu
-    command:
-    - bash
-    - -exc
-    - |
-      model_path=$0
-      model_name=$1
-      model_version=$2
-      output_model_archive_path=$3
-
-      mkdir -p "$(dirname "$output_model_archive_path")"
-
-      # TODO: Use the built-in base_handler once my fix is merged: https://github.com/pytorch/serve/pull/1682
-      echo '
-      from ts.torch_handler import base_handler
-      class BaseHandler(base_handler.BaseHandler):
-          pass
-      ' > base_handler.py  # torch-model-archiver needs the handler to have .py extension
-      torch-model-archiver --model-name "$model_name" --version "$model_version" --serialized-file "$model_path" --handler base_handler.py
-
-      # torch-model-archiver does not allow specifying the output path, but always writes to "${model_name}.<format>"
-      expected_model_archive_path="${model_name}.mar"
-      mv "$expected_model_archive_path" "$output_model_archive_path"
-
-    - {inputPath: Model}
-    - {inputValue: Model name}
-    - {inputValue: Model version}
-    - {outputPath: Model archive}

community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml

@@ -1,117 +0,0 @@
-name: Create fully connected pytorch network
-description: Creates fully-connected network in PyTorch ScriptModule format
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/PyTorch/Create_fully_connected_network/component.yaml'}
-inputs:
-- {name: input_size, type: Integer}
-- {name: hidden_layer_sizes, type: JsonArray, default: '[]', optional: true}
-- {name: output_size, type: Integer, default: '1', optional: true}
-- {name: activation_name, type: String, default: relu, optional: true}
-- {name: output_activation_name, type: String, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: model, type: PyTorchScriptModule}
-implementation:
-  container:
-    image: pytorch/pytorch:1.7.1-cuda11.0-cudnn8-runtime
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def create_fully_connected_pytorch_network(
-          input_size,
-          model_path,
-          hidden_layer_sizes = [],
-          output_size = 1,
-          activation_name = 'relu',
-          output_activation_name = None,
-          random_seed = 0,
-      ):
-          '''Creates fully-connected network in PyTorch ScriptModule format'''
-          import torch
-          torch.manual_seed(random_seed)
-
-          activation = getattr(torch, activation_name, None) or getattr(torch.nn.functional, activation_name, None)
-          if not activation:
-              raise ValueError(f'Activation "{activation_name}" was not found.')
-
-          class ActivationLayer(torch.nn.Module):
-              def forward(self, input):
-                  return activation(input)
-
-          layers = []
-          prev_layer_size = input_size
-          for layer_size in hidden_layer_sizes:
-              layer = torch.nn.Linear(prev_layer_size, layer_size)
-              prev_layer_size = layer_size
-              layers.append(layer)
-              layers.append(ActivationLayer())
-
-          # Adding the output layer
-          layers.append(torch.nn.Linear(prev_layer_size, output_size))
-
-          # Adding the optional activation after the output layer
-          if output_activation_name:
-              output_activation = getattr(torch, output_activation_name, None) or getattr(torch.nn.functional, output_activation_name, None)
-              class OutputActivationLayer(torch.nn.Module):
-                  def forward(self, input):
-                      return output_activation(input)
-              layers.append(OutputActivationLayer())
-
-          network = torch.nn.Sequential(*layers)
-          script_module = torch.jit.script(network)
-          print(script_module)
-          script_module.save(model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Create fully connected pytorch network', description='Creates fully-connected network in PyTorch ScriptModule format')
-      _parser.add_argument("--input-size", dest="input_size", type=int, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--hidden-layer-sizes", dest="hidden_layer_sizes", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-size", dest="output_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--activation-name", dest="activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-activation-name", dest="output_activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = create_fully_connected_pytorch_network(**_parsed_args)
-    args:
-    - --input-size
-    - {inputValue: input_size}
-    - if:
-        cond: {isPresent: hidden_layer_sizes}
-        then:
-        - --hidden-layer-sizes
-        - {inputValue: hidden_layer_sizes}
-    - if:
-        cond: {isPresent: output_size}
-        then:
-        - --output-size
-        - {inputValue: output_size}
-    - if:
-        cond: {isPresent: activation_name}
-        then:
-        - --activation-name
-        - {inputValue: activation_name}
-    - if:
-        cond: {isPresent: output_activation_name}
-        then:
-        - --output-activation-name
-        - {inputValue: output_activation_name}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --model
-    - {outputPath: model}

community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml

@@ -1,209 +0,0 @@
-name: Train pytorch model from csv
-description: Trains PyTorch model
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml'
-inputs:
-- {name: model, type: PyTorchScriptModule}
-- {name: training_data, type: CSV}
-- {name: label_column_name, type: String}
-- {name: loss_function_name, type: String, default: mse_loss, optional: true}
-- {name: number_of_epochs, type: Integer, default: '1', optional: true}
-- {name: learning_rate, type: Float, default: '0.1', optional: true}
-- {name: optimizer_name, type: String, default: Adadelta, optional: true}
-- {name: optimizer_parameters, type: JsonObject, optional: true}
-- {name: batch_size, type: Integer, default: '32', optional: true}
-- {name: batch_log_interval, type: Integer, default: '100', optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: trained_model, type: PyTorchScriptModule}
-implementation:
-  container:
-    image: pytorch/pytorch:1.7.1-cuda11.0-cudnn8-runtime
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.3' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_pytorch_model_from_csv(
-          model_path,
-          training_data_path,
-          trained_model_path,
-          label_column_name,
-          loss_function_name = 'mse_loss',
-          number_of_epochs = 1,
-          learning_rate = 0.1,
-          optimizer_name = 'Adadelta',
-          optimizer_parameters = None,
-          batch_size = 32,
-          batch_log_interval = 100,
-          random_seed = 0,
-      ):
-          '''Trains PyTorch model'''
-          import pandas
-          import torch
-
-          torch.manual_seed(random_seed)
-
-          use_cuda = torch.cuda.is_available()
-          device = torch.device("cuda" if use_cuda else "cpu")
-
-          model = torch.jit.load(model_path)
-          model.to(device)
-          model.train()
-
-          optimizer_class = getattr(torch.optim, optimizer_name, None)
-          if not optimizer_class:
-              raise ValueError(f'Optimizer "{optimizer_name}" was not found.')
-
-          optimizer_parameters = optimizer_parameters or {}
-          optimizer_parameters['lr'] = learning_rate
-          optimizer = optimizer_class(model.parameters(), **optimizer_parameters)
-
-          loss_function = getattr(torch, loss_function_name, None) or getattr(torch.nn, loss_function_name, None) or getattr(torch.nn.functional, loss_function_name, None)
-          if not loss_function:
-              raise ValueError(f'Loss function "{loss_function_name}" was not found.')
-
-          class CsvDataset(torch.utils.data.Dataset):
-
-              def __init__(self, file_path, label_column_name, drop_nan_columns_or_rows = 'columns'):
-                  dataframe = pandas.read_csv(file_path).convert_dtypes()
-                  # Preventing error: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found object
-                  if drop_nan_columns_or_rows == 'columns':
-                      non_nan_data = dataframe.dropna(axis='columns')
-                      removed_columns = set(dataframe.columns) - set(non_nan_data.columns)
-                      if removed_columns:
-                          print('Skipping columns with NaNs: ' + str(removed_columns))
-                      dataframe = non_nan_data
-                  if drop_nan_columns_or_rows == 'rows':
-                      non_nan_data = dataframe.dropna(axis='index')
-                      number_of_removed_rows = len(dataframe) - len(non_nan_data)
-                      if number_of_removed_rows:
-                          print(f'Skipped {number_of_removed_rows} rows with NaNs.')
-                      dataframe = non_nan_data
-                  numerical_data = dataframe.select_dtypes(include='number')
-                  non_numerical_data = dataframe.select_dtypes(exclude='number')
-                  if not non_numerical_data.empty:
-                      print('Skipping non-number columns:')
-                      print(non_numerical_data.dtypes)
-                  self._dataframe = dataframe
-                  self.labels = numerical_data[[label_column_name]]
-                  self.features = numerical_data.drop(columns=[label_column_name])
-
-              def __len__(self):
-                  return len(self._dataframe)
-
-              def __getitem__(self, index):
-                  return [self.features.loc[index].to_numpy(dtype='float32'), self.labels.loc[index].to_numpy(dtype='float32')]
-
-          dataset = CsvDataset(
-              file_path=training_data_path,
-              label_column_name=label_column_name,
-          )
-          train_loader = torch.utils.data.DataLoader(
-              dataset=dataset,
-              batch_size=batch_size,
-              shuffle=True,
-          )
-
-          last_full_batch_loss = None
-          for epoch in range(1, number_of_epochs + 1):
-              for batch_idx, (data, target) in enumerate(train_loader):
-                  data, target = data.to(device), target.to(device)
-                  optimizer.zero_grad()
-                  output = model(data)
-                  loss = loss_function(output, target)
-                  loss.backward()
-                  optimizer.step()
-                  if len(data) == batch_size:
-                      last_full_batch_loss = loss.item()
-                  if batch_idx % batch_log_interval == 0:
-                      print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
-                          epoch, batch_idx * len(data), len(train_loader.dataset),
-                          100. * batch_idx / len(train_loader), loss.item()))
-              print(f'Training epoch {epoch} completed. Last full batch loss: {last_full_batch_loss:.6f}')
-
-          # print(optimizer.state_dict())
-          model.save(trained_model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train pytorch model from csv', description='Trains PyTorch model')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--training-data", dest="training_data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--loss-function-name", dest="loss_function_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--number-of-epochs", dest="number_of_epochs", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--learning-rate", dest="learning_rate", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-name", dest="optimizer_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-parameters", dest="optimizer_parameters", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-size", dest="batch_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-log-interval", dest="batch_log_interval", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--trained-model", dest="trained_model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_pytorch_model_from_csv(**_parsed_args)
-    args:
-    - --model
-    - {inputPath: model}
-    - --training-data
-    - {inputPath: training_data}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: loss_function_name}
-        then:
-        - --loss-function-name
-        - {inputValue: loss_function_name}
-    - if:
-        cond: {isPresent: number_of_epochs}
-        then:
-        - --number-of-epochs
-        - {inputValue: number_of_epochs}
-    - if:
-        cond: {isPresent: learning_rate}
-        then:
-        - --learning-rate
-        - {inputValue: learning_rate}
-    - if:
-        cond: {isPresent: optimizer_name}
-        then:
-        - --optimizer-name
-        - {inputValue: optimizer_name}
-    - if:
-        cond: {isPresent: optimizer_parameters}
-        then:
-        - --optimizer-parameters
-        - {inputValue: optimizer_parameters}
-    - if:
-        cond: {isPresent: batch_size}
-        then:
-        - --batch-size
-        - {inputValue: batch_size}
-    - if:
-        cond: {isPresent: batch_log_interval}
-        then:
-        - --batch-log-interval
-        - {inputValue: batch_log_interval}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --trained-model
-    - {outputPath: trained_model}

community-content/pipeline_components/XGBoost/Predict/component.yaml

@@ -1,110 +0,0 @@
-name: Xgboost predict on CSV
-description: Makes predictions using a trained XGBoost model.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/XGBoost/Predict/component.yaml'}
-inputs:
-- {name: data, type: CSV, description: Feature data in Apache Parquet format.}
-- {name: model, type: XGBoostModel, description: Trained model in binary XGBoost format.}
-- {name: label_column_name, type: String, description: Optional. Name of the column
-    containing the label data that is excluded during the prediction., optional: true}
-outputs:
-- {name: predictions, description: Model predictions.}
-implementation:
-  container:
-    image: python:3.10
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'xgboost==1.6.1' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'xgboost==1.6.1' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def xgboost_predict_on_CSV(
-          data_path,
-          model_path,
-          predictions_path,
-          label_column_name = None,
-      ):
-          """Makes predictions using a trained XGBoost model.
-
-          Args:
-              data_path: Feature data in Apache Parquet format.
-              model_path: Trained model in binary XGBoost format.
-              predictions_path: Model predictions.
-              label_column_name: Optional. Name of the column containing the label data that is excluded during the prediction.
-
-          Annotations:
-              author: Alexey Volkov <alexey.volkov@ark-kun.com>
-          """
-          from pathlib import Path
-
-          import numpy
-          import pandas
-          import xgboost
-
-          df = pandas.read_csv(
-              data_path,
-          ).convert_dtypes()
-          print("Evaluation data information:")
-          df.info(verbose=True)
-          # Converting column types that XGBoost does not support
-          for column_name, dtype in df.dtypes.items():
-              if dtype in ["string", "object"]:
-                  print(f"Treating the {dtype.name} column '{column_name}' as categorical.")
-                  df[column_name] = df[column_name].astype("category")
-                  print(f"Inferred {len(df[column_name].cat.categories)} categories for the '{column_name}' column.")
-              # Working around the XGBoost issue with nullable floats: https://github.com/dmlc/xgboost/issues/8213
-              if pandas.api.types.is_float_dtype(dtype):
-                  # Converting from "Float64" to "float64"
-                  df[column_name] = df[column_name].astype(dtype.name.lower())
-          print("Final evaluation data information:")
-          df.info(verbose=True)
-
-          if label_column_name is not None:
-              df = df.drop(columns=[label_column_name])
-
-          testing_data = xgboost.DMatrix(
-              data=df,
-              enable_categorical=True,
-          )
-
-          model = xgboost.Booster(model_file=model_path)
-
-          predictions = model.predict(testing_data)
-
-          Path(predictions_path).parent.mkdir(parents=True, exist_ok=True)
-          numpy.savetxt(predictions_path, predictions)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Xgboost predict on CSV', description='Makes predictions using a trained XGBoost model.')
-      _parser.add_argument("--data", dest="data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--predictions", dest="predictions_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = xgboost_predict_on_CSV(**_parsed_args)
-    args:
-    - --data
-    - {inputPath: data}
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: label_column_name}
-        then:
-        - --label-column-name
-        - {inputValue: label_column_name}
-    - --predictions
-    - {outputPath: predictions}

community-content/pipeline_components/XGBoost/Train/component.yaml

@@ -1,241 +0,0 @@
-name: Train XGBoost model on CSV
-description: Trains an XGBoost model.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/XGBoost/Train/component.yaml'}
-inputs:
-- {name: training_data, type: CSV, description: Training data in CSV format.}
-- {name: label_column_name, type: String, description: Name of the column containing
-    the label data.}
-- {name: starting_model, type: XGBoostModel, description: Existing trained model to
-    start from (in the binary XGBoost format)., optional: true}
-- {name: num_iterations, type: Integer, description: Number of boosting iterations.,
-  default: '10', optional: true}
-- name: objective
-  type: String
-  description: |-
-    The learning task and the corresponding learning objective.
-    See https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters
-    The most common values are:
-    "reg:squarederror" - Regression with squared loss (default).
-    "reg:logistic" - Logistic regression.
-    "binary:logistic" - Logistic regression for binary classification, output probability.
-    "binary:logitraw" - Logistic regression for binary classification, output score before logistic transformation
-    "rank:pairwise" - Use LambdaMART to perform pairwise ranking where the pairwise loss is minimized
-    "rank:ndcg" - Use LambdaMART to perform list-wise ranking where Normalized Discounted Cumulative Gain (NDCG) is maximized
-  default: reg:squarederror
-  optional: true
-- {name: booster, type: String, description: 'The booster to use. Can be `gbtree`,
-    `gblinear` or `dart`; `gbtree` and `dart` use tree based models while `gblinear`
-    uses linear functions.', default: gbtree, optional: true}
-- {name: learning_rate, type: Float, description: 'Step size shrinkage used in update
-    to prevents overfitting. Range: [0,1].', default: '0.3', optional: true}
-- name: min_split_loss
-  type: Float
-  description: |-
-    Minimum loss reduction required to make a further partition on a leaf node of the tree.
-    The larger `min_split_loss` is, the more conservative the algorithm will be. Range: [0,Inf].
-  default: '0'
-  optional: true
-- name: max_depth
-  type: Integer
-  description: |-
-    Maximum depth of a tree. Increasing this value will make the model more complex and more likely to overfit.
-    0 indicates no limit on depth. Range: [0,Inf].
-  default: '6'
-  optional: true
-- {name: booster_params, type: JsonObject, description: 'Parameters for the booster.
-    See https://xgboost.readthedocs.io/en/latest/parameter.html', optional: true}
-outputs:
-- {name: model, type: XGBoostModel, description: Trained model in the binary XGBoost
-    format.}
-- {name: model_config, type: XGBoostModelConfig, description: The internal parameter
-    configuration of Booster as a JSON string.}
-implementation:
-  container:
-    image: python:3.10
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'xgboost==1.6.1' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'xgboost==1.6.1' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_XGBoost_model_on_CSV(
-          training_data_path,
-          model_path,
-          model_config_path,
-          label_column_name,
-          starting_model_path = None,
-          num_iterations = 10,
-          # Booster parameters
-          objective = "reg:squarederror",
-          booster = "gbtree",
-          learning_rate = 0.3,
-          min_split_loss = 0,
-          max_depth = 6,
-          booster_params = None,
-      ):
-          """Trains an XGBoost model.
-
-          Args:
-              training_data_path: Training data in CSV format.
-              model_path: Trained model in the binary XGBoost format.
-              model_config_path: The internal parameter configuration of Booster as a JSON string.
-              starting_model_path: Existing trained model to start from (in the binary XGBoost format).
-              label_column_name: Name of the column containing the label data.
-              num_iterations: Number of boosting iterations.
-              booster_params: Parameters for the booster. See https://xgboost.readthedocs.io/en/latest/parameter.html
-              objective: The learning task and the corresponding learning objective.
-                  See https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters
-                  The most common values are:
-                  "reg:squarederror" - Regression with squared loss (default).
-                  "reg:logistic" - Logistic regression.
-                  "binary:logistic" - Logistic regression for binary classification, output probability.
-                  "binary:logitraw" - Logistic regression for binary classification, output score before logistic transformation
-                  "rank:pairwise" - Use LambdaMART to perform pairwise ranking where the pairwise loss is minimized
-                  "rank:ndcg" - Use LambdaMART to perform list-wise ranking where Normalized Discounted Cumulative Gain (NDCG) is maximized
-              booster: The booster to use. Can be `gbtree`, `gblinear` or `dart`; `gbtree` and `dart` use tree based models while `gblinear` uses linear functions.
-              learning_rate: Step size shrinkage used in update to prevents overfitting. Range: [0,1].
-              min_split_loss: Minimum loss reduction required to make a further partition on a leaf node of the tree.
-                  The larger `min_split_loss` is, the more conservative the algorithm will be. Range: [0,Inf].
-              max_depth: Maximum depth of a tree. Increasing this value will make the model more complex and more likely to overfit.
-                  0 indicates no limit on depth. Range: [0,Inf].
-
-          Annotations:
-              author: Alexey Volkov <alexey.volkov@ark-kun.com>
-          """
-          import pandas
-          import xgboost
-
-          df = pandas.read_csv(
-              training_data_path,
-          ).convert_dtypes()
-          print("Training data information:")
-          df.info(verbose=True)
-          # Converting column types that XGBoost does not support
-          for column_name, dtype in df.dtypes.items():
-              if dtype in ["string", "object"]:
-                  print(f"Treating the {dtype.name} column '{column_name}' as categorical.")
-                  df[column_name] = df[column_name].astype("category")
-                  print(f"Inferred {len(df[column_name].cat.categories)} categories for the '{column_name}' column.")
-              # Working around the XGBoost issue with nullable floats: https://github.com/dmlc/xgboost/issues/8213
-              if pandas.api.types.is_float_dtype(dtype):
-                  # Converting from "Float64" to "float64"
-                  df[column_name] = df[column_name].astype(dtype.name.lower())
-          print()
-          print("Final training data information:")
-          df.info(verbose=True)
-
-          training_data = xgboost.DMatrix(
-              data=df.drop(columns=[label_column_name]),
-              label=df[[label_column_name]],
-              enable_categorical=True,
-          )
-
-          booster_params = booster_params or {}
-          booster_params.setdefault("objective", objective)
-          booster_params.setdefault("booster", booster)
-          booster_params.setdefault("learning_rate", learning_rate)
-          booster_params.setdefault("min_split_loss", min_split_loss)
-          booster_params.setdefault("max_depth", max_depth)
-
-          starting_model = None
-          if starting_model_path:
-              starting_model = xgboost.Booster(model_file=starting_model_path)
-
-          print()
-          print("Training the model:")
-          model = xgboost.train(
-              params=booster_params,
-              dtrain=training_data,
-              num_boost_round=num_iterations,
-              xgb_model=starting_model,
-              evals=[(training_data, "training_data")],
-          )
-
-          # Saving the model in binary format
-          model.save_model(model_path)
-
-          model_config_str = model.save_config()
-          with open(model_config_path, "w") as model_config_file:
-              model_config_file.write(model_config_str)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train XGBoost model on CSV', description='Trains an XGBoost model.')
-      _parser.add_argument("--training-data", dest="training_data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--starting-model", dest="starting_model_path", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--num-iterations", dest="num_iterations", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--objective", dest="objective", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--booster", dest="booster", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--learning-rate", dest="learning_rate", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--min-split-loss", dest="min_split_loss", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--max-depth", dest="max_depth", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--booster-params", dest="booster_params", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model-config", dest="model_config_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_XGBoost_model_on_CSV(**_parsed_args)
-    args:
-    - --training-data
-    - {inputPath: training_data}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: starting_model}
-        then:
-        - --starting-model
-        - {inputPath: starting_model}
-    - if:
-        cond: {isPresent: num_iterations}
-        then:
-        - --num-iterations
-        - {inputValue: num_iterations}
-    - if:
-        cond: {isPresent: objective}
-        then:
-        - --objective
-        - {inputValue: objective}
-    - if:
-        cond: {isPresent: booster}
-        then:
-        - --booster
-        - {inputValue: booster}
-    - if:
-        cond: {isPresent: learning_rate}
-        then:
-        - --learning-rate
-        - {inputValue: learning_rate}
-    - if:
-        cond: {isPresent: min_split_loss}
-        then:
-        - --min-split-loss
-        - {inputValue: min_split_loss}
-    - if:
-        cond: {isPresent: max_depth}
-        then:
-        - --max-depth
-        - {inputValue: max_depth}
-    - if:
-        cond: {isPresent: booster_params}
-        then:
-        - --booster-params
-        - {inputValue: booster_params}
-    - --model
-    - {outputPath: model}
-    - --model-config
-    - {outputPath: model_config}

