fix: missing bucket

* Update stable_diffusion notebook with steps for local inference.

* Lint

* Move comments to top and shorten line.

* Lint

* Make code comment titles, add print statements, and update Objective

* change print to display

* lint

* change training dockers to serving dockers

.cloud-build/execute_changed_notebooks_cli.py

@@ -17,7 +17,7 @@
 
 import argparse
 import pathlib
-import random
+import os
 
 import execute_changed_notebooks_helper
 
@@ -47,6 +47,12 @@ parser.add_argument(
     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.",
@@ -129,26 +135,35 @@ changed_notebooks = execute_changed_notebooks_helper.get_changed_notebooks(
     base_branch=args.base_branch,
 )
 
+
+results_bucket = f"{args.artifacts_bucket}"
+results_file = f"{args.build_id}.json"
+
 if args.test_percent == 100:
     notebooks = changed_notebooks
+    accumulative_results = {}
 else:
-    notebooks = [changed_notebook for changed_notebook in changed_notebooks if random.randint(1, 100) < args.test_percent]
+    accumulative_results = execute_changed_notebooks_helper.load_results(results_bucket, results_file)
+
+    notebooks = [changed_notebook for changed_notebook in changed_notebooks if execute_changed_notebooks_helper.select_notebook(changed_notebook, accumulative_results, args.test_percent)]
 
 if args.dry_run:
     print("Dry run ...\n")
     for notebook in notebooks:
-        print(f"Would execute: {notebook.path}")
+        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,
+        accumulative_results=accumulative_results,
         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,
+        private_pool_id=args.private_pool_id
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -21,11 +21,15 @@ import json
 import git
 import operator
 import os
+import io
+import json
 import pathlib
 import re
 import subprocess
+import random
+from google.cloud import storage
 import utils
-from typing import List, Optional
+from typing import List, Optional, Dict, Any
 from utils import util
 
 import execute_notebook_helper
@@ -65,7 +69,9 @@ def format_timedelta(delta: datetime.timedelta) -> str:
 @dataclasses.dataclass
 class NotebookExecutionResult:
     name: str
+    path: str
     duration: datetime.timedelta
+    start_time: datetime.datetime
     is_pass: bool
     log_url: str
     output_uri: str
@@ -80,6 +86,40 @@ class NotebookExecutionResult:
         else:
             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:
+        content = util.download_blob_into_memory(results_bucket, results_file, download_as_text=True)
+        accumulative_results = json.loads(content)
+        print(accumulative_results)
+    except Exception as e:
+        print(e)
+
+    # If there are no accumulative results, an empty dict is returned
+    return accumulative_results
+
+def select_notebook(changed_notebook: str,
+                    accumulative_results: Dict[str, Any],
+                    test_percent: int) -> bool:
+    '''
+    Algorithm to randomly select a notebook, but weight the propbability of selected based on past failures
+    '''
+
+    if changed_notebook in accumulative_results:
+        pass_count = accumulative_results[changed_notebook]['passed']
+        fail_count = accumulative_results[changed_notebook]['failed']
+    else:
+        pass_count = 1
+        fail_count = 0
+
+    return (random.randint(1, 100) * (1 + (fail_count / (pass_count + fail_count))) < test_percent)
+
 
 def _process_notebook(
     notebook_path: str,
@@ -191,7 +231,9 @@ def process_and_execute_notebook(
 
     result = NotebookExecutionResult(
         name=tag,
+        path=notebook,
         duration=datetime.timedelta(seconds=0),
+        start_time=datetime.datetime.now(),
         is_pass=False,
         output_uri=notebook_output_uri,
         log_url="",
@@ -201,7 +243,6 @@ def process_and_execute_notebook(
     )
 
     # TODO: Handle cases where multiple notebooks have the same name
-    time_start = datetime.datetime.now()
     operation = None
     try:
         # Get the python version for running the notebook if specified
@@ -247,9 +288,10 @@ def process_and_execute_notebook(
         # Block and wait for the result
         operation_result = operation.result(timeout=timeout_in_seconds)
 
-        result.duration = datetime.datetime.now() - time_start
+        result.duration = datetime.datetime.now() - result.start_time
         result.is_pass = True
         print(f"{notebook} PASSED in {format_timedelta(result.duration)}.")
+
     except Exception as error:
         result.error_message = str(error)
 
@@ -268,7 +310,7 @@ def process_and_execute_notebook(
             except Exception as error:
                 result.error_message = str(error)
 