community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml

@@ -1,204 +0,0 @@
-name: Split rows into subsets
-description: Splits the data table according to the split fractions.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: fraction_1, type: Float, description: 'The proportion of the lines to put
-    into the 1st split. Range: [0, 1]'}
-- name: fraction_2
-  type: Float
-  description: |-
-    The proportion of the lines to put into the 2nd split. Range: [0, 1]
-    If fraction_2 is not specified, then fraction_2 = 1 - fraction_1.
-    The remaining lines go to the 3rd split (if any).
-  optional: true
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: split_1, type: CSV}
-- {name: split_2, type: CSV}
-- {name: split_3, type: CSV}
-- {name: split_1_count, type: Integer}
-- {name: split_2_count, type: Integer}
-- {name: split_3_count, type: Integer}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def split_rows_into_subsets(
-          table_path,
-          split_1_path,
-          split_2_path,
-          split_3_path,
-          fraction_1,
-          fraction_2 = None,
-          random_seed = 0,
-      ):
-          """Splits the data table according to the split fractions.
-
-          Args:
-              fraction_1: The proportion of the lines to put into the 1st split. Range: [0, 1]
-              fraction_2: The proportion of the lines to put into the 2nd split. Range: [0, 1]
-                  If fraction_2 is not specified, then fraction_2 = 1 - fraction_1.
-                  The remaining lines go to the 3rd split (if any).
-          """
-          import random
-
-          random.seed(random_seed)
-
-          SHUFFLE_BUFFER_SIZE = 10000
-
-          num_splits = 3
-
-          if fraction_1 < 0 or fraction_1 > 1:
-              raise ValueError("fraction_1 must be in between 0 and 1.")
-
-          if fraction_2 is None:
-              fraction_2 = 1 - fraction_1
-          if fraction_2 < 0 or fraction_2 > 1:
-              raise ValueError("fraction_2 must be in between 0 and 1.")
-
-          fraction_3 = 1 - fraction_1 - fraction_2
-
-          fractions = [
-              fraction_1,
-              fraction_2,
-              fraction_3,
-          ]
-
-          assert sum(fractions) == 1
-
-          written_line_counts = [0] * num_splits
-
-          output_files = [
-              open(split_1_path, "wb"),
-              open(split_2_path, "wb"),
-              open(split_3_path, "wb"),
-          ]
-
-          with open(table_path, "rb") as input_file:
-              # Writing the headers
-              header_line = input_file.readline()
-              for output_file in output_files:
-                  output_file.write(header_line)
-
-              while True:
-                  line_buffer = []
-                  for i in range(SHUFFLE_BUFFER_SIZE):
-                      line = input_file.readline()
-                      if not line:
-                          break
-                      line_buffer.append(line)
-
-                  # We need to exactly partition the lines between the output files
-                  # To overcome possible systematic bias, we could calculate the total numbers
-                  # of lines written to each file and take that into account.
-                  num_read_lines = len(line_buffer)
-                  number_of_lines_for_files = [0] * num_splits
-                  # List that will have the index of the destination file for each line
-                  file_index_for_line = []
-                  remaining_lines = num_read_lines
-                  remaining_fraction = 1
-                  for i in range(num_splits):
-                      number_of_lines_for_file = (
-                          round(remaining_lines * (fractions[i] / remaining_fraction))
-                          if remaining_fraction > 0
-                          else 0
-                      )
-                      number_of_lines_for_files[i] = number_of_lines_for_file
-                      remaining_lines -= number_of_lines_for_file
-                      remaining_fraction -= fractions[i]
-                      file_index_for_line.extend([i] * number_of_lines_for_file)
-
-                  assert remaining_lines == 0, f"{remaining_lines}"
-                  assert len(file_index_for_line) == num_read_lines
-
-                  random.shuffle(file_index_for_line)
-
-                  for i in range(num_read_lines):
-                      output_files[file_index_for_line[i]].write(line_buffer[i])
-                      written_line_counts[file_index_for_line[i]] += 1
-
-                  # Exit if the file ended before we were able to fully fill the buffer
-                  if len(line_buffer) != SHUFFLE_BUFFER_SIZE:
-                      break
-
-          for output_file in output_files:
-              output_file.close()
-
-          return written_line_counts
-
-      def _serialize_int(int_value: int) -> str:
-          if isinstance(int_value, str):
-              return int_value
-          if not isinstance(int_value, int):
-              raise TypeError('Value "{}" has type "{}" instead of int.'.format(str(int_value), str(type(int_value))))
-          return str(int_value)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Split rows into subsets', description='Splits the data table according to the split fractions.')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--fraction-1", dest="fraction_1", type=float, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--fraction-2", dest="fraction_2", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--split-1", dest="split_1_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--split-2", dest="split_2_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--split-3", dest="split_3_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=3)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = split_rows_into_subsets(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_int,
-          _serialize_int,
-          _serialize_int,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --table
-    - {inputPath: table}
-    - --fraction-1
-    - {inputValue: fraction_1}
-    - if:
-        cond: {isPresent: fraction_2}
-        then:
-        - --fraction-2
-        - {inputValue: fraction_2}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --split-1
-    - {outputPath: split_1}
-    - --split-2
-    - {outputPath: split_2}
-    - --split-3
-    - {outputPath: split_3}
-    - '----output-paths'
-    - {outputPath: split_1_count}
-    - {outputPath: split_2_count}
-    - {outputPath: split_3_count}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml

@@ -1,241 +0,0 @@
-name: Deploy model to endpoint for Google Cloud Vertex AI Model
-description: Deploys Google Cloud Vertex AI Model to a Google Cloud Vertex AI Endpoint.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model_name, type: String, description: Full resource name of a Google Cloud
-    Vertex AI Model}
-- name: endpoint_name
-  type: String
-  description: |-
-    Optional. Full name of Google Cloud Vertex Endpoint. A new
-    endpoint is created if the name is not passed.
-  optional: true
-- name: machine_type
-  type: String
-  description: |-
-    The type of the machine. See the [list of machine types
-    supported for prediction
-    ](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types).
-    Defaults to "n1-standard-2"
-  default: n1-standard-2
-  optional: true
-- name: min_replica_count
-  type: Integer
-  description: |-
-    Optional. The minimum number of machine replicas this deployed
-    model will be always deployed on. If traffic against it increases,
-    it may dynamically be deployed onto more replicas, and as traffic
-    decreases, some of these extra replicas may be freed.
-  default: '1'
-  optional: true
-- name: max_replica_count
-  type: Integer
-  description: |-
-    Optional. The maximum number of replicas this deployed model may
-    be deployed on when the traffic against it increases. If requested
-    value is too large, the deployment will error, but if deployment
-    succeeds then the ability to scale the model to that many replicas
-    is guaranteed (barring service outages). If traffic against the
-    deployed model increases beyond what its replicas at maximum may
-    handle, a portion of the traffic will be dropped. If this value
-    is not provided, the smaller value of min_replica_count or 1 will
-    be used.
-  default: '1'
-  optional: true
-- name: accelerator_type
-  type: String
-  description: |-
-    Optional. Hardware accelerator type. Must also set accelerator_count if used.
-    One of ACCELERATOR_TYPE_UNSPECIFIED, NVIDIA_TESLA_K80, NVIDIA_TESLA_P100,
-    NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4
-  optional: true
-- {name: accelerator_count, type: Integer, description: Optional. The number of accelerators
-    to attach to a worker replica., optional: true}
-outputs:
-- {name: endpoint_name, type: String}
-- {name: endpoint_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.7.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.7.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def deploy_model_to_endpoint_for_Google_Cloud_Vertex_AI_Model(
-          model_name,
-          endpoint_name = None,
-          machine_type = "n1-standard-2",
-          min_replica_count = 1,
-          max_replica_count = 1,
-          accelerator_type = None,
-          accelerator_count = None,
-          #
-          # Uncomment when anyone requests these:
-          # deployed_model_display_name: str = None,
-          # traffic_percentage: int = 0,
-          # traffic_split: dict = None,
-          # service_account: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-          #
-          # encryption_spec_key_name: str = None,
-      ):
-          """Deploys Google Cloud Vertex AI Model to a Google Cloud Vertex AI Endpoint.
-
-          Args:
-              model_name: Full resource name of a Google Cloud Vertex AI Model
-              endpoint_name: Optional. Full name of Google Cloud Vertex Endpoint. A new
-                  endpoint is created if the name is not passed.
-              machine_type: The type of the machine. See the [list of machine types
-                  supported for prediction
-                  ](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types).
-                  Defaults to "n1-standard-2"
-              min_replica_count (int):
-                  Optional. The minimum number of machine replicas this deployed
-                  model will be always deployed on. If traffic against it increases,
-                  it may dynamically be deployed onto more replicas, and as traffic
-                  decreases, some of these extra replicas may be freed.
-              max_replica_count (int):
-                  Optional. The maximum number of replicas this deployed model may
-                  be deployed on when the traffic against it increases. If requested
-                  value is too large, the deployment will error, but if deployment
-                  succeeds then the ability to scale the model to that many replicas
-                  is guaranteed (barring service outages). If traffic against the
-                  deployed model increases beyond what its replicas at maximum may
-                  handle, a portion of the traffic will be dropped. If this value
-                  is not provided, the smaller value of min_replica_count or 1 will
-                  be used.
-              accelerator_type (str):
-                  Optional. Hardware accelerator type. Must also set accelerator_count if used.
-                  One of ACCELERATOR_TYPE_UNSPECIFIED, NVIDIA_TESLA_K80, NVIDIA_TESLA_P100,
-                  NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4
-              accelerator_count (int):
-                  Optional. The number of accelerators to attach to a worker replica.
-          """
-          import json
-          from google.cloud import aiplatform
-
-          model = aiplatform.Model(model_name=model_name)
-
-          if endpoint_name:
-              endpoint = aiplatform.Endpoint(endpoint_name=endpoint_name)
-          else:
-              endpoint_display_name = model.display_name[:118] + "_endpoint"
-              endpoint = aiplatform.Endpoint.create(
-                  display_name=endpoint_display_name,
-                  project=model.project,
-                  location=model.location,
-                  # encryption_spec_key_name=encryption_spec_key_name,
-                  labels={"component-source": "github-com-ark-kun-pipeline-components"},
-              )
-
-          endpoint = model.deploy(
-              endpoint=endpoint,
-              # deployed_model_display_name=deployed_model_display_name,
-              machine_type=machine_type,
-              min_replica_count=min_replica_count,
-              max_replica_count=max_replica_count,
-              accelerator_type=accelerator_type,
-              accelerator_count=accelerator_count,
-              # service_account=service_account,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-              # encryption_spec_key_name=encryption_spec_key_name,
-          )
-
-          endpoint_json = json.dumps(endpoint.to_dict(), indent=2)
-          print(endpoint_json)
-          return (endpoint.resource_name, endpoint_json)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Deploy model to endpoint for Google Cloud Vertex AI Model', description='Deploys Google Cloud Vertex AI Model to a Google Cloud Vertex AI Endpoint.')
-      _parser.add_argument("--model-name", dest="model_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--endpoint-name", dest="endpoint_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--machine-type", dest="machine_type", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--min-replica-count", dest="min_replica_count", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--max-replica-count", dest="max_replica_count", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--accelerator-type", dest="accelerator_type", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--accelerator-count", dest="accelerator_count", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = deploy_model_to_endpoint_for_Google_Cloud_Vertex_AI_Model(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model-name
-    - {inputValue: model_name}
-    - if:
-        cond: {isPresent: endpoint_name}
-        then:
-        - --endpoint-name
-        - {inputValue: endpoint_name}
-    - if:
-        cond: {isPresent: machine_type}
-        then:
-        - --machine-type
-        - {inputValue: machine_type}
-    - if:
-        cond: {isPresent: min_replica_count}
-        then:
-        - --min-replica-count
-        - {inputValue: min_replica_count}
-    - if:
-        cond: {isPresent: max_replica_count}
-        then:
-        - --max-replica-count
-        - {inputValue: max_replica_count}
-    - if:
-        cond: {isPresent: accelerator_type}
-        then:
-        - --accelerator-type
-        - {inputValue: accelerator_type}
-    - if:
-        cond: {isPresent: accelerator_count}
-        then:
-        - --accelerator-count
-        - {inputValue: accelerator_count}
-    - '----output-paths'
-    - {outputPath: endpoint_name}
-    - {outputPath: endpoint_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml

@@ -1,297 +0,0 @@
-name: Upload PyTorch model archive to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model_archive, type: PyTorchModelArchive}
-- {name: torchserve_version, type: String, default: 0.6.0, optional: true}
-- name: use_gpu
-  type: Boolean
-  default: "False"
-  optional: true
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.13.1' 'google-cloud-build==3.8.3' || PIP_DISABLE_PIP_VERSION_CHECK=1
-      python3 -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.13.1'
-      'google-cloud-build==3.8.3' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI(
-          model_archive_path,
-          torchserve_version = "0.6.0",
-          use_gpu = False,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          container_image_tag = torchserve_version + "-" + ("gpu" if use_gpu else "cpu")
-          container_image_uri = f"pytorch/torchserve:{container_image_tag}"
-
-          # Vertex Endpoints refuse to support non-Google container registries.
-          # We have to work around this to reduce user frustration
-          # TODO: Remove this code when Vertex Endpoints service starts supporting other container registries.
-          def copy_container_image(
-              src_container_image_uri,
-              dst_container_image_uri,
-              project_id,
-          ):
-              from google.cloud.devtools import cloudbuild
-              from google import protobuf
-              build_client = cloudbuild.CloudBuildClient()
-              build_config = cloudbuild.Build(
-                  images=[dst_container_image_uri],
-                  steps=[
-                      cloudbuild.BuildStep(
-                          name="gcr.io/cloud-builders/docker",
-                          entrypoint="bash",
-                          args=[
-                              "-exc",
-                              'docker pull --quiet "$0" && docker tag "$0" "$1"',
-                              src_container_image_uri,
-                              dst_container_image_uri,
-                          ],
-                      ),
-                  ],
-                  timeout=protobuf.duration_pb2.Duration(
-                      seconds=1800,
-                  ),
-              )
-              build_operation = build_client.create_build(
-                  project_id=project_id,
-                  build=build_config,
-              )
-              try:
-                  result = build_operation.result()
-              except:
-                  print(f"Logs are available at [{build_operation.metadata.build.log_url}].")
-                  raise
-              return result
-
-          project_id = aiplatform.initializer.global_config.project
-          mirrored_container_uri = f"gcr.io/{project_id}/container_mirror/{container_image_uri}"
-          # FIX: Only mirror when image does not exist
-          # docker does is unable to get the registry data from inside container (it cannot connecto to docker socket):
-          # docker.errors.DockerException: Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory'))
-          # import docker
-          # try:
-          #     docker_client = docker.from_env()
-          #     docker_client.images.get_registry_data(mirrored_container_uri)
-          # except docker.errors.NotFound:
-          if True:
-              print(f"Mirroring {container_image_uri} to {mirrored_container_uri}")
-              copy_container_image(
-                  src_container_image_uri=container_image_uri,
-                  dst_container_image_uri=mirrored_container_uri,
-                  project_id=project_id,
-              )
-          container_image_uri = mirrored_container_uri
-          # End of container image mirroring code
-
-          model_archive_file_name = os.path.basename(model_archive_path)
-          model_archive_dir = os.path.dirname(model_archive_path)
-
-          model = aiplatform.Model.upload(
-              # FIX: Use public image or mirror the official image
-              #serving_container_image_uri="gcr.io/avolkov-31337/mirror/pytorch/torchserve",
-              serving_container_image_uri=container_image_uri,
-              artifact_uri=model_archive_dir,
-              serving_container_command=[
-                  "bash",
-                  "-exc",
-                  '''
-      model_archive_uri="$0"
-      #model_archive_local_path=$(mktemp --suffix ".mar")
-      # For some reason the model must already be inside the model-store directory.
-      model_archive_local_path=./model-store/model.mar
-
-      # Downloading the model archive from GCS
-      # TODO: Fix gsutil bugs (requires project ID, has auth issues) and use gsutil instead.
-      # gcloud storage cp "$model_archive_uri" "$model_archive_local_path"
-      pip install google-cloud-storage
-      python -c '
-      import sys
-      from google.cloud import storage
-
-      model_archive_uri = sys.argv[1]
-      model_archive_local_path = sys.argv[2]
-
-      storage_client = storage.Client()
-      blob = storage.Blob.from_string(uri=model_archive_uri, client=storage_client)
-      blob.download_to_filename(filename=model_archive_local_path)
-      ' "$model_archive_uri" "$model_archive_local_path"
-
-      #Note: config.properties is owned by root. Our user is not root.
-      echo "
-      service_envelope=json
-      # Needed for external access
-      inference_address=http://0.0.0.0:8080
-      management_address=http://0.0.0.0:8081
-      " > config2.properties
-      torchserve --start --foreground --no-config-snapshots --models main-model="$model_archive_local_path" --model-store ./model-store/ --ts-config config2.properties
-                  ''',
-                  "$(AIP_STORAGE_URI)/" + model_archive_file_name,
-              ],
-              serving_container_predict_route="/predictions/main-model",
-              #serving_container_predict_route="/v1/models/main-model:predict",
-              serving_container_health_route="/ping",
-              serving_container_ports=[8080],
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _deserialize_bool(s) -> bool:
-          from distutils.util import strtobool
-          return strtobool(s) == 1
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload PyTorch model archive to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model-archive", dest="model_archive_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--torchserve-version", dest="torchserve_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--use-gpu", dest="use_gpu", type=_deserialize_bool, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model-archive
-    - {inputPath: model_archive}
-    - if:
-        cond: {isPresent: torchserve_version}
-        then:
-        - --torchserve-version
-        - {inputValue: torchserve_version}
-    - if:
-        cond: {isPresent: use_gpu}
-        then:
-        - --use-gpu
-        - {inputValue: use_gpu}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml

@@ -1,181 +0,0 @@
-name: Upload Scikit learn pickle model to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model, type: ScikitLearnPickleModel}
-- {name: sklearn_version, type: String, optional: true}
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.16.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.16.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI(
-          model_path,
-          sklearn_version = None,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          import shutil
-          import tempfile
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          # The serving container decides the model type based on the model file extension.
-          # So we need to rename the mode file (e.g. /tmp/inputs/model/data) to *.pkl
-          _, renamed_model_path = tempfile.mkstemp(suffix=".pkl")
-          shutil.copyfile(src=model_path, dst=renamed_model_path)
-
-          model = aiplatform.Model.upload_scikit_learn_model_file(
-              model_file_path=renamed_model_path,
-              sklearn_version=sklearn_version,
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload Scikit learn pickle model to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--sklearn-version", dest="sklearn_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: sklearn_version}
-        then:
-        - --sklearn-version
-        - {inputValue: sklearn_version}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml

@@ -1,190 +0,0 @@
-name: Upload Tensorflow model to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model, type: TensorflowSavedModel}
-- {name: tensorflow_version, type: String, optional: true}
-- name: use_gpu
-  type: Boolean
-  default: "False"
-  optional: true
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.16.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.16.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_Tensorflow_model_to_Google_Cloud_Vertex_AI(
-          model_path,
-          tensorflow_version = None,
-          use_gpu = False,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          model = aiplatform.Model.upload_tensorflow_saved_model(
-              saved_model_dir=model_path,
-              tensorflow_version=tensorflow_version,
-              use_gpu=use_gpu,
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _deserialize_bool(s) -> bool:
-          from distutils.util import strtobool
-          return strtobool(s) == 1
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload Tensorflow model to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--tensorflow-version", dest="tensorflow_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--use-gpu", dest="use_gpu", type=_deserialize_bool, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: tensorflow_version}
-        then:
-        - --tensorflow-version
-        - {inputValue: tensorflow_version}
-    - if:
-        cond: {isPresent: use_gpu}
-        then:
-        - --use-gpu
-        - {inputValue: use_gpu}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml

@@ -1,181 +0,0 @@
-name: Upload XGBoost model to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model, type: XGBoostModel}
-- {name: xgboost_version, type: String, optional: true}
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.16.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.16.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_XGBoost_model_to_Google_Cloud_Vertex_AI(
-          model_path,
-          xgboost_version = None,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          import shutil
-          import tempfile
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          # The serving container decides the model type based on the model file extension.
-          # So we need to rename the mode file (e.g. /tmp/inputs/model/data) to *.bst
-          _, renamed_model_path = tempfile.mkstemp(suffix=".bst")
-          shutil.copyfile(src=model_path, dst=renamed_model_path)
-
-          model = aiplatform.Model.upload_xgboost_model_file(
-              model_file_path=renamed_model_path,
-              xgboost_version=xgboost_version,
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload XGBoost model to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--xgboost-version", dest="xgboost_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_XGBoost_model_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: xgboost_version}
-        then:
-        - --xgboost-version
-        - {inputValue: xgboost_version}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/storage/download/component.yaml

@@ -1,35 +0,0 @@
-name: Download from GCS
-inputs:
-- {name: GCS path, type: String}
-outputs:
-- {name: Data}
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml'
-implementation:
-    container:
-        image: google/cloud-sdk
-        command:
-        - bash # Pattern comparison only works in Bash
-        - -ex
-        - -c
-        - |
-            if [ -n "${GOOGLE_APPLICATION_CREDENTIALS}" ]; then
-                gcloud auth activate-service-account --key-file="${GOOGLE_APPLICATION_CREDENTIALS}"
-            fi
-
-            uri="$0"
-            output_path="$1"
-
-            # Checking whether the URI points to a single blob, a directory or a URI pattern
-            # URI points to a blob when that URI does not end with slash and listing that URI only yields the same URI
-            if [[ "$uri" != */ ]] && (gcloud storage ls "$uri" | grep --fixed-strings --line-regexp "$uri"); then
-                mkdir -p "$(dirname "$output_path")"
-                gcloud storage cp --recursive "$uri" "$output_path"
-            else
-                mkdir -p "$output_path" # When source path is a directory, gsutil requires the destination to also be a directory
-                gcloud storage rsync --recursive "$uri" "$output_path" # gsutil cp has different path handling than Linux cp. It always puts the source directory (name) inside the destination directory. gsutil rsync does not have that problem.
-            fi
-        - inputValue: GCS path
-        - outputPath: Data

community-content/pipeline_components/image_ml_model_training/load_image_classification_model/component.yaml

@@ -1,112 +0,0 @@
-name: Load image classification model from tfhub
-description: |
-  Loads specified model from TFHub, creates layer to receive additional (3 channel) imagery data.
-  Args:
-    class_names (Sequence[str]):
-        Sequence of strings of categories for classification corresponding to input data.
-    loaded_model_path (str):
-        Output path for the loaded model.
-    image_size_path (str):
-        Output path for the model expected image size.
-    model_name (Optional[str]):
-        Name of the pre-trained image classification model to load from TFHub.
-        Eligible model_name:
-        - efficientnetv2-s
-        - efficientnetv2-m
-        - efficientnetv2-l
-        - efficientnetv2-s-21k
-        - efficientnetv2-m-21k
-        - efficientnetv2-l-21k
-        - efficientnetv2-xl-21k
-        - efficientnetv2-b0-21k
-        - efficientnetv2-b1-21k
-        - efficientnetv2-b2-21k
-        - efficientnetv2-b3-21k
-        - efficientnetv2-s-21k-ft1k
-        - efficientnetv2-m-21k-ft1k
-        - efficientnetv2-l-21k-ft1k
-        - efficientnetv2-xl-21k-ft1k
-        - efficientnetv2-b0-21k-ft1k
-        - efficientnetv2-b1-21k-ft1k
-        - efficientnetv2-b2-21k-ft1k
-        - efficientnetv2-b3-21k-ft1k
-        - efficientnetv2-b0
-        - efficientnetv2-b1
-        - efficientnetv2-b2
-        - efficientnetv2-b3
-        - efficientnet_b0
-        - efficientnet_b1
-        - efficientnet_b2
-        - efficientnet_b3
-        - efficientnet_b4
-        - efficientnet_b5
-        - efficientnet_b6
-        - efficientnet_b7
-        - bit_s-r50x1
-        - inception_v3
-        - inception_resnet_v2
-        - resnet_v1_50
-        - resnet_v1_101
-        - resnet_v1_152
-        - resnet_v2_50
-        - resnet_v2_101
-        - resnet_v2_152
-        - nasnet_large
-        - nasnet_mobile
-        - pnasnet_large
-        - mobilenet_v2_100_224
-        - mobilenet_v2_130_224
-        - mobilenet_v2_140_224
-        - mobilenet_v3_small_100_224
-        - mobilenet_v3_small_075_224
-        - mobilenet_v3_large_100_224
-        - mobilenet_v3_large_075_224
-    dropout_rate (Optional[float]):
-        Fraction of input units to drop in the last layer. Value should be between 0.0 and 1.0.
-    trainable (Optional[bool]):
-        If true fine tuning will be performed on entire Hub model. If false only additional
-        layers will be trained.
-    l2_regularization_penalty (Optional[float]):
-        l2 regularization penalty.
-inputs:
-- {name: class_names, type: 'typing.List[str]', description: List of class names corresponding
-    to the input image data}
-- {name: model_name, type: String, description: Name of the TFHub model to load, default: efficientnetv2-xl-21k,
-  optional: true}
-- {name: dropout_rate, type: Float, description: Dropout rate, default: '0.2', optional: true}
-- name: trainable
-  type: Boolean
-  description: True if fine tuning should be performed
-  default: "True"
-  optional: true
-- {name: l2_regularization_penalty, type: Float, description: Regularization penalty,
-  default: '0.0001', optional: true}
-outputs:
-- {name: loaded_model_path, type: TensorflowSavedModel, description: Output path for
-    the loaded model}
-- {name: image_size_path, type: HeightWidth}
-implementation:
-  container:
-    image: us-docker.pkg.dev/vertex-ai/ready-to-go-image-classification/image-components:v0.2
-    # command is a list of strings (command-line arguments).
-    # The YAML language has two syntaxes for lists and you can use either of them.
-    # Here we use the "flow syntax" - comma-separated strings inside square brackets.
-    command: [
-      python3,
-      # Path of the program inside the container
-      /pipelines/component/src/loading_component.py,
-      --loaded-model-path,
-      {outputPath: loaded_model_path},
-      --class-names,
-      {inputValue: class_names},
-      --model-name,
-      {inputValue: model_name},
-      --dropout-rate,
-      {inputValue: dropout_rate},
-      --trainable,
-      {inputValue: trainable},
-      --l2-regularization-penalty,
-      {inputValue: l2_regularization_penalty},
-      --image-size-path,
-      {outputPath: image_size_path},
-    ]

community-content/pipeline_components/image_ml_model_training/pipeline.py

@@ -1,62 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-from kfp.v2 import dsl
-
-# %% Loading components
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url('https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml')
-deploy_model_to_endpoint_op = components.load_component_from_url('https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml')
-transcode_imagedataset_tfrecord_from_csv_op = components.load_component_from_url('https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/community-content/pipeline_components/image_ml_model_training/transcode_tfrecord_image_dataset_from_csv/component.yaml')
-load_image_classification_model_from_tfhub_op = components.load_component_from_url('https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/b5b65198a6c2ffe8c0fa2aa70127e3325752df68/community-content/pipeline_components/image_ml_model_training/load_image_classification_model/component.yaml')
-preprocess_image_data_op = components.load_component_from_url('https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/community-content/pipeline_components/image_ml_model_training/preprocess_image_data/component.yaml')
-train_tensorflow_image_classification_model_op = components.load_component_from_url('https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/community-content/pipeline_components/image_ml_model_training/train_image_classification_model/component.yaml')
-
-
-# %% Pipeline definition
-def image_classification_pipeline():
-    class_names = ['daisy', 'dandelion', 'roses', 'sunflowers', 'tulips']
-    csv_image_data_path = 'gs://cloud-samples-data/ai-platform/flowers/flowers.csv'
-    deploy_model = False
-
-    image_data = dsl.importer(
-        artifact_uri=csv_image_data_path, artifact_class=dsl.Dataset).output
-
-    image_tfrecord_data = transcode_imagedataset_tfrecord_from_csv_op(
-        csv_image_data_path=image_data,
-        class_names=class_names
-    ).outputs['tfrecord_image_data_path']
-
-    loaded_model_outputs = load_image_classification_model_from_tfhub_op(
-        class_names=class_names,
-    ).outputs
-
-    preprocessed_data = preprocess_image_data_op(
-        image_tfrecord_data,
-        height_width_path=loaded_model_outputs['image_size_path'],
-    ).outputs
-
-    trained_model = (train_tensorflow_image_classification_model_op(
-        preprocessed_training_data_path = preprocessed_data['preprocessed_training_data_path'],
-        preprocessed_validation_data_path = preprocessed_data['preprocessed_validation_data_path'],
-        model_path=loaded_model_outputs['loaded_model_path']).
-                   set_cpu_limit('96').
-                   set_memory_limit('128G').
-                   add_node_selector_constraint('cloud.google.com/gke-accelerator', 'NVIDIA_TESLA_A100').
-                   set_gpu_limit('8').
-                   outputs['trained_model_path'])
-
-    vertex_model_name = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op(
-        model=trained_model,
-    ).outputs['model_name']
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs['endpoint_name']
-
-pipeline_func = image_classification_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/pipeline_components/image_ml_model_training/preprocess_image_data/component.yaml

@@ -1,57 +0,0 @@
-name: Preprocess image data
-description: |
-  Preprocess the image data and split between train and validation.
-  Args:
-    input_data_path (str):
-        Input path for the TFRecord image data. Data will be formatted as 'label' (encoded image
-        label), and 'image_raw' (the binary string of the image data).
-    height_width_path (str):
-        Path to square height and width to resize images to. File should contain single float value.
-        Value is dependent on training model.
-    preprocessed_training_data_path (str):
-        Output path for the TFRecord training data. Data will be formatted as 'label' (encoded image
-        label), and 'image_raw' (the binary string of the image data).
-    preprocessed_validation_data_path (str):
-        Output path for the TFRecord validation data. Data will be formatted as 'label' (encoded
-        image label), and 'image_raw' (the binary string of the image data).
-    validation_split (Optional[float]):
-        Fraction of data that will make up validation dataset. Value should be between 0.0 and 1.0.
-    seed (Optional[int]):
-        The global random seed to ensure the system gets a unique random sequence
-        that is deterministic (https://www.tensorflow.org/api_docs/python/tf/random/set_seed).
-inputs:
-- {name: input_data_path, type: ImageDatasetTFRecord, description: 'Input path for
-    the TFRecord image data,'}
-- {name: height_width_path, type: HeightWidth, description: 'Path to square height and width to
-    resize images to,'}
-- {name: validation_split, type: Float, description: 'Fraction of data that will make
-    up validation dataset,', default: '0.2', optional: true}
-- {name: seed, type: Integer, description: Random seed, default: '0', optional: true}
-outputs:
-- {name: preprocessed_training_data_path, type: ImageDatasetTFRecord, description: 'Output
-    path for the training data,'}
-- {name: preprocessed_validation_data_path, type: ImageDatasetTFRecord, description: 'Output
-    path for the validation data,'}
-implementation:
-  container:
-    image: us-docker.pkg.dev/vertex-ai/ready-to-go-image-classification/image-components:v0.2
-    # command is a list of strings (command-line arguments).
-    # The YAML language has two syntaxes for lists and you can use either of them.
-    # Here we use the "flow syntax" - comma-separated strings inside square brackets.
-    command: [
-      python3,
-      # Path of the program inside the container
-      /pipelines/component/src/preprocessing_component.py,
-      --input-data-path,
-      {inputPath: input_data_path},
-      --height-width-path,
-      {inputPath: height_width_path},
-      --validation-split,
-      {inputValue: validation_split},
-      --seed,
-      {inputValue: seed},
-      --preprocessed-training-data-path,
-      {outputPath: preprocessed_training_data_path},
-      --preprocessed-validation-data-path,
-      {outputPath: preprocessed_validation_data_path},
-    ]

community-content/pipeline_components/image_ml_model_training/train_image_classification_model/component.yaml