-        result.duration = datetime.datetime.now() - time_start
+        result.duration = datetime.datetime.now() - result.start_time
         result.is_pass = False
 
         print(
@@ -336,12 +378,54 @@ def get_changed_notebooks(
 
     return notebooks
 
+def _save_results(results: List[NotebookExecutionResult],
+                  accumulative_results: Dict[str,Any],
+                  artifacts_bucket: str,
+                  results_file: str):
+
+    artifacts_bucket = artifacts_bucket.replace("gs://", "").split('/')[0]
+
+    print("Updating accumulative results ...")
+    for result in results:
+        if result.path in accumulative_results:
+            accumulative_results[result.path]['duration'] = result.duration.total_seconds()
+            accumulative_results[result.path]['start_time'] = str(result.start_time)
+            if result.is_pass:
+                accumulative_results[result.path]['passed'] += 1
+            else:
+                accumulative_results[result.path]['failed'] += 1
+            print(f"updating {result.path}")
+        else:
+            if result.is_pass:
+                pass_count = 1
+                fail_count = 0
+            else:
+                pass_count = 0
+                fail_count = 1
+            accumulative_results[result.path] = {
+                    'duration': result.duration.total_seconds(),
+                    'start_time': str(result.start_time),
+                    'passed': pass_count,
+                    'failed': fail_count
+                    }
+            print(f"adding {result.path}")
+
+    print("Saving accumulative results ...")
+    content = json.dumps(accumulative_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,
+    accumulative_results: List[NotebookExecutionResult],
     should_parallelize: bool,
     timeout: int,
     variable_project_id: str,
@@ -369,6 +453,10 @@ 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 
+        accumulative_results (List):
+            Required: The in-memory previous accumulative notebook CI/CD test results.
         variable_project_id (str):
             Required. The value for PROJECT_ID to inject into notebooks.
         variable_region (str):
@@ -471,7 +559,7 @@ def process_and_execute_notebooks(
             print("=" * 100)
 
             build_id = results_sorted[0].build_id
-            logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
+            logs_bucket_name = (results_sorted[0].logs_bucket).replace("gs://", "")
             log_file_name = f"log-{build_id}.txt"
 
             log_contents = util.download_blob_into_memory(
@@ -489,6 +577,11 @@ def process_and_execute_notebooks(
             else:
                 print(log_contents)
 
+        _save_results(results_sorted, 
+                      accumulative_results,
+                      artifacts_bucket, 
+                      results_file)
+
         print("\n=== END RESULTS===\n")
 
         total_notebook_duration = functools.reduce(

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

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

.cloud-build/requirements.txt

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

notebooks/community/ml_ops/stage3/get_started_vertex_pipelines_xgboost_with_prediction.ipynb

@@ -196,7 +196,7 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "! pip3 install {USER_FLAG} --upgrade --quiet google-cloud-aiplatform \\\n",
-        "                                             google-cloud-pipeline-components \\\n",
+        "                                             google-cloud-pipeline-components==1.0.25 \\\n",
         "                                             kfp "
       ]
     },

notebooks/community/model_garden/model_garden_pipeline_templates_bert.ipynb

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

notebooks/community/model_garden/model_garden_pipeline_templates_t5x.ipynb

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

notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb

@@ -184,7 +184,9 @@
         "\n",
         "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
         "\n",
-        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
       ]
     },
     {
@@ -211,7 +213,10 @@
         "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
         "\n",
         "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
-        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account you created in step-5 above, it's like \"<account_name>@<project>.iam.gserviceaccount.com\"\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -271,7 +276,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "id": "354da31189dc"
       },
@@ -336,8 +341,6 @@
         "        \"MODEL_ID\": model_id,\n",
         "        \"TASK\": task,\n",
         "    }\n",
-        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
-        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
         "    model = aiplatform.Model.upload(\n",
         "        display_name=model_name,\n",
         "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
@@ -345,7 +348,6 @@
         "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
         "        serving_container_health_route=\"/ping\",\n",
         "        serving_container_environment_variables=serving_env,\n",
-        "        artifact_uri=artifact_uri,\n",
         "    )\n",
         "    model.deploy(\n",
         "        endpoint=endpoint,\n",
@@ -353,6 +355,7 @@
         "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
         "        accelerator_count=1,\n",
         "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
         "    )\n",
         "    return model, endpoint"
       ]
@@ -427,6 +430,8 @@
         "        \"--resolution=512\",\n",
         "        \"--learning_rate=1e-5\",\n",
         "        \"--train_batch_size=2\",\n",
+        "        \"--checkpointing_steps=50000\",\n",
+        "        \"--checkpoints_total_limit=1\",\n",
         "    ],\n",
         "    replica_count=num_nodes,\n",
         "    machine_type=machine_type,\n",
@@ -572,7 +577,7 @@
       "outputs": [],
       "source": [
         "model, endpoint = deploy_model(\n",
-        "    model_id=f\"gs://{GCS_BUCKET}/controlnet/output\", task=\"image-to-image\"\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/controlnet/output\", task=\"controlnet\"\n",
         ")"
       ]
     },