@@ -1,90 +0,0 @@
-name: Train tensorflow image classification model
-description: |
-  Creates a trained image classification TensorFlow model.
-  Args:
-    preprocessed_training_data_path (str):
-        Input path to the TFRecord training data. Data will be formatted as 'label' (encoded image
-        label), and 'image_raw' (the binary string of the image data).
-    preprocessed_validation_data_path (str):
-        Input path to the TFRecord validation data. Data will be formatted as 'label' (encoded
-        image label), and 'image_raw' (the binary string of the image data).
-    model_path (str):
-        Input path to the loaded pre-trained model.
-    trained_model_path (str):
-        Output path to save the trained model to.
-    optimizer_name (Optional[str]):
-        Name of the tf.keras optimizer. Available optimizers are listed at
-        https://keras.io/api/optimizers/
-    optimizer_parameters (Optional[Dict[str, str]]):
-        Optimizer parameters.
-    loss_function_name (Optional[str]):
-        Name of the loss function.
-    loss_function_parameters (Optional[Dict[str, str]]):
-        Loss function parameters.
-    number_of_epochs (Optional[int]):
-        Number of training iterations over data.
-    metric_names (Optional[Sequence[str]]):
-        List of tf.keras.metrics to be evaluated by the model during training and testing. Available
-        metrics are listed at https://keras.io/api/metrics/.
-    seed Optional(int):
-        The global random seed to ensure the system gets a unique random sequence
-        that is deterministic (https://www.tensorflow.org/api_docs/python/tf/random/set_seed).
-inputs:
-- {name: preprocessed_training_data_path, type: ImageDatasetTFRecord, description: 'Input
-    path for the training data,'}
-- {name: preprocessed_validation_data_path, type: ImageDatasetTFRecord, description: 'Input
-    path for the validation data,'}
-- {name: model_path, type: TensorflowSavedModel, description: 'Input path for the
-    model,'}
-- {name: optimizer_name, type: String, description: 'Name of the optimizer,', default: SGD,
-  optional: true}
-- {name: optimizer_parameters, type: 'typing.Dict[str, str]', description: 'Optimizer
-    parameters,', default: '{}', optional: true}
-- {name: loss_function_name, type: String, description: 'Name of the loss function,',
-  default: CategoricalCrossentropy, optional: true}
-- {name: loss_function_parameters, type: 'typing.Dict[str, str]', description: 'Loss
-    function parameters,', default: '{}', optional: true}
-- {name: number_of_epochs, type: Integer, description: 'Number of epochs,', default: '10',
-  optional: true}
-- {name: metric_names, type: 'typing.List[str]', description: 'List of metrics to
-    use,', default: '["accuracy"]', optional: true}
-- {name: seed, type: Integer, description: 'Random seed,', default: '0', optional: true}
-- {name: batch_size, type: Integer, description: Batch size, default: '16', optional: true}
-outputs:
-- {name: trained_model_path, type: TensorflowSavedModel, description: 'Output path
-    for the saved model,'}
-implementation:
-  container:
-    image: us-docker.pkg.dev/vertex-ai/ready-to-go-image-classification/image-components:v0.2
-    # command is a list of strings (command-line arguments).
-    # The YAML language has two syntaxes for lists and you can use either of them.
-    # Here we use the "flow syntax" - comma-separated strings inside square brackets.
-    command: [
-      python3,
-      # Path of the program inside the container
-      /pipelines/component/src/training_component.py,
-      --preprocessed-training-data-path,
-      {inputPath: preprocessed_training_data_path},
-      --preprocessed-validation-data-path,
-      {inputPath: preprocessed_validation_data_path},
-      --model-path,
-      {inputPath: model_path},
-      --trained-model-path,
-      {outputPath: trained_model_path},
-      --optimizer-name,
-      {inputValue: optimizer_name},
-      --loss-function-name,
-      {inputValue: loss_function_name},
-      --number-of-epochs,
-      {inputValue: number_of_epochs},
-      --seed,
-      {inputValue: seed},
-      --batch-size,
-      {inputValue: batch_size},
-      --metric-names,
-      {inputValue: metric_names},
-      --optimizer-parameters,
-      {inputValue: optimizer_parameters},
-      --loss-function-parameters,
-      {inputValue: loss_function_parameters},
-    ]

community-content/pipeline_components/image_ml_model_training/transcode_tfrecord_image_dataset_from_csv/component.yaml

@@ -1,37 +0,0 @@
-name: Transcode imagedataset tfrecord from csv
-description: |
-  Transcodes CSV Data into TFRecord file of TFExamples.
-  Args:
-    csv_image_data_path (str):
-        Path to the CSV image data. Data must include 'image_filepath' (Path to image file) and
-        'image_label' (output for a prediction) fields.
-    class_names (Sequence[str]):
-        Sequence of strings of categories for classification corresponding to input data.
-    tfrecord_image_data_path (str):
-        Output path for the TFRecord image data. Data will be formatted as 'label' (encoded image
-        label), and 'image_raw' (the binary string of the image data).
-inputs:
-- {name: csv_image_data_path, type: ImageDatasetCSV, description: Input path for the
-    CSV image data}
-- {name: class_names, type: 'typing.List[str]', description: List of class names corresponding
-    to the input image data}
-outputs:
-- {name: tfrecord_image_data_path, type: ImageDatasetTFRecord, description: Output
-    path for the TFRecord image data}
-implementation:
-  container:
-    image: us-docker.pkg.dev/vertex-ai/ready-to-go-image-classification/image-components:v0.2
-    # command is a list of strings (command-line arguments).
-    # The YAML language has two syntaxes for lists and you can use either of them.
-    # Here we use the "flow syntax" - comma-separated strings inside square brackets.
-    command: [
-      python3,
-      # Path of the program inside the container
-      /pipelines/component/src/transcoding_csv_component.py,
-      --csv-image-data-path,
-      {inputPath: csv_image_data_path},
-      --tfrecord-image-data-path,
-      {outputPath: tfrecord_image_data_path},
-      --class-names,
-      {inputValue: class_names},
-    ]

community-content/pipeline_components/image_ml_model_training/transcode_tfrecord_image_dataset_from_jsonl/component.yaml

@@ -1,39 +0,0 @@
-name: Transcode imagedataset tfrecord from jsonlines
-description: |
-  Transcodes JSONL Data into TFRecord file of TFExamples.
-  Args:
-    jsonl_image_data_path (str):
-        Input path for the JSONL image data
-        Path to the JSONL image data. Each line corresponds to a JSON input describing an image.
-        Schema follows AutoML image classification JSONL format
-        https://cloud.google.com/vertex-ai/docs/image-data/classification/prepare-data#json-lines.
-    class_names (Sequence[str]):
-        Sequence of strings of categories for classification corresponding to input data.
-    tfrecord_image_data_path (str):
-        Output path for the TFRecord image data. Data will be formatted as 'label' (encoded image
-        label), and 'image_raw' (the binary string of the image data).
-inputs:
-- {name: jsonl_image_data_path, type: ImageDatasetJsonLines, description: Input path
-    for the JSONL image data}
-- {name: class_names, type: 'typing.List[str]', description: List of class names corresponding
-    to the input image data}
-outputs:
-- {name: tfrecord_image_data_path, type: ImageDatasetTFRecord, description: Output
-    path for the TFRecord image data}
-implementation:
-  container:
-    image: us-docker.pkg.dev/vertex-ai/ready-to-go-image-classification/image-components:v0.2
-    # command is a list of strings (command-line arguments).
-    # The YAML language has two syntaxes for lists and you can use either of them.
-    # Here we use the "flow syntax" - comma-separated strings inside square brackets.
-    command: [
-      python3,
-      # Path of the program inside the container
-      /pipelines/component/src/transcoding_jsonl_component.py,
-      --jsonl-image-data-path,
-      {inputPath: jsonl_image_data_path},
-      --tfrecord-image-data-path,
-      {outputPath: tfrecord_image_data_path},
-      --class-names,
-      {inputValue: class_names},
-    ]

community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml

@@ -1,113 +0,0 @@
-name: Binarize column using Pandas on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/pandas/Binarize_column/in_CSV_format/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: column_name, type: String}
-- {name: predicate, type: String, default: '> 0', optional: true}
-- {name: new_column_name, type: String, optional: true}
-- name: keep_original_column
-  type: Boolean
-  default: "False"
-  optional: true
-outputs:
-- {name: transformed_table, type: CSV}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.3' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def binarize_column_using_Pandas_on_CSV_data(
-          table_path,
-          transformed_table_path,
-          column_name,
-          predicate = "> 0",
-          new_column_name = None,
-          keep_original_column = False,
-      ):
-          import pandas
-
-          df = pandas.read_csv(table_path).convert_dtypes()
-          original_series = df[column_name]
-
-          # Dynamically executing the predicate code
-          # Variable namespace for code execution
-          namespace = dict(x=original_series)
-          # I though that there should be no space before `predicate` so that "dot" predicate methods like ".between(min, max)" work.
-          # However Python allows spaces before dot: `df .isna()`.
-          # So having a space is not a problem
-          transform_code = f"""new_series_boolean = x {predicate}"""
-          # Note: exec() takes no keyword arguments
-          # exec(__source=transform_code, __globals=namespace)
-          exec(transform_code, namespace)
-          new_series_boolean = namespace["new_series_boolean"]
-
-          # There are multiple ways to convert boolean column to integer.
-          # .apply(int) might be faster. https://stackoverflow.com/a/49804868/1497385
-          # TODO: Do a proper benchmark.
-          new_series = new_series_boolean.apply(int)
-          # new_series = new_series_boolean.astype(int)
-          # new_series = new_series_boolean.replace({False: 0, True: 1})
-
-          if new_column_name:
-              df.insert(loc=0, column=new_column_name, value=new_series)
-              if not keep_original_column:
-                  df = df.drop(columns=[column_name])
-          else:
-              df[column_name] = new_series
-
-          df.to_csv(transformed_table_path, index=False)
-
-      def _deserialize_bool(s) -> bool:
-          from distutils.util import strtobool
-          return strtobool(s) == 1
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Binarize column using Pandas on CSV data', description='')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--column-name", dest="column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--predicate", dest="predicate", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--new-column-name", dest="new_column_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--keep-original-column", dest="keep_original_column", type=_deserialize_bool, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--transformed-table", dest="transformed_table_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = binarize_column_using_Pandas_on_CSV_data(**_parsed_args)
-    args:
-    - --table
-    - {inputPath: table}
-    - --column-name
-    - {inputValue: column_name}
-    - if:
-        cond: {isPresent: predicate}
-        then:
-        - --predicate
-        - {inputValue: predicate}
-    - if:
-        cond: {isPresent: new_column_name}
-        then:
-        - --new-column-name
-        - {inputValue: new_column_name}
-    - if:
-        cond: {isPresent: keep_original_column}
-        then:
-        - --keep-original-column
-        - {inputValue: keep_original_column}
-    - --transformed-table
-    - {outputPath: transformed_table}

community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml

@@ -1,75 +0,0 @@
-name: Fill all missing values using Pandas on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: replacement_value, type: String, default: '0', optional: true}
-- {name: column_names, type: JsonArray, optional: true}
-outputs:
-- {name: transformed_table, type: CSV}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.1' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.1' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def fill_all_missing_values_using_Pandas_on_CSV_data(
-          table_path,
-          transformed_table_path,
-          replacement_value = "0",
-          column_names = None,
-      ):
-          import pandas
-
-          df = pandas.read_csv(
-              table_path,
-              dtype="string",
-          )
-
-          for column_name in column_names or df.columns:
-              df[column_name] = df[column_name].fillna(value=replacement_value)
-
-          df.to_csv(
-              transformed_table_path, index=False,
-          )
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Fill all missing values using Pandas on CSV data', description='')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--replacement-value", dest="replacement_value", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--column-names", dest="column_names", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--transformed-table", dest="transformed_table_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = fill_all_missing_values_using_Pandas_on_CSV_data(**_parsed_args)
-    args:
-    - --table
-    - {inputPath: table}
-    - if:
-        cond: {isPresent: replacement_value}
-        then:
-        - --replacement-value
-        - {inputValue: replacement_value}
-    - if:
-        cond: {isPresent: column_names}
-        then:
-        - --column-names
-        - {inputValue: column_names}
-    - --transformed-table
-    - {outputPath: transformed_table}

community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml

@@ -1,59 +0,0 @@
-name: Select columns using Pandas on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/pandas/Select_columns/in_CSV_format/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: column_names, type: JsonArray}
-outputs:
-- {name: transformed_table, type: CSV}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.2' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.2' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def select_columns_using_Pandas_on_CSV_data(
-          table_path,
-          transformed_table_path,
-          column_names,
-      ):
-          import pandas
-
-          df = pandas.read_csv(
-              table_path,
-              dtype="string",
-          )
-          df = df[column_names]
-          df.to_csv(transformed_table_path, index=False)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Select columns using Pandas on CSV data', description='')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--column-names", dest="column_names", type=json.loads, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--transformed-table", dest="transformed_table_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = select_columns_using_Pandas_on_CSV_data(**_parsed_args)
-    args:
-    - --table
-    - {inputPath: table}
-    - --column-names
-    - {inputValue: column_names}
-    - --transformed-table
-    - {outputPath: transformed_table}

community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml

@@ -1,102 +0,0 @@
-name: Create fully connected tensorflow network
-description: Creates fully-connected network in Tensorflow SavedModel format
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/tensorflow/Create_fully_connected_network/component.yaml'}
-inputs:
-- {name: input_size, type: Integer}
-- {name: hidden_layer_sizes, type: JsonArray, default: '[]', optional: true}
-- {name: output_size, type: Integer, default: '1', optional: true}
-- {name: activation_name, type: String, default: relu, optional: true}
-- {name: output_activation_name, type: String, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: model, type: TensorflowSavedModel}
-implementation:
-  container:
-    image: tensorflow/tensorflow:2.7.0
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def create_fully_connected_tensorflow_network(
-          input_size,
-          model_path,
-          hidden_layer_sizes = [],
-          output_size = 1,
-          activation_name = "relu",
-          output_activation_name = None,
-          random_seed = 0,
-      ):
-          """Creates fully-connected network in Tensorflow SavedModel format"""
-          import tensorflow as tf
-          tf.random.set_seed(seed=random_seed)
-
-          model = tf.keras.models.Sequential()
-          model.add(tf.keras.Input(shape=(input_size,)))
-          for layer_size in hidden_layer_sizes:
-              model.add(tf.keras.layers.Dense(units=layer_size, activation=activation_name))
-          # The last layer is left without activation
-          model.add(tf.keras.layers.Dense(units=output_size, activation=output_activation_name))
-
-          print(model.summary())
-
-          # Using tf.keras.models.save_model instead of tf.saved_model.save to prevent downstream error:
-          #tf.saved_model.save(model, model_path)
-          # ValueError: Unable to create a Keras model from this SavedModel.
-          # This SavedModel was created with `tf.saved_model.save`, and lacks the Keras metadata.
-          # Please save your Keras model by calling `model.save`or `tf.keras.models.save_model`.
-          # See https://github.com/keras-team/keras/issues/16451
-          tf.keras.models.save_model(model, model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Create fully connected tensorflow network', description='Creates fully-connected network in Tensorflow SavedModel format')
-      _parser.add_argument("--input-size", dest="input_size", type=int, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--hidden-layer-sizes", dest="hidden_layer_sizes", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-size", dest="output_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--activation-name", dest="activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-activation-name", dest="output_activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = create_fully_connected_tensorflow_network(**_parsed_args)
-    args:
-    - --input-size
-    - {inputValue: input_size}
-    - if:
-        cond: {isPresent: hidden_layer_sizes}
-        then:
-        - --hidden-layer-sizes
-        - {inputValue: hidden_layer_sizes}
-    - if:
-        cond: {isPresent: output_size}
-        then:
-        - --output-size
-        - {inputValue: output_size}
-    - if:
-        cond: {isPresent: activation_name}
-        then:
-        - --activation-name
-        - {inputValue: activation_name}
-    - if:
-        cond: {isPresent: output_activation_name}
-        then:
-        - --output-activation-name
-        - {inputValue: output_activation_name}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --model
-    - {outputPath: model}

community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml

@@ -1,100 +0,0 @@
-name: Predict with TensorFlow model on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/tensorflow/Predict/on_CSV/component.yaml'}
-inputs:
-- {name: dataset, type: CSV}
-- {name: model, type: TensorflowSavedModel}
-- {name: label_column_name, type: String, optional: true}
-- {name: batch_size, type: Integer, default: '1000', optional: true}
-outputs:
-- {name: predictions}
-implementation:
-  container:
-    image: tensorflow/tensorflow:2.9.1
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def predict_with_TensorFlow_model_on_CSV_data(
-          dataset_path,
-          model_path,
-          predictions_path,
-          label_column_name = None,
-          batch_size = 1000,
-      ):
-          import numpy
-          import tensorflow as tf
-
-          model = tf.saved_model.load(export_dir=model_path)
-
-          dataset = tf.data.experimental.make_csv_dataset(
-              file_pattern=dataset_path,
-              batch_size=batch_size,
-              label_name=label_column_name,
-              header=True,
-              num_epochs=1,
-              shuffle=False,
-              ignore_errors=False,
-          )
-
-          def stack_feature_batches(features_batch):
-              # Need to stack individual feature columns to create a single feature tensor
-              # Need to cast all column tensor types to float to prevent errors.
-              list_of_feature_batches = list(
-                  tf.cast(x=feature_batch, dtype=tf.float32)
-                  for feature_batch in features_batch.values()
-              )
-              return tf.stack(list_of_feature_batches, axis=-1)
-
-          def transform_features_and_drop_labels(features_batch, labels_batch):
-              return stack_feature_batches(features_batch)
-
-          dataset_map_fn = (
-              transform_features_and_drop_labels
-              if label_column_name
-              else stack_feature_batches
-          )
-
-          dataset = dataset.map(dataset_map_fn)
-
-          with open(predictions_path, "w") as predictions_file:
-              for features_batch in dataset:
-                  predictions_tensor = model(features_batch)
-                  numpy.savetxt(predictions_file, predictions_tensor.numpy())
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Predict with TensorFlow model on CSV data', description='')
-      _parser.add_argument("--dataset", dest="dataset_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-size", dest="batch_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--predictions", dest="predictions_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = predict_with_TensorFlow_model_on_CSV_data(**_parsed_args)
-    args:
-    - --dataset
-    - {inputPath: dataset}
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: label_column_name}
-        then:
-        - --label-column-name
-        - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: batch_size}
-        then:
-        - --batch-size
-        - {inputValue: batch_size}
-    - --predictions
-    - {outputPath: predictions}