notebooks/community/model_garden/model_garden_pytorch_detectron2.ipynb

@@ -45,7 +45,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>                                                                                               <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_detectron2.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_detectron2.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -189,7 +189,9 @@
         "\n",
         "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
         "\n",
-        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User`, `Storage Object Admin`, and `GCS Storage Bucket Owner` roles for deploying fine tuned model to Vertex AI endpoint."
       ]
     },
     {
@@ -213,10 +215,16 @@
         "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
         "\n",
         "# The region you want to launch jobs in.\n",
-        "REGION = \"\"  # @param {type:\"string\"}\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
         "\n",
         "# The Cloud Storage bucket for storing experiments output. For example 'gs://my_bucket'.\n",
-        "BUCKET_URI = \"\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model.\n",
+        "# The service account looks like:\n",
+        "# '<account_name>@<project>.iam.gserviceaccount.com'\n",
+        "# Follow step 5 above to create this account.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -814,7 +822,8 @@
       },
       "outputs": [],
       "source": [
-        "local_balloon_data_directory = \"balloon\"  # @param {type:\"string\"}"
+        "local_balloon_data_directory = \"balloon\"  # @param {type:\"string\"}\n",
+        "BALLOON_DATA_GCS_PATH = os.path.join(BUCKET_URI, \"balloon_dataset\")"
       ]
     },
     {
@@ -902,14 +911,47 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "oOfgze5RpJQ8"
+        "id": "0OykIZen9gCC"
       },
       "outputs": [],
       "source": [
         "# Move Balloon data from local directory to Cloud Storage.\n",
-        "BALLOON_DATA_GCS_PATH = os.path.join(BUCKET_URI, \"balloon_dataset\")\n",
-        "!gsutil -m cp -r $local_balloon_data_directory/* $BALLOON_DATA_GCS_PATH/\n",
-        "!gsutil ls $BALLOON_DATA_GCS_PATH"
+        "\n",
+        "import glob\n",
+        "\n",
+        "from google.cloud import storage\n",
+        "\n",
+        "\n",
+        "def get_bucket_and_blob_name(filepath):\n",
+        "    # The gcs path is of the form gs://<bucket-name>/<blob-name>\n",
+        "    gs_suffix = filepath.split(\"gs://\", 1)[1]\n",
+        "    return tuple(gs_suffix.split(\"/\", 1))\n",
+        "\n",
+        "\n",
+        "def upload_local_dir_to_gcs(local_dir_path, gcs_dir_path):\n",
+        "    \"\"\"Uploads files in a local directory to a GCS directory.\"\"\"\n",
+        "    client = storage.Client()\n",
+        "    bucket_name = gcs_dir_path.split(\"/\")[2]\n",
+        "    bucket = client.get_bucket(bucket_name)\n",
+        "    for local_file in glob.glob(local_dir_path + \"/**\"):\n",
+        "        if not os.path.isfile(local_file):\n",
+        "            continue\n",
+        "        filename = local_file[1 + len(local_dir_path) :]\n",
+        "        gcs_file_path = os.path.join(gcs_dir_path, filename)\n",
+        "        _, blob_name = get_bucket_and_blob_name(gcs_file_path)\n",
+        "        blob = bucket.blob(blob_name)\n",
+        "        blob.upload_from_filename(local_file)\n",