community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml

@@ -1,170 +0,0 @@
-name: Train model using Keras on CSV
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml'}
-inputs:
-- {name: training_data, type: CSV}
-- {name: model, type: TensorflowSavedModel}
-- {name: label_column_name, type: String}
-- {name: loss_function_name, type: String, default: mean_squared_error, optional: true}
-- {name: number_of_epochs, type: Integer, default: '1', optional: true}
-- {name: learning_rate, type: Float, default: '0.1', optional: true}
-- {name: optimizer_name, type: String, default: Adadelta, optional: true}
-- {name: optimizer_parameters, type: JsonObject, optional: true}
-- {name: batch_size, type: Integer, default: '32', optional: true}
-- {name: metric_names, type: JsonArray, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: trained_model, type: TensorflowSavedModel}
-implementation:
-  container:
-    image: tensorflow/tensorflow:2.8.0
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_model_using_Keras_on_CSV(
-          training_data_path,
-          model_path,
-          trained_model_path,
-          label_column_name,
-          loss_function_name = "mean_squared_error",
-          number_of_epochs = 1,
-          learning_rate = 0.1,
-          optimizer_name = "Adadelta",
-          optimizer_parameters = None,
-          batch_size = 32,
-          metric_names = None,
-          random_seed = 0,
-      ):
-          import tensorflow as tf
-          tf.random.set_seed(seed=random_seed)
-
-          # Loading model using Keras. Model loaded using TensorFlow does not have .fit.
-          #model = tf.saved_model.load(export_dir=model_path)
-          keras_model = tf.keras.models.load_model(filepath=model_path)
-
-          optimizer_parameters = optimizer_parameters or {}
-          optimizer_parameters["learning_rate"] = learning_rate
-          optimizer_config = {
-              "class_name": optimizer_name,
-              "config": optimizer_parameters,
-          }
-          optimizer = tf.keras.optimizers.get(optimizer_config)
-          loss = tf.keras.losses.get(loss_function_name)
-
-          training_dataset = tf.data.experimental.make_csv_dataset(
-              file_pattern=training_data_path,
-              batch_size=batch_size,
-              label_name=label_column_name,
-              header=True,
-              # Need to specify num_epochs=1 otherwise the training becomes infinite
-              num_epochs=1,
-              shuffle=True,
-              shuffle_seed=random_seed,
-              ignore_errors=True,
-          )
-          def stack_feature_batches(features_batch, labels_batch):
-              # Need to stack individual feature columns to create a single feature tensor
-              # Need to cast all column tensor types to float to prevent error:
-              # TypeError: Tensors in list passed to 'values' of 'Pack' Op have types [int32, float32, float32, int32, int32] that don't all match.
-              list_of_feature_batches = list(tf.cast(x=feature_batch, dtype=tf.float32) for feature_batch in features_batch.values())
-              return tf.stack(list_of_feature_batches, axis=-1), labels_batch
-
-          training_dataset = training_dataset.map(stack_feature_batches)
-
-          # Need to compile the model to prevent error:
-          # ValueError: No gradients provided for any variable: [..., ...].
-          keras_model.compile(
-              optimizer=optimizer,
-              loss=loss,
-              metrics=metric_names,
-          )
-          keras_model.fit(
-              training_dataset,
-              epochs=number_of_epochs,
-          )
-
-          # Using tf.keras.models.save_model instead of tf.saved_model.save to prevent downstream error:
-          #tf.saved_model.save(keras_model, trained_model_path)
-          # ValueError: Unable to create a Keras model from this SavedModel.
-          # This SavedModel was created with `tf.saved_model.save`, and lacks the Keras metadata.
-          # Please save your Keras model by calling `model.save`or `tf.keras.models.save_model`.
-          # See https://github.com/keras-team/keras/issues/16451
-          tf.keras.models.save_model(keras_model, trained_model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train model using Keras on CSV', description='')
-      _parser.add_argument("--training-data", dest="training_data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--loss-function-name", dest="loss_function_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--number-of-epochs", dest="number_of_epochs", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--learning-rate", dest="learning_rate", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-name", dest="optimizer_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-parameters", dest="optimizer_parameters", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-size", dest="batch_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--metric-names", dest="metric_names", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--trained-model", dest="trained_model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_model_using_Keras_on_CSV(**_parsed_args)
-    args:
-    - --training-data
-    - {inputPath: training_data}
-    - --model
-    - {inputPath: model}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: loss_function_name}
-        then:
-        - --loss-function-name
-        - {inputValue: loss_function_name}
-    - if:
-        cond: {isPresent: number_of_epochs}
-        then:
-        - --number-of-epochs
-        - {inputValue: number_of_epochs}
-    - if:
-        cond: {isPresent: learning_rate}
-        then:
-        - --learning-rate
-        - {inputValue: learning_rate}
-    - if:
-        cond: {isPresent: optimizer_name}
-        then:
-        - --optimizer-name
-        - {inputValue: optimizer_name}
-    - if:
-        cond: {isPresent: optimizer_parameters}
-        then:
-        - --optimizer-parameters
-        - {inputValue: optimizer_parameters}
-    - if:
-        cond: {isPresent: batch_size}
-        then:
-        - --batch-size
-        - {inputValue: batch_size}
-    - if:
-        cond: {isPresent: metric_names}
-        then:
-        - --metric-names
-        - {inputValue: metric_names}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --trained-model
-    - {outputPath: trained_model}

community-content/pytorch_efficient_training/README.md

@@ -1,33 +0,0 @@
-# PyTorch Efficient Training Examples
-
-This folder provides PyTorch efficient training examples using ResNet-50 and ImageNet data.
-
-## Requirements
-
-```shell
-pip install --upgrade pip
-pip install -r requirements.txt
-```
-
-## Description
-
-* resnet.py - Train ResNet-50 on single GPU.
-* resnet_dp.py - Train ResNet-50 on single node multiple GPUs with `DataParallel` strategy.
-* resnet_ddp.py - Train ResNet-50 on single node multiple GPUs with `DistributedDataParallel` strategy.
-* resnet_ddp_wds.py - Train ResNet-50 on single node multiple GPUs with `DistributedDataParallel` strategy and `Webdataset`.
-* resnet_fsdp.py - Train ResNet-50 on single node multiple GPUs with `FullyShardedDataParallel` strategy.
-* resnet_fsdp_wds.py - Train ResNet-50 on single node multiple GPUs with `FullyShardedDataParallel` strategy and `Webdataset`.
-* shard_imagenet.py - Shard ImagNet individual files into `tar` files.
-
-## Benchmark
-
-When run the benchmark on Nvidia T4 GPUs using ImageNet validation dataset, you can get the result like:
-Strategy               | Seconds/Epoch - Local Data | Seconds/Epoch - Cloud Data
----------------------- | -------------------------- | --------------------------
-On 1 GPU               | 489                        | 804 (2x slower)
-On 4 GPUs (DP)         | 157                        | 738 (5x slower)
-On 4 GPUs (DDP)        | 134                        | 432 (3x slower)
-On 4 GPUs (DDP + WDS)  | 131                        | 133 (same performance)
-On 4 GPUs (FSDP)       | 139                        | 353 (3x slower)
-On 4 GPUs (FSDP + WDS) | 138                        | 135 (same performance)
-

community-content/pytorch_efficient_training/requirements.txt

@@ -1 +0,0 @@
-webdataset == 0.2.26

community-content/pytorch_efficient_training/resnet.py

@@ -1,197 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on single GPU."""
-
-import argparse
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image, target = image.to(device), target.to(device)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image, target = image.to(device), target.to(device)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def run_training(args):
-  """Run training and evaluation."""
-  # Create model.
-  model = resnet50(weights=None)
-  model = model.to(args.device)
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=True,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True)
-  print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-        f'num workers: {train_dataloader.num_workers}, '
-        f'batch size: {args.train_batch_size}, '
-        f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True)
-  print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-        f'num workers: {eval_dataloader.num_workers}, '
-        f'batch size: {args.eval_batch_size}, '
-        f'batches/epoch: {len(eval_dataloader)}')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-  print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  args.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-
-  print('Launch job on 1 GPU')
-  run_training(args)
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_ddp.py

@@ -1,234 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with DDP."""
-
-import argparse
-import os
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torch.distributed as dist
-import torch.multiprocessing as mp
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image = image.to(device, non_blocking=True)
-    target = target.to(device, non_blocking=True)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image = image.to(device, non_blocking=True)
-      target = target.to(device, non_blocking=True)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def worker(gpu, args):
-  """Run training and evaluation."""
-  # Init process group.
-  print(f'Initiating process {gpu}')
-  dist.init_process_group(
-      backend='nccl',
-      init_method='env://',
-      world_size=args.gpus,
-      rank=gpu)
-
-  # Create model.
-  model = resnet50(weights=None)
-  torch.cuda.set_device(gpu)
-  model.to(args.device)
-  model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)
-  model = nn.parallel.DistributedDataParallel(model, device_ids=[gpu])
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_sampler = torch.utils.data.distributed.DistributedSampler(
-      train_dataset, num_replicas=args.gpus, rank=gpu)
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      sampler=train_sampler)
-  if gpu == 0:
-    print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-          f'num workers: {train_dataloader.num_workers}, '
-          f'global batch size: {args.train_batch_size * args.gpus}, '
-          f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_sampler = torch.utils.data.distributed.DistributedSampler(
-      eval_dataset, num_replicas=args.gpus, rank=gpu)
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True,
-      sampler=eval_sampler)
-  if gpu == 0:
-    print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-          f'num workers: {eval_dataloader.num_workers}, '
-          f'batch size: {args.eval_batch_size}, '
-          f'batches/epoch: {len(eval_dataloader)}')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    if gpu == 0:
-      print(f'Running epoch {epoch}')
-    train_sampler.set_epoch(epoch)
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    if gpu == 0:
-      print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    if gpu == 0:
-      print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-
-  if gpu == 0:
-    print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '8888'
-
-  args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-  print(f'Launch job on {args.gpus} GPUs with DDP')
-  mp.spawn(worker, nprocs=args.gpus, args=(args,))
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_ddp_wds.py

@@ -1,249 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with DDP."""
-
-import argparse
-import functools
-import itertools
-import math
-import os
-import time
-
-import torch
-from torch import nn
-import torch.distributed as dist
-import torch.multiprocessing as mp
-import torchmetrics
-from torchvision.models import resnet50
-from torchvision.transforms import transforms
-import webdataset as wds
-
-
-def wds_split(src, rank, world_size):
-  """Shards split function for webdataset."""
-  # The context of caller of this function is within multiple processes
-  # (by DDP world_size) and multiple workers (by dataloader_num_workers).
-  # So we totally have (world_size * num_workers) workers for processing data.
-  # NOTE: Raw data should be sharded to enough shards to make sure one process
-  # can handle at least one shard, otherwise the process may hang.
-  worker_id = 0
-  num_workers = 1
-  worker_info = torch.utils.data.get_worker_info()
-  if worker_info:
-    worker_id = worker_info.id
-    num_workers = worker_info.num_workers
-  for s in itertools.islice(src, rank * num_workers + worker_id, None,
-                            world_size * num_workers):
-    yield s
-
-
-def identity(x):
-  return x
-
-
-def create_wds_dataloader(rank, args, mode):
-  """Create webdataset dataset and dataloader."""
-  if mode == 'train':
-    transform = transforms.Compose([
-        transforms.RandomResizedCrop(224),
-        transforms.RandomHorizontalFlip(),
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    data_path = args.train_data_path
-    data_size = args.train_data_size
-    batch_size_local = args.train_batch_size
-    batch_size_global = args.train_batch_size * args.gpus
-    # Since webdataset disallows partial batch, we pad the last batch for train.
-    batches = int(math.ceil(data_size / batch_size_global))
-  else:
-    transform = transforms.Compose([
-        transforms.Resize(256),
-        transforms.CenterCrop(224),
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    data_path = args.eval_data_path
-    data_size = args.eval_data_size
-    batch_size_local = args.eval_batch_size
-    batch_size_global = args.eval_batch_size * args.gpus
-    # Since webdataset disallows partial batch, we drop the last batch for eval.
-    batches = int(data_size / batch_size_global)
-
-  dataset = wds.DataPipeline(
-      wds.SimpleShardList(data_path),
-      functools.partial(wds_split, rank=rank, world_size=args.gpus),
-      wds.tarfile_to_samples(),
-      wds.decode('pil'),
-      wds.to_tuple('jpg;png;jpeg cls'),
-      wds.map_tuple(transform, identity),
-      wds.batched(batch_size_local, partial=False),
-  )
-  num_workers = args.dataloader_num_workers
-  dataloader = wds.WebLoader(
-      dataset=dataset,
-      batch_size=None,
-      shuffle=False,
-      num_workers=num_workers,
-      persistent_workers=True if num_workers > 0 else False,
-      pin_memory=True).repeat(nbatches=batches)
-  print(f'{mode} dataloader | samples: {data_size}, '
-        f'num_workers: {num_workers}, '
-        f'local batch size: {batch_size_local}, '
-        f'global batch size: {batch_size_global}, '
-        f'batches: {batches}')
-  return dataloader
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image = image.to(device, non_blocking=True)
-    target = target.to(device, non_blocking=True)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image = image.to(device, non_blocking=True)
-      target = target.to(device, non_blocking=True)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def worker(gpu, args):
-  """Run training and evaluation."""
-  # Init process group.
-  print(f'Initiating process {gpu}')
-  dist.init_process_group(
-      backend='nccl',
-      init_method='env://',
-      world_size=args.gpus,
-      rank=gpu)
-
-  # Create model.
-  model = resnet50(weights=None)
-  torch.cuda.set_device(gpu)
-  model.to(args.device)
-  model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)
-  model = nn.parallel.DistributedDataParallel(model, device_ids=[gpu])
-
-  # Create dataloader.
-  train_dataloader = create_wds_dataloader(gpu, args, 'train')
-  eval_dataloader = create_wds_dataloader(gpu, args, 'eval')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    if gpu == 0:
-      print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    if gpu == 0:
-      print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    if gpu == 0:
-      print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-
-  if gpu == 0:
-    print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--train_data_size',
-      default=50000,
-      type=int,
-      help='data size for training')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  parser.add_argument(
-      '--eval_data_size',
-      default=50000,
-      type=int,
-      help='data size for evaluation')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '8888'
-
-  args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-  print(f'Launch job on {args.gpus} GPUs with DDP')
-  mp.spawn(worker, nprocs=args.gpus, args=(args,))
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_dp.py

@@ -1,207 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with DP."""
-
-import argparse
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image, target = image.to(device), target.to(device)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image, target = image.to(device), target.to(device)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def run_training(args):
-  """Run training and evaluation."""
-  # Create model.
-  model = resnet50(weights=None)
-  model = nn.DataParallel(model)
-  model = model.to(args.device)
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=True,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True)
-  print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-        f'num workers: {train_dataloader.num_workers}, '
-        f'global batch size: {args.train_batch_size}, '
-        f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True)
-  print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-        f'num workers: {eval_dataloader.num_workers}, '
-        f'global batch size: {args.eval_batch_size}, '
-        f'batches/epoch: {len(eval_dataloader)}')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-  print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-
-  args.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-  args.train_batch_size *= args.gpus
-  args.eval_batch_size *= args.gpus
-  args.dataloader_num_workers *= args.gpus
-
-  print(f'Launch job on {args.gpus} GPU with nn.DataParallel')
-  run_training(args)
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_fsdp.py

@@ -1,242 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with FSDP."""
-
-import argparse
-import functools
-import os
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torch.distributed as dist
-from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
-from torch.distributed.fsdp.wrap import size_based_auto_wrap_policy
-import torch.multiprocessing as mp
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image = image.to(device, non_blocking=True)
-    target = target.to(device, non_blocking=True)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image = image.to(device, non_blocking=True)
-      target = target.to(device, non_blocking=True)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def worker(gpu, args):
-  """Run training and evaluation."""
-  # Init process group.
-  print(f'Initiating process {gpu}')
-  dist.init_process_group(
-      backend='nccl',
-      init_method='env://',
-      world_size=args.gpus,
-      rank=gpu)
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_sampler = torch.utils.data.distributed.DistributedSampler(
-      train_dataset, num_replicas=args.gpus, rank=gpu)
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      sampler=train_sampler)
-  if gpu == 0:
-    print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-          f'num workers: {train_dataloader.num_workers}, '
-          f'global batch size: {args.train_batch_size * args.gpus}, '
-          f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_sampler = torch.utils.data.distributed.DistributedSampler(
-      eval_dataset, num_replicas=args.gpus, rank=gpu)
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True,
-      sampler=eval_sampler)
-  if gpu == 0:
-    print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-          f'num workers: {eval_dataloader.num_workers}, '
-          f'batch size: {args.eval_batch_size}, '
-          f'batches/epoch: {len(eval_dataloader)}')
-
-  # Wrap policy.
-  my_auto_wrap_policy = functools.partial(
-      size_based_auto_wrap_policy, min_num_params=100)
-  torch.cuda.set_device(gpu)
-
-  # Create model.
-  model = resnet50(weights=None)
-  model.to(args.device)
-  model = FSDP(model, auto_wrap_policy=my_auto_wrap_policy)
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    if gpu == 0:
-      print(f'Running epoch {epoch}')
-    train_sampler.set_epoch(epoch)
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    if gpu == 0:
-      print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    if gpu == 0:
-      print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-
-  if gpu == 0:
-    print('Done')
-  dist.destroy_process_group()
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=2,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-
-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '8888'
-
-  args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-  print(f'Launch job on {args.gpus} GPUs with FSDP')
-  mp.spawn(worker, nprocs=args.gpus, args=(args,))
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_fsdp_wds.py

@@ -1,240 +0,0 @@
-"""Train resnet on multiple GPUs with DDP."""
-
-import argparse
-import functools
-import itertools
-import math
-import os
-import time
-
-import torch
-from torch import nn
-import torch.distributed as dist
-from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
-from torch.distributed.fsdp.wrap import size_based_auto_wrap_policy
-import torch.multiprocessing as mp
-import torchmetrics
-from torchvision.models import resnet50
-from torchvision.transforms import transforms
-import webdataset as wds
-
-
-def wds_split(src, rank, world_size):
-  """Shards split function for webdataset."""
-  # The context of caller of this function is within multiple processes
-  # (by DDP world_size) and multiple workers (by dataloader_num_workers).
-  # So we totally have (world_size * num_workers) workers for processing data.
-  # NOTE: Raw data should be sharded to enough shards to make sure one process
-  # can handle at least one shard, otherwise the process may hang.
-  worker_id = 0
-  num_workers = 1
-  worker_info = torch.utils.data.get_worker_info()
-  if worker_info:
-    worker_id = worker_info.id
-    num_workers = worker_info.num_workers
-  for s in itertools.islice(src, rank * num_workers + worker_id, None,
-                            world_size * num_workers):
-    yield s
-
-
-def identity(x):
-  return x
-
-
-def create_wds_dataloader(rank, args, mode):
-  """Create webdataset dataset and dataloader."""
-  if mode == 'train':
-    transform = transforms.Compose([
-        transforms.RandomResizedCrop(224),
-        transforms.RandomHorizontalFlip(),
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    data_path = args.train_data_path
-    data_size = args.train_data_size
-    batch_size_local = args.train_batch_size
-    batch_size_global = args.train_batch_size * args.gpus
-    # Since webdataset disallows partial batch, we pad the last batch for train.
-    batches = int(math.ceil(data_size / batch_size_global))
-  else:
-    transform = transforms.Compose([
-        transforms.Resize(256),
-        transforms.CenterCrop(224),
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    data_path = args.eval_data_path
-    data_size = args.eval_data_size
-    batch_size_local = args.eval_batch_size
-    batch_size_global = args.eval_batch_size * args.gpus
-    # Since webdataset disallows partial batch, we drop the last batch for eval.
-    batches = int(data_size / batch_size_global)
-
-  dataset = wds.DataPipeline(
-      wds.SimpleShardList(data_path),
-      functools.partial(wds_split, rank=rank, world_size=args.gpus),
-      wds.tarfile_to_samples(),
-      wds.decode('pil'),
-      wds.to_tuple('jpg;png;jpeg cls'),
-      wds.map_tuple(transform, identity),
-      wds.batched(batch_size_local, partial=False),
-  )
-  num_workers = args.dataloader_num_workers
-  dataloader = wds.WebLoader(
-      dataset=dataset,
-      batch_size=None,
-      shuffle=False,
-      num_workers=num_workers,
-      persistent_workers=True if num_workers > 0 else False,
-      pin_memory=True).repeat(nbatches=batches)
-  print(f'{mode} dataloader | samples: {data_size}, '
-        f'num_workers: {num_workers}, '
-        f'local batch size: {batch_size_local}, '
-        f'global batch size: {batch_size_global}, '
-        f'batches: {batches}')
-  return dataloader
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image = image.to(device, non_blocking=True)
-    target = target.to(device, non_blocking=True)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image = image.to(device, non_blocking=True)
-      target = target.to(device, non_blocking=True)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def worker(gpu, args):
-  """Run training and evaluation."""
-  # Init process group.
-  print(f'Initiating process {gpu}')
-  dist.init_process_group(
-      backend='nccl',
-      init_method='env://',
-      world_size=args.gpus,
-      rank=gpu)
-
-  # Create dataloader.
-  train_dataloader = create_wds_dataloader(gpu, args, 'train')
-  eval_dataloader = create_wds_dataloader(gpu, args, 'eval')
-
-  # Wrap policy.
-  my_auto_wrap_policy = functools.partial(
-      size_based_auto_wrap_policy, min_num_params=100)
-  torch.cuda.set_device(gpu)
-
-  # Create model.
-  model = resnet50(weights=None)
-  model.to(args.device)
-  model = FSDP(model, auto_wrap_policy=my_auto_wrap_policy)
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    if gpu == 0:
-      print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    if gpu == 0:
-      print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    if gpu == 0:
-      print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-
-  if gpu == 0:
-    print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=2,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--train_data_size',
-      default=50000,
-      type=int,
-      help='data size for training')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  parser.add_argument(
-      '--eval_data_size',
-      default=50000,
-      type=int,
-      help='data size for evaluation')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '8888'
-
-  args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-  print(f'Launch job on {args.gpus} GPUs with FSDP')
-  mp.spawn(worker, nprocs=args.gpus, args=(args,))
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/shard_imagenet.py

@@ -1,98 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-r"""Main function to shard ImageNet dataset.
-
-Example usage:
-python3 -u shard_imagenet.py \
---image_list_file=/home/jupyter/data/imagenet/train_list.txt \
---output_pattern=/home/jupyter/data/imagenet/validation-%06d.tar
-"""
-
-import argparse
-import os
-import random
-import webdataset as wds  # version: 0.2.26
-
-
-# NOTE: only supports writing to local path,
-# need gcsfuse mounting if want to write to gcs bucket.
-def write_shards(args):
-  """Shard individual data files."""
-  output_dir = os.path.dirname(args.output_pattern)
-  if not os.path.isdir(output_dir):
-    os.makedirs(output_dir)
-
-  items = []
-  # Image list file is a text file, each line is a pair (image_path, label).
-  with open(args.image_list_file, 'r') as f:
-    for line in f:
-      item = line.strip().split(' ')
-      items.append((item[0], int(item[1])))
-  # Shuffle items to avoid any large sequences of a single class
-  # in the dataset.
-  random.shuffle(items)
-
-  def _read_image(image_path):
-    with open(image_path, 'rb') as f:
-      return f.read()
-
-  with wds.ShardWriter(pattern=args.output_pattern,
-                       maxcount=args.max_images_per_shard,
-                       maxsize=args.max_bytes_per_shard) as sink:
-    for i, (image_path, target) in enumerate(items):
-      key = str(i)
-      image = _read_image(image_path)
-      sample = {'__key__': key, 'jpg': image, 'cls': target}
-      sink.write(sample)
-    if len(items) != sink.total:
-      raise ValueError('Items read {} != items written {}'.format(
-          len(items), sink.total))
-
-
-def create_args():
-  """Creates arg parser."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--image_list_file',
-      default='',
-      type=str,
-      help='path to image list file')
-  parser.add_argument(
-      '--output_pattern',
-      default='',
-      type=str,
-      help='the pattern for output shards, like /path/to/train-%06d.tar')
-  parser.add_argument(
-      '--max_images_per_shard',
-      default=10 * 1024,
-      type=int,
-      help='max number of images per shard')
-  parser.add_argument(
-      '--max_bytes_per_shard',
-      default=300 * 1024 * 1024,
-      type=int,
-      help='max bytes per shard')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  write_shards(args)
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/trainer/Dockerfile

@@ -1,40 +1,16 @@
-# Stage 1: Build Environment
-FROM pytorch/pytorch:1.8.1-cuda11.1-cudnn8-runtime AS builder
-
-# Install necessary tools and dependencies
-RUN apt-get update && \
-    apt-get install -y curl gnupg && \
-    echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] http://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list && \
-    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - && \
-    apt-get update -y && \
-    apt-get install -y google-cloud-sdk
-
-# Copy application code
-COPY . /trainer
-
-# Set working directory
-WORKDIR /trainer
-
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Stage 2: Runtime Environment
 FROM pytorch/pytorch:1.8.1-cuda11.1-cudnn8-runtime
 
-# Install Google Cloud SDK
 RUN apt-get update && \
     apt-get install -y curl gnupg && \
     echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] http://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list && \
-    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - && \
+    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg  add - && \
     apt-get update -y && \
-    apt-get install -y google-cloud-sdk && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
+    apt-get install google-cloud-sdk -y
 
-# Copy from the builder stage
-COPY --from=builder /trainer /trainer
+COPY . /trainer
 
-# Set working directory
 WORKDIR /trainer
 
-# Set the entry point
-ENTRYPOINT ["python", "-m", "task"]
+RUN pip install -r requirements.txt
+
+ENTRYPOINT ["python", "-m", "task"]

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/trainer/requirements.txt

@@ -1,3 +1,3 @@
-torch==2.8.0
+torch==1.8.1
 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==2.7.0
+torch==1.8.1
 torchvision==0.9.1
 tensorboard==2.5.0

community-content/pytorch_image_classification_single_gpu_with_vertex_sdk_and_torchserve/vertex_prediction_with_custom_torchserve_container.ipynb

@@ -110,7 +110,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls $gcs_output_uri_prefix"
+        "! gsutil ls $gcs_output_uri_prefix"
       ]
     },
     {
@@ -192,7 +192,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage cp --recursive $gcs_output_uri_prefix/model ./model_server/"
+        "! gsutil cp -r $gcs_output_uri_prefix/model ./model_server/"
       ]
     },
     {
@@ -556,7 +556,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage rm --recursive --continue-on-error $gcs_output_uri_prefix"
+        "! gsutil rm -rf $gcs_output_uri_prefix"
       ]
     },
     {

community-content/pytorch_image_classification_single_gpu_with_vertex_sdk_and_torchserve/vertex_training_with_custom_container.ipynb

@@ -412,7 +412,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls $gcs_output_uri_prefix"
+        "! gsutil ls $gcs_output_uri_prefix"
       ]
     }
   ],

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

@@ -31,7 +31,17 @@
       "source": [
         "# Deploying a PyTorch Text Classification Model on [Vertex AI](https://cloud.google.com/vertex-ai)\n",
         "\n",
-        "**Kindly reach out to Vertex AI before you run any scale tests or you have any questions.**\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."
       ]
     },
     {

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/custom_container/scripts/train-cloud.sh

@@ -77,4 +77,4 @@ echo "After the job is completed successfully, model files will be saved at $JOB
 
 # # Verify the model was exported
 # echo "Verify the model was exported:"
-# gcloud storage ls ${JOB_DIR}/
+# gsutil ls ${JOB_DIR}/

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/predictor/Dockerfile.serve

@@ -34,4 +34,4 @@ RUN echo "service_envelope=json\n"     "inference_address=http://0.0.0.0:${AIP_H
 USER model-server
 
 # run Torchserve HTTP serve to respond to prediction requests
-CMD ["echo", "AIP_STORAGE_URI=${AIP_STORAGE_URI}", ";",     "gcloud", "storage", "cp", "--recursive", "${AIP_STORAGE_URI}/${MODEL_NAME}.mar", "/home/model-server/model-store/", ";",     "ls", "-ltr", "/home/model-server/model-store/", ";",     "torchserve", "--start", "--ts-config=/home/model-server/config.properties",     "--models", "${MODEL_NAME}=${MODEL_NAME}.mar",     "--model-store", "/home/model-server/model-store"]
+CMD ["echo", "AIP_STORAGE_URI=${AIP_STORAGE_URI}", ";",     "gsutil", "cp", "-r", "${AIP_STORAGE_URI}/${MODEL_NAME}.mar", "/home/model-server/model-store/", ";",     "ls", "-ltr", "/home/model-server/model-store/", ";",     "torchserve", "--start", "--ts-config=/home/model-server/config.properties",     "--models", "${MODEL_NAME}=${MODEL_NAME}.mar",     "--model-store", "/home/model-server/model-store"]

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/python_package/scripts/train-cloud.sh

@@ -67,4 +67,4 @@ echo "After the job is completed successfully, model files will be saved at $JOB
 
 # # Verify the model was exported
 # echo "Verify the model was exported:"
-# gcloud storage ls ${JOB_DIR}/
+# gsutil ls ${JOB_DIR}/

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/mlops_pipeline_tf_agents_bandits_movie_recommendation.ipynb

@@ -478,7 +478,8 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage buckets create --location $REGION $BUCKET_NAME"      ]
+        "! gsutil mb -l $REGION $BUCKET_NAME"
+      ]
     },
     {
       "cell_type": "markdown",
@@ -497,7 +498,8 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls --all-versions --long $BUCKET_NAME"      ]
+        "! gsutil ls -al $BUCKET_NAME"
+      ]
     },
     {
       "cell_type": "markdown",
@@ -580,7 +582,8 @@
       "outputs": [],
       "source": [
         "# Download the sample data into your RAW_DATA_PATH\n",
-        "! gcloud storage cp \"gs://cloud-samples-data/vertex-ai/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/u.data\" $RAW_DATA_PATH"      ]
+        "! gsutil cp \"gs://cloud-samples-data/vertex-ai/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/u.data\" $RAW_DATA_PATH"
+      ]
     },
     {
       "cell_type": "code",
@@ -1618,7 +1621,9 @@
         "! gcloud scheduler jobs delete $SIMULATOR_SCHEDULER_JOB --quiet\n",
         "\n",
         "# Delete Cloud Storage objects that were created.\n",
-        "! gcloud storage rm --recursive $PIPELINE_ROOT\n",        "! gcloud storage rm --recursive $TRAINING_ARTIFACTS_DIR"      ]
+        "! gsutil -m rm -r $PIPELINE_ROOT\n",
+        "! gsutil -m rm -r $TRAINING_ARTIFACTS_DIR"
+      ]
     }
   ],
   "metadata": {

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/logger/requirements.txt

@@ -1,4 +1,4 @@
 google-cloud-bigquery==2.20.0
-tensorflow==2.12.1
-pillow==10.3.0
+tensorflow==2.7.2
+pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/prediction_container/requirements.txt

@@ -1,4 +1,4 @@
 google-cloud-pubsub==2.5.0
-pillow==10.3.0
+pillow==9.0.1
 tf-agents==0.8.0
-tensorflow==2.12.1
+tensorflow==2.7.2

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/simulator/requirements.txt

@@ -1,5 +1,5 @@
 dataclasses==0.6
 google-cloud-aiplatform==1.8.1
-tensorflow==2.12.1
-pillow==10.3.0
+tensorflow==2.7.2
+pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/step_by_step_sdk_tf_agents_bandits_movie_recommendation/step_by_step_sdk_tf_agents_bandits_movie_recommendation.ipynb

@@ -398,7 +398,6 @@
         "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",
@@ -473,7 +472,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage buckets create --location $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_NAME"
       ]
     },
     {
@@ -493,7 +492,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls --all-versions --long $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_NAME"
       ]
     },
     {
@@ -566,7 +565,7 @@
       "outputs": [],
       "source": [
         "# Copy the sample data into your DATA_PATH\n",
-        "! gcloud storage cp \"gs://cloud-samples-data/vertex-ai/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/u.data\"  $DATA_PATH"
+        "! gsutil cp \"gs://cloud-samples-data/vertex-ai/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/u.data\"  $DATA_PATH"
       ]
     },
     {
@@ -580,15 +579,11 @@
         "# Set hyperparameters.\n",
         "BATCH_SIZE = 8  # @param {type:\"integer\"} Training and prediction batch size.\n",
         "TRAINING_LOOPS = 5  # @param {type:\"integer\"} Number of training iterations.\n",
-        "STEPS_PER_LOOP = (\n",
-        "    2  # @param {type:\"integer\"} Number of driver steps per training iteration.\n",
-        ")\n",
+        "STEPS_PER_LOOP = 2  # @param {type:\"integer\"} Number of driver steps per training iteration.\n",
         "\n",
         "# Set MovieLens simulation environment parameters.\n",
         "RANK_K = 20  # @param {type:\"integer\"} Rank for matrix factorization in the MovieLens environment; also the observation dimension.\n",
-        "NUM_ACTIONS = (\n",
-        "    20  # @param {type:\"integer\"} Number of actions (movie items) to choose from.\n",
-        ")\n",
+        "NUM_ACTIONS = 20  # @param {type:\"integer\"} Number of actions (movie items) to choose from.\n",
         "PER_ARM = False  # Use the non-per-arm version of the MovieLens environment.\n",
         "\n",
         "# Set agent parameters.\n",
@@ -626,8 +621,7 @@
       "source": [
         "# Define RL environment.\n",
         "env = movielens_py_environment.MovieLensPyEnvironment(\n",
-        "    DATA_PATH, RANK_K, BATCH_SIZE, num_movies=NUM_ACTIONS, csv_delimiter=\"\\t\"\n",
-        ")\n",
+        "    DATA_PATH, RANK_K, BATCH_SIZE, num_movies=NUM_ACTIONS, csv_delimiter=\"\\t\")\n",
         "environment = tf_py_environment.TFPyEnvironment(env)\n",
         "\n",
         "# Define RL agent/algorithm.\n",
@@ -637,8 +631,7 @@
         "    tikhonov_weight=TIKHONOV_WEIGHT,\n",
         "    alpha=AGENT_ALPHA,\n",
         "    dtype=tf.float32,\n",
-        "    accepts_per_arm_features=PER_ARM,\n",
-        ")\n",
+        "    accepts_per_arm_features=PER_ARM)\n",
         "print(\"TimeStep Spec (for each batch):\\n\", agent.time_step_spec, \"\\n\")\n",
         "print(\"Action Spec (for each batch):\\n\", agent.action_spec, \"\\n\")\n",
         "print(\"Reward Spec (for each batch):\\n\", environment.reward_spec(), \"\\n\")\n",
@@ -646,8 +639,7 @@
         "# Define RL metric.\n",
         "optimal_reward_fn = functools.partial(\n",
         "    environment_utilities.compute_optimal_reward_with_movielens_environment,\n",
-        "    environment=environment,\n",
-        ")\n",
+        "    environment=environment)\n",
         "regret_metric = tf_bandit_metrics.RegretMetric(optimal_reward_fn)\n",
         "metrics = [regret_metric]"
       ]
@@ -712,38 +704,35 @@
         "    if training_data_spec_transformation_fn is None:\n",
         "        data_spec = agent.policy.trajectory_spec\n",
         "    else:\n",
-        "        data_spec = training_data_spec_transformation_fn(agent.policy.trajectory_spec)\n",
-        "    replay_buffer = trainer.get_replay_buffer(\n",
-        "        data_spec, environment.batch_size, steps_per_loop\n",
-        "    )\n",
+        "        data_spec = training_data_spec_transformation_fn(\n",
+        "            agent.policy.trajectory_spec)\n",
+        "    replay_buffer = trainer.get_replay_buffer(data_spec, environment.batch_size,\n",
+        "                                              steps_per_loop)\n",
         "\n",
         "    # `step_metric` records the number of individual rounds of bandit interaction;\n",
         "    # that is, (number of trajectories) * batch_size.\n",
         "    step_metric = tf_metrics.EnvironmentSteps()\n",
         "    metrics = [\n",
         "        tf_metrics.NumberOfEpisodes(),\n",
-        "        tf_metrics.AverageEpisodeLengthMetric(batch_size=environment.batch_size),\n",
+        "        tf_metrics.AverageEpisodeLengthMetric(batch_size=environment.batch_size)\n",
         "    ]\n",
         "    if additional_metrics:\n",
         "        metrics += additional_metrics\n",
         "\n",
         "    if isinstance(environment.reward_spec(), dict):\n",
-        "        metrics += [\n",
-        "            tf_metrics.AverageReturnMultiMetric(\n",
-        "                reward_spec=environment.reward_spec(), batch_size=environment.batch_size\n",
-        "            )\n",
-        "        ]\n",
+        "        metrics += [tf_metrics.AverageReturnMultiMetric(\n",
+        "            reward_spec=environment.reward_spec(),\n",
+        "            batch_size=environment.batch_size)]\n",
         "    else:\n",
-        "        metrics += [tf_metrics.AverageReturnMetric(batch_size=environment.batch_size)]\n",
+        "        metrics += [\n",
+        "            tf_metrics.AverageReturnMetric(batch_size=environment.batch_size)]\n",
         "\n",
         "    # Store intermediate metric results, indexed by metric names.\n",
         "    metric_results = defaultdict(list)\n",
         "\n",
         "    if training_data_spec_transformation_fn is not None:\n",
-        "\n",
-        "        def add_batch_fn(data):\n",
-        "            return replay_buffer.add_batch(training_data_spec_transformation_fn(data))\n",
-        "\n",
+        "        def add_batch_fn(data): return replay_buffer.add_batch(training_data_spec_transformation_fn(data)) \n",
+        "        \n",
         "    else:\n",
         "        add_batch_fn = replay_buffer.add_batch\n",
         "\n",
@@ -753,12 +742,10 @@
         "        env=environment,\n",
         "        policy=agent.collect_policy,\n",
         "        num_steps=steps_per_loop * environment.batch_size,\n",
-        "        observers=observers,\n",
-        "    )\n",
+        "        observers=observers)\n",
         "\n",
         "    training_loop = trainer.get_training_loop_fn(\n",
-        "        driver, replay_buffer, agent, steps_per_loop\n",
-        "    )\n",
+        "        driver, replay_buffer, agent, steps_per_loop)\n",
         "    saver = policy_saver.PolicySaver(agent.policy)\n",
         "\n",
         "    for _ in range(training_loops):\n",
@@ -796,8 +783,7 @@
         "    environment=environment,\n",
         "    training_loops=TRAINING_LOOPS,\n",
         "    steps_per_loop=STEPS_PER_LOOP,\n",
-        "    additional_metrics=metrics,\n",
-        ")\n",
+        "    additional_metrics=metrics)\n",
         "\n",
         "tf.profiler.experimental.stop()"
       ]
@@ -1106,15 +1092,11 @@
       },
       "outputs": [],
       "source": [
-        "RUN_HYPERPARAMETER_TUNING = (\n",
-        "    True  # Execute hyperparameter tuning instead of regular training.\n",
-        ")\n",
+        "RUN_HYPERPARAMETER_TUNING = True  # Execute hyperparameter tuning instead of regular training.\n",
         "TRAIN_WITH_BEST_HYPERPARAMETERS = False  # Do not train.\n",
         "\n",
         "HPTUNING_RESULT_DIR = \"hptuning/\"  # @param {type: \"string\"} Directory to store the best hyperparameter(s) in `BUCKET_NAME` and locally (temporarily).\n",
-        "HPTUNING_RESULT_PATH = os.path.join(\n",
-        "    HPTUNING_RESULT_DIR, \"result.json\"\n",
-        ")  # @param {type: \"string\"} Path to the file containing the best hyperparameter(s)."
+        "HPTUNING_RESULT_PATH = os.path.join(HPTUNING_RESULT_DIR, \"result.json\")  # @param {type: \"string\"} Path to the file containing the best hyperparameter(s)."
       ]
     },
     {
@@ -1142,7 +1124,7 @@
         "    image_uri: str,\n",
         "    args: List[str],\n",
         "    location: str = \"us-central1\",\n",
-        "    api_endpoint: str = \"us-central1-aiplatform.googleapis.com\",\n",
+        "    api_endpoint: str = \"us-central1-aiplatform.googleapis.com\"\n",
         ") -> None:\n",
         "    \"\"\"Creates a hyperparameter tuning job using a custom container.\n",
         "\n",
@@ -1215,8 +1197,8 @@
         "\n",
         "    # Create job\n",
         "    response = client.create_hyperparameter_tuning_job(\n",
-        "        parent=parent, hyperparameter_tuning_job=hyperparameter_tuning_job\n",
-        "    )\n",
+        "        parent=parent,\n",
+        "        hyperparameter_tuning_job=hyperparameter_tuning_job)\n",
         "    job_id = response.name.split(\"/\")[-1]\n",
         "    print(\"Job ID:\", job_id)\n",
         "    print(\"Job config:\", response)\n",
@@ -1260,8 +1242,7 @@
         "    image_uri=f\"gcr.io/{PROJECT_ID}/{HPTUNING_TRAINING_CONTAINER}:latest\",\n",
         "    args=args,\n",
         "    location=REGION,\n",
-        "    api_endpoint=f\"{REGION}-aiplatform.googleapis.com\",\n",
-        ")"
+        "    api_endpoint=f\"{REGION}-aiplatform.googleapis.com\")"
       ]
     },
     {
@@ -1311,8 +1292,7 @@
         "    name = client.hyperparameter_tuning_job_path(\n",
         "        project=project,\n",
         "        location=location,\n",
-        "        hyperparameter_tuning_job=hyperparameter_tuning_job_id,\n",
-        "    )\n",
+        "        hyperparameter_tuning_job=hyperparameter_tuning_job_id)\n",
         "    response = client.get_hyperparameter_tuning_job(name=name)\n",
         "    return response"
       ]
@@ -1333,8 +1313,7 @@
         "        location=REGION,\n",
         "        api_endpoint=f\"{REGION}-aiplatform.googleapis.com\")\n",
         "    if response.state.name == 'JOB_STATE_SUCCEEDED':\n",
-        "        print(\"Job succeeded.\n",
-        "Job Time:\", response.update_time - response.create_time)\n",
+        "        print(\"Job succeeded.\\nJob Time:\", response.update_time - response.create_time)\n",
         "        trials = response.trials\n",
         "        print(\"Trials:\", trials)\n",
         "        break\n",
@@ -1369,8 +1348,8 @@
         "if trials:\n",
         "    # Dict mapping from metric names to the best metric values seen so far\n",
         "    best_objective_values = dict.fromkeys(\n",
-        "        [metric.metric_id for metric in trials[0].final_measurement.metrics], -np.inf\n",
-        "    )\n",
+        "        [metric.metric_id for metric in trials[0].final_measurement.metrics],\n",
+        "        -np.inf)\n",
         "    # Dict mapping from metric names to a list of the best combination(s) of\n",
         "    # hyperparameter(s). Each combination is a dict mapping from hyperparameter\n",
         "    # names to their values.\n",
@@ -1379,13 +1358,12 @@
         "        # `final_measurement` and `parameters` are `RepeatedComposite` objects.\n",
         "        # Reference the structure above to extract the value of your interest.\n",
         "        for metric in trial.final_measurement.metrics:\n",
-        "            params = {param.parameter_id: param.value for param in trial.parameters}\n",
+        "            params = {\n",
+        "                param.parameter_id: param.value for param in trial.parameters}\n",
         "            if metric.value > best_objective_values[metric.metric_id]:\n",
         "                best_params[metric.metric_id] = [params]\n",
         "            elif metric.value == best_objective_values[metric.metric_id]:\n",
-        "                best_params[param.parameter_id].append(\n",
-        "                    params\n",
-        "                )  # Handle cases where multiple hyperparameter values lead to the same performance.\n",
+        "                best_params[param.parameter_id].append(params)  # Handle cases where multiple hyperparameter values lead to the same performance.\n",
         "    print(\"Best hyperparameter value(s):\")\n",
         "    for metric, params in best_params.items():\n",
         "        print(f\"Metric={metric}: {sorted(params)}\")\n",
@@ -1465,9 +1443,7 @@
       },
       "outputs": [],
       "source": [
-        "PREDICTION_CONTAINER = (\n",
-        "    \"prediction-custom-container\"  # @param {type:\"string\"} Name of the container image.\n",
-        ")"
+        "PREDICTION_CONTAINER = \"prediction-custom-container\"  # @param {type:\"string\"} Name of the container image."
       ]
     },
     {
@@ -1499,7 +1475,7 @@
         "  machineType: 'E2_HIGHCPU_8'\"\"\".format(\n",
         "    PROJECT_ID=PROJECT_ID,\n",
         "    PREDICTION_CONTAINER=PREDICTION_CONTAINER,\n",
-        "    ARTIFACTS_DIR=ARTIFACTS_DIR,\n",
+        "    ARTIFACTS_DIR=ARTIFACTS_DIR\n",
         ")\n",
         "\n",
         "with open(\"cloudbuild.yaml\", \"w\") as fp:\n",
@@ -1616,12 +1592,8 @@
       },
       "outputs": [],
       "source": [
-        "RUN_HYPERPARAMETER_TUNING = (\n",
-        "    False  # Execute regular training instead of hyperparameter tuning.\n",
-        ")\n",
-        "TRAIN_WITH_BEST_HYPERPARAMETERS = (\n",
-        "    True  # @param {type:\"bool\"} Whether to use learned hyperparameters in training.\n",
-        ")"
+        "RUN_HYPERPARAMETER_TUNING = False  # Execute regular training instead of hyperparameter tuning.\n",
+        "TRAIN_WITH_BEST_HYPERPARAMETERS = True  # @param {type:\"bool\"} Whether to use learned hyperparameters in training."
       ]
     },
     {
@@ -1661,12 +1633,10 @@
         "job = aiplatform.CustomContainerTrainingJob(\n",
         "    display_name=\"train-movielens\",\n",
         "    container_uri=f\"gcr.io/{PROJECT_ID}/{HPTUNING_TRAINING_CONTAINER}:latest\",\n",
-        "    command=[\"python3\", \"-m\", \"src.training.task\"]\n",
-        "    + args,  # Pass in training arguments, including hyperparameters.\n",
+        "    command=[\"python3\", \"-m\", \"src.training.task\"] + args,  # Pass in training arguments, including hyperparameters.\n",
         "    model_serving_container_image_uri=f\"gcr.io/{PROJECT_ID}/{PREDICTION_CONTAINER}:latest\",\n",
         "    model_serving_container_predict_route=\"/predict\",\n",
-        "    model_serving_container_health_route=\"/health\",\n",
-        ")\n",
+        "    model_serving_container_health_route=\"/health\")\n",
         "\n",
         "print(\"Training Spec:\", job._managed_model)\n",
         "\n",
@@ -1675,8 +1645,7 @@
         "    replica_count=1,\n",
         "    machine_type=\"n1-standard-4\",\n",
         "    accelerator_type=\"ACCELERATOR_TYPE_UNSPECIFIED\",\n",
-        "    accelerator_count=0,\n",
-        ")"
+        "    accelerator_count=0)"
       ]
     },
     {
@@ -1815,7 +1784,7 @@
         "! gcloud ai models delete $model.name --quiet\n",
         "\n",
         "# Delete Cloud Storage objects that were created\n",
-        "! gcloud storage rm --recursive $ARTIFACTS_DIR"
+        "! gsutil -m rm -r $ARTIFACTS_DIR"
       ]
     }
   ],