+        "        print(\"Copied {} to {}.\".format(local_file, gcs_file_path))\n",
+        "\n",
+        "\n",
+        "upload_local_dir_to_gcs(\n",
+        "    os.path.join(local_balloon_data_directory, \"train\"),\n",
+        "    os.path.join(BALLOON_DATA_GCS_PATH, \"train\"),\n",
+        ")\n",
+        "upload_local_dir_to_gcs(\n",
+        "    os.path.join(local_balloon_data_directory, \"val\"),\n",
+        "    os.path.join(BALLOON_DATA_GCS_PATH, \"val\"),\n",
+        ")"
       ]
     },
     {
@@ -944,26 +986,22 @@
         "train_dataset_name = \"balloon_train\"  # @param {type:\"string\"}\n",
         "train_coco_json_file = os.path.join(\n",
         "    BALLOON_DATA_GCS_PATH, \"train/balloon_train_coco_format.json\"\n",
-        ")  # @param {type:\"string\"}\n",
+        ")\n",
         "train_coco_json_file = gcs_fuse_path(train_coco_json_file)\n",
-        "train_image_root = os.path.join(\n",
-        "    BALLOON_DATA_GCS_PATH, \"train\"\n",
-        ")  # @param {type:\"string\"}\n",
+        "train_image_root = os.path.join(BALLOON_DATA_GCS_PATH, \"train\")\n",
         "train_image_root = gcs_fuse_path(train_image_root)\n",
         "val_dataset_name = \"balloon_val\"  # @param {type:\"string\"}\n",
         "val_coco_json_file = os.path.join(\n",
         "    BALLOON_DATA_GCS_PATH, \"val/balloon_val_coco_format.json\"\n",
-        ")  # @param {type:\"string\"}\n",
+        ")\n",
         "val_coco_json_file = gcs_fuse_path(val_coco_json_file)\n",
-        "val_image_root = os.path.join(BALLOON_DATA_GCS_PATH, \"val\")  # @param {type:\"string\"}\n",
+        "val_image_root = os.path.join(BALLOON_DATA_GCS_PATH, \"val\")\n",
         "val_image_root = gcs_fuse_path(val_image_root)\n",
         "output_dir = os.path.join(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "#################################################\n",
         "# Model and dataset related parameters for Mask R-CNN.\n",
-        "config_file = (\n",
-        "    \"COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml\"  # @param {type:\"string\"}\n",
-        ")\n",
+        "config_file = \"COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml\"\n",
         "config_file = gcs_fuse_path(config_file)\n",
         "remainder_args_list = []\n",
         "remainder_args_list += [\"DATASETS.TRAIN\"] + [\n",
@@ -982,7 +1020,7 @@
         "\n",
         "# #################################################\n",
         "# # Model and dataset related parameters for RetinaNet.\n",
-        "# config_file='COCO-Detection/retinanet_R_50_FPN_3x.yaml' # @param {type:\"string\"}\n",
+        "# config_file='COCO-Detection/retinanet_R_50_FPN_3x.yaml'\n",
         "# config_file = gcs_fuse_path(config_file)\n",
         "# remainder_args_list = []\n",
         "# remainder_args_list += ['DATASETS.TRAIN'] + ['(\"{train_dataset_name}\",)'.format(train_dataset_name=train_dataset_name)]\n",
@@ -998,7 +1036,7 @@
         "\n",
         "# #################################################\n",
         "# # Model and dataset related parameters for Faster R-CNN.\n",
-        "# config_file='COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml' # @param {type:\"string\"}\n",
+        "# config_file='COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml'\n",
         "# config_file = gcs_fuse_path(config_file)\n",
         "# remainder_args_list = []\n",
         "# remainder_args_list += ['DATASETS.TRAIN'] + ['(\"{train_dataset_name}\",)'.format(train_dataset_name=train_dataset_name)]\n",