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/multi_worker_vertex_training_on_cpu_with_custom_container.ipynb

@@ -324,7 +324,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls $gcs_output_uri_prefix"
+        "! gsutil ls $gcs_output_uri_prefix"
       ]
     },
     {
@@ -344,7 +344,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage rm --recursive --continue-on-error $gcs_output_uri_prefix"
+        "! gsutil rm -rf $gcs_output_uri_prefix"
       ]
     }
   ],

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/multi_worker_vertex_training_on_gpu_with_custom_container.ipynb

@@ -328,7 +328,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls $gcs_output_uri_prefix"
+        "! gsutil ls $gcs_output_uri_prefix"
       ]
     },
     {
@@ -348,7 +348,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage rm --recursive --continue-on-error $gcs_output_uri_prefix"
+        "! gsutil rm -rf $gcs_output_uri_prefix"
       ]
     }
   ],

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.12.1
+tensorflow==2.7.2

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.12.1
+tensorflow==2.7.2

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/vertex_training_with_local_mode_container.ipynb

@@ -341,7 +341,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage ls $gcs_output_uri_prefix"
+        "! gsutil ls $gcs_output_uri_prefix"
       ]
     },
     {
@@ -361,7 +361,7 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud storage rm --recursive --continue-on-error $gcs_output_uri_prefix"
+        "! gsutil rm -rf $gcs_output_uri_prefix"
       ]
     }
   ],

community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining/README.md

@@ -1,126 +0,0 @@
-# Vertex AI Training: Llama 3.1 8B pre-training using Nvidia A3 Mega VMs (H100)
-This document provides a step-by-step guide for pre-training a Llama 3.1 8B model on the `en-wiki` dataset using multiple [Vertex AI Custom Training](https://cloud.google.com/vertex-ai/docs/training/overview) `a3-megagpu-8g` nodes.
-
-We will use a custom container based on NVIDIA's [NeMo Framework](https://docs.nvidia.com/nemo-framework/user-guide/24.07/overview.html) to demonstrate a scalable, multi-node training workflow. All required artifacts and commands are included.
-
-## 1. Prerequisites
-
-### 1.1. Google Cloud Project setup
-- **Enable APIs:** Ensure the Vertex AI API is [enabled for your project](http://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).
-- **H100 Mega Quota:** A3 Mega VMs are powered by H100 GPUs. Request quota for `custom_model_training_nvidia_h100_mega_gpus` in one of the [supported regions](https://cloud.google.com/vertex-ai/docs/general/locations#accelerator_support). If using Spot VMs, request `custom_model_training_preemptible_nvidia_h100_mega_gpus` quota instead.
-- **Reservations (Optional but recommended):** For guaranteed capacity, [create a reservation](https://cloud.google.com/compute/docs/instances/reservations-shared) and ensure the reservation is shared with the Vertex AI service account. This guide requires a minimum of **16 H100 GPUs** (2 full A3 Mega nodes).
-
-### 1.2. GCS bucket
-Create a [Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) in the same region where you have quota. If you're using Hierarchical Namespace for your bucket, you may need to update permissions of the Vertex AI Custom Code Service Agent .
-
-This bucket is used for:
-- Staging the training application.
-- Storing model checkpoints and logs.
-- Storing data if you use your own data.
-
-
-## 2. Setup & configuration
-
-### 2.1. Clone the repo
-First clone the repo into your development environment.
-
-```bash
-git clone https://github.com/GoogleCloudPlatform/vertex-ai-samples.git
-```
-
-Navigate to the root folder for this sample.
-
-### 2.2. Environment Setup
-First, configure your local environment. These variables are used in subsequent commands.
-
-```bash
-# Required: Update with your values
-export PROJECT_ID="<your-project-id>"
-export REPOSITORY="<your-artifact-registry-repo-name>" # e.g., "my-containers"
-export BUCKET="<your-gcs-bucket-name>"
-
-# Optional: Change if needed
-export REGION="us-central1"
-
-# --- Do not change the lines below ---
-export ARTIFACT_REGISTRY="${REGION}-docker.pkg.dev/${PROJECT_ID}/${REPOSITORY}"
-export REPO_ROOT=$(git rev-parse --show-toplevel)
-```
-
-## 3. Build and push a docker container image to Artifact Registry
-Normally, you can use any custom training container on Vertex AI Training. In this example you build a NeMo Docker image that is based on the [Nvidia’s NeMo 24.09](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo/tags) image. Use Cloud Build to build and push the container image.
-
-This document picked NeMo as the demonstrating container since it’s a widely adopted GPU LLM training framework providing high performance and versatile training functionalities.
-
-In addition to the base image, some customizations are included to form the final prebuilt image:
-- Some dependencies are installed to integrate with Vertex AI Training.
-- An entrypoint script that sets up required environments and calls the training job.
-- Some patches are applied to the NeMo code to let it  load the dataset from a GCS bucket.
-
-Run this command to build the container and push the container into the Google Artifact Registry.
-
-```bash
-cd "${REPO_ROOT}/community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining"
-export IMAGE_NAME="vertex-nemo-llama"
-gcloud builds submit . \
-    --project="${PROJECT_ID}" \
-    --region="${REGION}" \
-    --config=docker/cloudbuild.yml \
-    --substitutions="_ARTIFACT_REGISTRY=${ARTIFACT_REGISTRY},_IMAGE_NAME=${IMAGE_NAME}" \
-    --timeout="2h" \
-    --machine-type="e2-highcpu-32"
-```
-
-## 4. Launch the Training Job
-
-
-###  4.1. Job Configuration File
-Once the container is built, update the job_config.json to set up the training job.
-File: job_config.json
-```json
-{
-  "project_id": "<project-id>",
-  "region": "<region>",
-  "zone": "<zone if using reservation>",
-  "bucket": "<bucket>",
-  "dataset_bucket": "github-repo/data/third-party/enwiki-latest-pages-articles",
-  "image_uri": "<docker image uri from artifact registry>",
-  "strategy": "spot",
-  "nodes": "2",
-  "machine_type": "a3-megagpu-8g",
-  "gpu_type": "NVIDIA_H100_MEGA_80GB",
-  "gpus_per_node": "8",
-  "recipe_name": "llama3_1_8b_pretrain_a3mega",
-  "job_prefix": "vertex-spot-",
-  "reservation_name": ""
-}
-```
-
-### 4.2 Launch the Training Job
-
-First, create a Python virtual environment using your tool of choice, then install
-the requirements specified in `requirements.txt`. Using `pip`, the command would be:
-```bash
-pip install -r requirements.txt
-```
-
-Now launch the Vertex AI training job using the provided Python script.
-
-```bash
-python3 scripts/launch.py --config_file=job_config.json
-```
-
-This script reads job_config.json, defines the cluster specification (2 nodes, 8 GPUs each), and submits the custom training job to Vertex AI.
-
-## 5. Monitor and Clean Up
-
-### 5.1. Monitoring
-Vertex AI Console: Track the job's status in the Google Cloud Console under Vertex AI > Training > Custom Jobs.
-Logs: View detailed logs in Cloud Logging by filtering for your job name.
-Checkpoints: Model checkpoints are saved to your GCS bucket at the path specified in your training script's configuration.
-
-### 5.2. Cleaning Up
-To avoid ongoing charges, delete the resources you created:
-- The Artifact Registry image.
-- The contents of the GCS bucket (checkpoints, logs).
-- The Vertex AI Custom Job will eventually complete or fail, incurring no further cost.

community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining/configs/llama3_1_8b_pretrain_a3mega.yaml

@@ -1,265 +0,0 @@
-# Reference:
-# https://github.com/NVIDIA/NeMo-Framework-Launcher/blob/24.07/launcher_scripts/conf/training/llama/llama3_1_8b.yaml
-name: llama3_1_8b_pretrain_a3mega
-restore_from_path: null  # used when starting from a .nemo file
-
-trainer:
-  devices: 8
-  num_nodes: 1
-  accelerator: gpu
-  precision: bf16
-  logger: false  # logger provided by exp_manager
-  enable_checkpointing: false
-  use_distributed_sampler: false
-  max_epochs: -1  # PTL default. In practice, max_steps will be reached first.
-  max_steps: 30  # consumed_samples = global_step * micro_batch_size * data_parallel_size * accumulate_grad_batches
-  log_every_n_steps: 1
-  val_check_interval: null
-  limit_val_batches: 1
-  limit_test_batches: 1
-  accumulate_grad_batches: 1  # do not modify, grad acc is automatic for training megatron models
-  gradient_clip_val: 1.0
-  benchmark: false
-  enable_model_summary: false  # default PTL callback for this does not support model parallelism, instead we log manually
-
-exp_manager:
-  explicit_log_dir: null
-  exp_dir: /data
-  name: ${name}
-  create_dllogger_logger: true
-  dllogger_logger_kwargs:
-    verbose: true
-    stdout: true
-    json_file: "/data/dllogger.json"
-  create_wandb_logger: false
-  wandb_logger_kwargs:
-    project: null
-    name: null
-  resume_if_exists: true
-  resume_ignore_no_checkpoint: true
-  create_checkpoint_callback: false
-  checkpoint_callback_params:
-    monitor: val_loss
-    save_top_k: 3
-    mode: min
-    always_save_nemo: false  # saves nemo file during validation, not implemented for model parallel
-    save_nemo_on_train_end: false  # not recommended when training large models on clusters with short time limits
-    filename: 'megatron_gpt--{val_loss:.2f}-{step}-{consumed_samples}'
-    model_parallel_size: ${multiply:${model.tensor_model_parallel_size}, ${model.pipeline_model_parallel_size}}
-  seconds_to_sleep: 5  # Allows node_rank!=0 to sleep and let node0 to init, like preparing data
-
-model:
-  mcore_gpt: true
-  # specify micro_batch_size, global_batch_size, and model parallelism
-  # gradient accumulation will be done automatically based on data_parallel_size
-  micro_batch_size: 1  # limited by GPU memory
-  global_batch_size: 1024  # will use more micro batches to reach global batch size
-  tensor_model_parallel_size: 1  # intra-layer model parallelism
-  pipeline_model_parallel_size: 2  # inter-layer model parallelism
-  context_parallel_size: 1
-  virtual_pipeline_model_parallel_size: null  # interleaved pipeline
-  ## Sequence Parallelism
-  # Makes tensor parallelism more memory efficient for LLMs (20B+) by parallelizing layer norms and dropout sequentially
-  # See Reducing Activation Recomputation in Large Transformer Models: https://arxiv.org/abs/2205.05198 for more details.
-  sequence_parallel: false
-
-  fsdp: false
-  fsdp_cpu_offload: true
-  fsdp_sharding_strategy: "full"  # Method to shard model states. Available options are 'full', 'hybrid', and 'grad'.
-  fsdp_grad_reduce_dtype: "16"  # Gradient reduction data type.
-  fsdp_sharded_checkpoint: false  # Store and load FSDP shared checkpoint.
-  fsdp_use_orig_params: false  # Set to True to use FSDP for specific peft scheme.
-
-  # Distributed checkpoint setup
-  dist_ckpt_format: "torch_dist"  # Set to 'torch_dist' to use PyTorch distributed checkpoint format.
-  dist_ckpt_load_on_device: true  # whether to load checkpoint weights directly on GPU or to CPU
-  dist_ckpt_parallel_save: true  # if true, each worker will write its own part of the dist checkpoint
-  dist_ckpt_parallel_save_within_dp: false  # if true, save will be parallelized only within a DP group (whole world otherwise), which might slightly reduce the save overhead
-  dist_ckpt_parallel_load: false  # if true, each worker will load part of the dist checkpoint and exchange with NCCL. Might use some extra GPU memory
-  dist_ckpt_torch_dist_multiproc: 2  # number of extra processes per rank used during ckpt save with PyTorch distributed format
-  dist_ckpt_assume_constant_structure: false  # set to True only if the state dict structure doesn't change within a single job. Allows caching some computation across checkpoint saves.
-  dist_ckpt_parallel_dist_opt: true  # parallel save/load of a DistributedOptimizer. 'True' allows performant save and reshardable checkpoints. Set to 'False' only in order to minimize the number of checkpoint files.
-  dist_ckpt_load_strictness: null  # defines checkpoint keys mismatch behavior (only during dist-ckpt load). Choices: assume_ok_unexpected (default - try loading without any check), log_all (log mismatches), raise_all (raise mismatches)
-
-  # model architecture
-  encoder_seq_length: 8192
-  max_position_embeddings: ${.encoder_seq_length}
-  num_layers: 32  # 8b: 32 | 70b: 80 | 405b: 126
-  hidden_size: 4096  # 8b: 4096 | 70b: 8192 | 405b: 16384
-  ffn_hidden_size: 14336  # 8b: 14336 | 70b: 28672 | 405b: 53248
-  num_attention_heads: 32  # 8b: 32 | 70b: 64 | 405b: 128
-  num_query_groups: 8  # Number of query groups for group query attention. If None, normal attention is used. 8b: 8 | 70b: 8 | 405b: 16
-  init_method_std: 0.01  # Standard deviation of the zero mean normal distribution used for weight initialization.  8b: 0.01 | 70b: 0.008944 | 405b: 0.02
-  use_scaled_init_method: true  # use scaled residuals initialization
-  hidden_dropout: 0.0  # Dropout probability for hidden state transformer.
-  attention_dropout: 0.0  # Dropout probability for attention
-  ffn_dropout: 0.0  # Dropout probability in the feed-forward layer.
-  kv_channels: null  # Projection weights dimension in multi-head attention. Set to hidden_size // num_attention_heads if null
-  apply_query_key_layer_scaling: true  # scale Q * K^T by 1 / layer-number.
-  normalization: 'rmsnorm'  # Normalization layer to use. Options are 'layernorm', 'rmsnorm'
-  layernorm_epsilon: 1e-5
-  do_layer_norm_weight_decay: false  # True means weight decay on all params
-  make_vocab_size_divisible_by: 128  # Pad the vocab size to be divisible by this value for computation efficiency.
-  pre_process: true  # add embedding
-  post_process: true  # add pooler
-  persist_layer_norm: true  # Use of persistent fused layer norm kernel.
-  bias: false  # Whether to use bias terms in all weight matrices.
-  activation: 'fast-swiglu'  # Options ['gelu', 'geglu', 'swiglu', 'reglu', 'squared-relu', 'fast-geglu', 'fast-swiglu', 'fast-reglu']
-  headscale: false  # Whether to learn extra parameters that scale the output of the each self-attention head.
-  transformer_block_type: 'pre_ln'  # Options ['pre_ln', 'post_ln', 'normformer']
-  openai_gelu: false  # Use OpenAI's GELU instead of the default GeLU
-  normalize_attention_scores: true  # Whether to scale the output Q * K^T by 1 / sqrt(hidden_size_per_head). This arg is provided as a configuration option mostly for compatibility with models that have been weight-converted from HF. You almost always want to se this to True.
-  position_embedding_type: 'rope'  # Position embedding type. Options ['learned_absolute', 'rope']
-  rotary_percentage: 1.0  # If using position_embedding_type=rope, then the per head dim is multiplied by this.
-  attention_type: 'multihead'  # Attention type. Options ['multihead']
-  share_embeddings_and_output_weights: false  # Share embedding and output layer weights.
-  scale_positional_embedding: true  # This is false for llama3 models. Only used for >= llama3.1.
-
-  # Use GPT2BPETokenizer for test, because the testing dataset is tokenized by this tokenizer.
-  # https://docs.nvidia.com/nemo-framework/user-guide/24.07/playbooks/singlenodepretrain.html#data-download-and-pre-processing
-  tokenizer:
-    library: megatron
-    type: GPT2BPETokenizer
-    model: null  # /path/to/tokenizer.model
-    vocab_file: null
-    merge_file: null
-    delimiter: null  # only used for tabular tokenizer
-    sentencepiece_legacy: false  # Legacy=True allows you to add special tokens to sentencepiece tokenizers.
-
-  # Mixed precision
-  native_amp_init_scale: 4294967296  # 2 ** 32
-  native_amp_growth_interval: 1000
-  hysteresis: 2  # Gradient scale hysteresis
-  fp32_residual_connection: false  # Move residual connections to fp32
-  fp16_lm_cross_entropy: false  # Move the cross entropy unreduced loss calculation for lm head to fp16
-
-  # Megatron O2-style half-precision
-  megatron_amp_O2: true  # Enable O2-level automatic mixed precision using main parameters
-  grad_allreduce_chunk_size_mb: 125
-
-  # Fusion
-  grad_div_ar_fusion: true  # Fuse grad division into torch.distributed.all_reduce. Only used with O2 and no pipeline parallelism..
-  gradient_accumulation_fusion: true  # Fuse weight gradient accumulation to GEMMs. Only used with pipeline parallelism and O2.
-  bias_activation_fusion: true  # Use a kernel that fuses the bias addition from weight matrices with the subsequent activation function.
-  bias_dropout_add_fusion: true  # Use a kernel that fuses the bias addition, dropout and residual connection addition.
-  masked_softmax_fusion: true  # Use a kernel that fuses the attention softmax with it's mask.
-  apply_rope_fusion: true  # Use a kernel to add rotary positional embeddings. Only used if position_embedding_type=rope
-  cross_entropy_loss_fusion: true
-
-  # Miscellaneous
-  seed: 1234
-  resume_from_checkpoint: null  # manually set the checkpoint file to load from
-  use_cpu_initialization: false  # Init weights on the CPU (slow for large models)
-  onnx_safe: false  # Use work-arounds for known problems with Torch ONNX exporter.
-  apex_transformer_log_level: 30  # Python logging level displays logs with severity greater than or equal to this
-  gradient_as_bucket_view: true  # PyTorch DDP argument. Allocate gradients in a contiguous bucket to save memory (less fragmentation and buffer memory)
-  sync_batch_comm: false  # Enable stream synchronization after each p2p communication between pipeline stages
-
-  ## Activation Checkpointing
-  # NeMo Megatron supports 'selective' activation checkpointing where only the memory intensive part of attention is checkpointed.
-  # These memory intensive activations are also less compute intensive which makes activation checkpointing more efficient for LLMs (20B+).
-  # See Reducing Activation Recomputation in Large Transformer Models: https://arxiv.org/abs/2205.05198 for more details.
-  # 'full' will checkpoint the entire transformer layer.
-  activations_checkpoint_granularity: null  # 'selective' or 'full'
-  activations_checkpoint_method: null  # 'uniform', 'block'
-  # 'uniform' divides the total number of transformer layers and checkpoints the input activation
-  # of each chunk at the specified granularity. When used with 'selective', 'uniform' checkpoints all attention blocks in the model.
-  # 'block' checkpoints the specified number of layers per pipeline stage at the specified granularity
-  activations_checkpoint_num_layers: null
-  # when using 'uniform' this creates groups of transformer layers to checkpoint. Usually set to 1. Increase to save more memory.
-  # when using 'block' this this will checkpoint the first activations_checkpoint_num_layers per pipeline stage.
-  num_micro_batches_with_partial_activation_checkpoints: null
-  # This feature is valid only when used with pipeline-model-parallelism.
-  # When an integer value is provided, it sets the number of micro-batches where only a partial number of Transformer layers get checkpointed
-  # and recomputed within a window of micro-batches. The rest of micro-batches in the window checkpoint all Transformer layers. The size of window is
-  # set by the maximum outstanding micro-batch backpropagations, which varies at different pipeline stages. The number of partial layers to checkpoint
-  # per micro-batch is set by 'activations_checkpoint_num_layers' with 'activations_checkpoint_method' of 'block'.
-  # This feature enables using activation checkpoint at a fraction of micro-batches up to the point of full GPU memory usage.
-  activations_checkpoint_layers_per_pipeline: null
-  # This feature is valid only when used with pipeline-model-parallelism.
-  # When an integer value (rounded down when float is given) is provided, it sets the number of Transformer layers to skip checkpointing at later
-  # pipeline stages. For example, 'activations_checkpoint_layers_per_pipeline' of 3 makes pipeline stage 1 to checkpoint 3 layers less than
-  # stage 0 and stage 2 to checkpoint 6 layers less stage 0, and so on. This is possible because later pipeline stage
-  # uses less GPU memory with fewer outstanding micro-batch backpropagations. Used with 'num_micro_batches_with_partial_activation_checkpoints',
-  # this feature removes most of activation checkpoints at the last pipeline stage, which is the critical execution path.
-
-  ## Transformer Engine
-  transformer_engine: true
-  fp8: false  # enables fp8 in TransformerLayer forward
-  fp8_e4m3: false  # sets fp8_format = recipe.Format.E4M3
-  fp8_hybrid: false  # sets fp8_format = recipe.Format.HYBRID
-  fp8_margin: 0  # scaling margin
-  fp8_interval: 1  # scaling update interval
-  fp8_amax_history_len: 1024  # Number of steps for which amax history is recorded per tensor
-  fp8_amax_compute_algo: 'max'  # 'most_recent' or 'max'. Algorithm for computing amax from history
-  ub_tp_comm_overlap: false  # do not turn on because of b/397797926
-  use_flash_attention: true
-  gc_interval: 100
-
-  ## Offloading Activations/Weights to CPU
-  cpu_offloading: false
-  cpu_offloading_num_layers: ${sum:${.num_layers},-1}  # This value should be between [1,num_layers-1] as we don't want to offload the final layer's activations and expose any offloading duration for the final layer
-  cpu_offloading_activations: true
-  cpu_offloading_weights: true
-
-  data:
-    # Path to data must be specified by the user.
-    # Supports List, String and Dictionary
-    # List : can override from the CLI: "model.data.data_prefix=[.5,/raid/data/pile/my-gpt3_00_text_document,.5,/raid/data/pile/my-gpt3_01_text_document]",
-    # Or see example below:
-    # data_prefix:
-    # - .5
-    # - /raid/data/pile/my-gpt3_00_text_document
-    # - .5
-    # - /raid/data/pile/my-gpt3_01_text_document
-    # Dictionary: can override from CLI "model.data.data_prefix"={"train":[1.0, /path/to/data], "validation":/path/to/data, "test":/path/to/test}
-    # Or see example below:
-    # "model.data.data_prefix: {train:[1.0,/path/to/data], validation:[/path/to/data], test:[/path/to/test]}"
-    data_prefix: [1.0, /data/hfbpe_gpt_training_data_text_document]
-    index_mapping_dir: null  # path to save index mapping .npy files, by default will save in the same location as data_prefix
-    data_impl: mmap
-    splits_string: 900,50,50
-    seq_length: ${model.encoder_seq_length}
-    skip_warmup: true
-    num_workers: 2
-    dataloader_type: single  # cyclic
-    reset_position_ids: false  # Reset position ids after end-of-document token
-    reset_attention_mask: false  # Reset attention mask after end-of-document token
-    eod_mask_loss: false  # Mask loss for the end of document tokens
-    validation_drop_last: true  # Set to false if the last partial validation samples is to be consumed
-    no_seqlen_plus_one_input_tokens: false  # Set to True to disable fetching (sequence length + 1) input tokens, instead get (sequence length) input tokens and mask the last token
-    pad_samples_to_global_batch_size: false  # Set to True if you want to pad the last partial batch with -1's to equal global batch size
-    shuffle_documents: true  # Set to False to disable documents shuffling. Sample index will still be shuffled
-
-  # Nsys profiling options
-  nsys_profile:
-    enabled: false
-    start_step: 0  # Global batch to start profiling
-    end_step: 1  # Global batch to end profiling
-    ranks: [0]  # Global rank IDs to profile
-    gen_shape: false  # Generate model and kernel details including input shapes
-
-  memory_profile:
-    enabled: false
-    start_step: 0
-    end_step: 1
-    ranks: [0]
-    output_path: /data  # Must be a dir
-
-  optim:
-    name: distributed_fused_adam  # E.g., fused_adam or set _target_: torch.optim.AdamW field
-    lr: 2e-5
-    weight_decay: 0.01
-    betas:
-    - 0.9
-    - 0.98
-    bucket_cap_mb: 125
-    overlap_grad_sync: true
-    overlap_param_sync: true
-    contiguous_grad_buffer: true
-    contiguous_param_buffer: true
-    sched:
-      name: CosineAnnealing
-      warmup_steps: 400
-      constant_steps: 0
-      min_lr: 2e-6

community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining/docker/cloudbuild.yml

@@ -1,26 +0,0 @@
-# Copyright 2024 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-steps:
-- name: 'gcr.io/cloud-builders/docker'
-  args:
-  - 'build'
-  - '--tag=${_ARTIFACT_REGISTRY}/${_IMAGE_NAME}'
-  - '--file=docker/vertex-dist-recipes.Dockerfile'
-  - '.'
-  automapSubstitutions: true
-  env:
-  - 'DOCKER_BUILDKIT=1'
-images:
-- '${_ARTIFACT_REGISTRY}/${_IMAGE_NAME}'

community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining/docker/patches/24.09/gpu_stats.patch

@@ -1,41 +0,0 @@
-diff --git a/nemo/collections/nlp/parts/megatron_trainer_builder.py b/nemo/collections/nlp/parts/megatron_trainer_builder.py
-index b2c85cde4..a3a9670c3 100644
---- a/nemo/collections/nlp/parts/megatron_trainer_builder.py
-+++ b/nemo/collections/nlp/parts/megatron_trainer_builder.py
-@@ -19,6 +19,7 @@ from lightning_fabric.utilities.exceptions import MisconfigurationException
- from omegaconf import DictConfig
- from pytorch_lightning import Trainer
- from pytorch_lightning.callbacks import ModelSummary
-+from pytorch_lightning.callbacks import Callback
- from pytorch_lightning.plugins.environments import TorchElasticEnvironment
-
- from nemo.collections.common.metrics.perf_metrics import FLOPsMeasurementCallback
-@@ -38,6 +39,23 @@ from nemo.utils.callbacks.dist_ckpt_io import (
-     AsyncFinalizerCallback,
-     DistributedCheckpointIO,
- )
-+from vmg.util.device_stats import gpu_stats_str
-+
-+class GpuStatsMon(Callback):
-+    def on_train_start(self, trainer, pl_module) -> None:
-+        rank=pl_module.global_rank
-+        print(f'train_start: {rank=} {gpu_stats_str()}', flush=True)
-+
-+    def on_train_batch_start(self, trainer, pl_module, batch, batch_idx) -> None:
-+        rank=pl_module.global_rank
-+        print(f'batch_start: {rank=} {gpu_stats_str()}', flush=True)
-+
-+    def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx) -> None:
-+        rank=pl_module.global_rank
-+        print(f'batch_end: {rank=} {gpu_stats_str()}', flush=True)
-
-
- class MegatronTrainerBuilder:
-@@ -178,6 +196,7 @@ class MegatronTrainerBuilder:
-         if self.cfg.get('exp_manager', {}).get('log_tflops_per_sec_per_gpu', True):
-             callbacks.append(FLOPsMeasurementCallback(self.cfg))
-
-+        callbacks.append(GpuStatsMon())
-         return callbacks
-
-     def create_trainer(self, callbacks=None) -> Trainer:

community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining/docker/patches/24.09/local_rank.patch

@@ -1,41 +0,0 @@
-diff -ruN old-datasets/blended_megatron_dataset_builder.py datasets/blended_megatron_dataset_builder.py
---- old-datasets/blended_megatron_dataset_builder.py	2025-05-02 04:08:45.369199665 +0000
-+++ datasets/blended_megatron_dataset_builder.py	2025-05-02 04:10:47.369119891 +0000
-@@ -2,6 +2,7 @@
-
- import logging
- import math
-+import os
- from concurrent.futures import ThreadPoolExecutor
- from typing import Any, Callable, Iterable, List, Optional, Type, Union
-
-@@ -353,7 +354,7 @@
-         num_dataset_builder_threads = self.config.num_dataset_builder_threads
-
-         if torch.distributed.is_initialized():
--            rank = torch.distributed.get_rank()
-+            rank = int(os.getenv("LOCAL_RANK", "0"))
-             # First, build on rank 0
-             if rank == 0:
-                 num_workers = num_dataset_builder_threads
-@@ -475,7 +476,7 @@
-             Optional[Union[DistributedDataset, Iterable]]: The DistributedDataset instantion, the Iterable instantiation, or None
-         """
-         if torch.distributed.is_initialized():
--            rank = torch.distributed.get_rank()
-+            rank = int(os.getenv("LOCAL_RANK", "0"))
-
-             dataset = None
-
-diff -ruN old-datasets/gpt_dataset.py datasets/gpt_dataset.py
---- old-datasets/gpt_dataset.py	2025-05-02 04:08:45.369199665 +0000
-+++ datasets/gpt_dataset.py	2025-05-02 04:09:30.309170278 +0000
-@@ -351,7 +351,7 @@
-
-         if not path_to_cache or (
-             not cache_hit
--            and (not torch.distributed.is_initialized() or torch.distributed.get_rank() == 0)
-+            and (not torch.distributed.is_initialized() or int(os.getenv("LOCAL_RANK", "0")) == 0)
-         ):
-
-             log_single_rank(

community-content/vertex-distributed-training/a3mega/llama-3-8b-nemo-pretraining/docker/patches/24.09/nemo2hf.patch

@@ -1,13 +0,0 @@
-diff --git a/scripts/checkpoint_converters/convert_llama_nemo_to_hf.py b/scripts/checkpoint_converters/convert_llama_nemo_to_hf.py
-index 8da15148d..005cae6c9 100644
---- a/scripts/checkpoint_converters/convert_llama_nemo_to_hf.py
-+++ b/scripts/checkpoint_converters/convert_llama_nemo_to_hf.py
-@@ -104,6 +104,8 @@ def convert(input_nemo_file, output_hf_file, precision=None, cpu_only=False) ->
-     dummy_trainer = Trainer(devices=1, accelerator='cpu', strategy=NLPDDPStrategy())
-     model_config = MegatronGPTModel.restore_from(input_nemo_file, trainer=dummy_trainer, return_config=True)
-     model_config.tensor_model_parallel_size = 1
-+    model_config.virtual_pipeline_model_parallel_size = None
-+    model_config.sequence_parallel = False
-     model_config.pipeline_model_parallel_size = 1
-     if cpu_only:
-         map_location = torch.device('cpu')