@@ -1054,7 +1092,6 @@
         "job = aiplatform.CustomContainerTrainingJob(\n",
         "    display_name=JOB_NAME,\n",
         "    container_uri=container_uri,\n",
-        "    command=[\"python\", \"-m\", \"trainer.task\"],\n",
         ")\n",
         "model = job.run(\n",
         "    args=docker_args_list,\n",
@@ -1088,17 +1125,13 @@
         "# Upload models to model registry\n",
         "from datetime import datetime\n",
         "\n",
-        "PRETRAINED_MODEL_PTH_FILE = os.path.join(\n",
-        "    output_dir, \"model_final.pth\"\n",
-        ")  # @param {type:\"string\"}\n",
-        "PRETRAINED_MODEL_CFG_YAML_FILE = os.path.join(\n",
-        "    output_dir, \"config.yaml\"\n",
-        ")  # @param {type:\"string\"}\n",
+        "PRETRAINED_MODEL_PTH_FILE = os.path.join(output_dir, \"model_final.pth\")\n",
+        "PRETRAINED_MODEL_CFG_YAML_FILE = os.path.join(output_dir, \"config.yaml\")\n",
         "TEST_THRESHOLD = 0.7\n",
         "PREDICTION_CONTAINER_URI = SERVE_DOCKER_URI\n",
         "PREDICTION_DISPLAY_NAME = \"upload_detectron2_\" + datetime.now().strftime(\n",
         "    \"%Y%m%d_%H%M%S\"\n",
-        ")  # @param {type:\"string\"}\n",
+        ")\n",
         "\n",
         "model = upload_model(\n",
         "    project=PROJECT_ID,\n",
@@ -1123,9 +1156,7 @@
         "# Deploy uploaded models\n",
         "from datetime import datetime\n",
         "\n",
-        "DEPLOYED_NAME = \"deploy_iod_\" + datetime.now().strftime(\n",
-        "    \"%Y%m%d_%H%M%S\"\n",
-        ")  # @param {type:\"string\"}\n",
+        "DEPLOYED_NAME = \"deploy_iod_\" + datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
         "MACHINE_TYPE = \"n1-highmem-16\"  # @param {type:\"string\"}\n",
         "\n",
         "TRAFFIC_SPLIT = {\"0\": 100}\n",
@@ -1133,13 +1164,13 @@
         "MIN_NODES = 1\n",
         "MAX_NODES = 1\n",
         "\n",
-        "\n",
         "endpoint = model.deploy(\n",
         "    deployed_model_display_name=DEPLOYED_NAME,\n",
         "    traffic_split=TRAFFIC_SPLIT,\n",
         "    machine_type=MACHINE_TYPE,\n",
         "    min_replica_count=MIN_NODES,\n",
         "    max_replica_count=MAX_NODES,\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
         ")\n",
         "\n",
         "print(\"endpoint id is: \", endpoint.name)"
@@ -1155,11 +1186,12 @@
       "source": [
         "# Run predictions\n",
         "# Fill the \"endpoint_id\" from previous step below.\n",
+        "# For example 'endpoint_id = \"8211918096324100096\"'.\n",
         "\n",
-        "endpoint_id = \"1218390824971141120\"  # @param {type:\"string\"}\n",
+        "endpoint_id = \"\"  # @param {type:\"string\"}\n",
         "local_test_filepath = os.path.join(\n",
         "    local_balloon_data_directory, \"val/410488422_5f8991f26e_b.jpg\"\n",
-        ")  # @param {type:\"string\"}\n",
+        ")\n",
         "instances = get_prediction_instances(local_test_filepath)\n",
         "api_endpoint = REGION + \"-aiplatform.googleapis.com\"\n",
         "\n",
@@ -1182,7 +1214,7 @@
         "boxes = prediction[\"boxes\"]\n",
         "classes = prediction[\"classes\"]\n",
         "scores = prediction[\"scores\"]\n",
-        "if \"masks_rle\" in prediction:\n",
+        "if prediction[\"masks_rle\"]:\n",
         "    masks_numpy = decode_rle_masks(prediction[\"masks_rle\"])\n",
         "else:\n",
         "    masks_numpy = None\n",

notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb

@@ -24,6 +24,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "99c1c3fc2ca5"
@@ -48,12 +49,13 @@
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "Open in Vertex AI Workbench\n",
         "    </a>\n",
-        "    (a Python-3 CPU notebook is recommended)\n",
+        "    (a Python-3 GPU notebook with preinstalled HuggingFace/transformer libraries is recommended)\n",
         "  </td>\n",
         "</table>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "3de7470326a2"
@@ -61,13 +63,15 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook demonstrates finetuning [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth) and deploying it on Vertex AI for online prediction.\n",
+        "This notebook demonstrates running local inference on [Vertex AI Workbench](https://cloud.google.com/vertex-ai-workbench).\n",
+        "This notebook also demonstrates finetuning [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth) and deploying it on Vertex AI for online prediction.\n",
         "\n",
         "### Objective\n",
         "\n",
+        "- Run local predictions for text-to-image and text-guided-image-to-image with serving dockers.\n",
         "- Finetune the stable-diffusion-v1.5 model with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth).\n",
-        "- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
-        "- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Upload the model to [Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model to a [Vertex AI Endpoint resource](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
         "- Run online predictions for text-to-image and text-guided-image-to-image.\n",
         "\n",
         "### Costs\n",
@@ -81,6 +85,114 @@
       ]
     },
     {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e8a42fa49305"
+      },
+      "source": [
+        "## Local inference (Workbench only)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1169c41b76b3"
+      },
+      "source": [
+        "The quickest and easiest way to use this model locally is by using Vertex AI Workbench with a pre-built custom container that has the necessary packages installed.\n",
+        "\n",
+        "\n",
+        "\n",
+        "1.   Follow [this link](https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb) to deploy the notebook to a Vertex AI Workbench Instance.\n",
+        "2.   Select `Create a new Notebook`.\n",
+        "3.   Click `Advanced Options`.\n",
+        "4.   Under **Environment**, select `Custom Container` for `Environment`. \n",
+        "5.   Set `Docker container image` to `us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/transformers-notebook`.\n",
+        "6.   Under **Machine configuration**, select a GPU and select `Install NVIDIA GPU driver automatically for me`.\n",
+        "7.   Click `Create` to create the Vertex AI Workbench instance. \n",
+        "\n",
+        "Once the notebook is ready, simply execute the code block(s) below in the Workbench instance."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1d5ebc91c786"
+      },
+      "source": [
+        "### Text-to-image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d39ed8c97cc5"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "from diffusers import StableDiffusionPipeline\n",
+        "\n",
+        "model_id = \"runwayml/stable-diffusion-v1-5\"\n",
+        "pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)\n",
+        "pipe = pipe.to(\"cuda\")\n",
+        "\n",
+        "prompt = \"a photo of an astronaut riding a horse on mars\"\n",
+        "image = pipe(prompt).images[0]\n",
+        "\n",
+        "display(image)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5aed5ed7b6f6"
+      },
+      "source": [
+        "### Text-guided image-to-image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "faadabb7728f"
+      },
+      "outputs": [],
+      "source": [
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "import torch\n",
+        "from diffusers import StableDiffusionImg2ImgPipeline\n",
+        "from PIL import Image\n",
+        "\n",
+        "device = \"cuda\"\n",
+        "model_id_or_path = \"runwayml/stable-diffusion-v1-5\"\n",
+        "pipe = StableDiffusionImg2ImgPipeline.from_pretrained(\n",
+        "    model_id_or_path, torch_dtype=torch.float16\n",
+        ")\n",
+        "pipe = pipe.to(device)\n",
+        "\n",
+        "url = \"https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg\"\n",
+        "\n",
+        "response = requests.get(url)\n",
+        "init_image = Image.open(BytesIO(response.content)).convert(\"RGB\")\n",
+        "init_image = init_image.resize((768, 512))\n",
+        "\n",
+        "prompt = \"A fantasy landscape, trending on artstation\"\n",
+        "\n",
+        "images = pipe(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "264c07757582"
@@ -92,6 +204,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "d73ffa0c0b83"
@@ -125,6 +238,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "fb671e75ca7b"
@@ -142,12 +256,11 @@
       "outputs": [],
       "source": [
         "# Install gdown for downloading example training images.\n",
-        "!pip install gdown\n",
-        "# Install gsutil for downloading/uploading data from/to Cloud Storage buckets.\n",
-        "!pip install gsutil"
+        "!pip install gdown"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "5244aac3d929"
@@ -171,6 +284,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "bb7adab99e41"
@@ -184,10 +298,13 @@
         "\n",
         "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
         "\n",
-        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6c460088b873"
@@ -211,10 +328,14 @@
         "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
         "\n",
         "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
-        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "e828eb320337"
@@ -237,6 +358,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "2cc825514deb"
@@ -261,6 +383,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "0c250872074f"
@@ -278,12 +401,13 @@
       "outputs": [],
       "source": [
         "import base64\n",
+        "import glob\n",
         "import os\n",
         "from datetime import datetime\n",
         "from io import BytesIO\n",
         "\n",
         "import requests\n",
-        "from google.cloud import aiplatform\n",
+        "from google.cloud import aiplatform, storage\n",
         "from PIL import Image\n",
         "\n",
         "\n",
@@ -326,8 +450,6 @@
         "        \"MODEL_ID\": model_id,\n",
         "        \"TASK\": task,\n",
         "    }\n",
-        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
-        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
         "    model = aiplatform.Model.upload(\n",
         "        display_name=model_name,\n",
         "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
@@ -335,7 +457,6 @@
         "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
         "        serving_container_health_route=\"/ping\",\n",
         "        serving_container_environment_variables=serving_env,\n",
-        "        artifact_uri=artifact_uri,\n",
         "    )\n",
         "    model.deploy(\n",
         "        endpoint=endpoint,\n",
@@ -343,11 +464,35 @@
         "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
         "        accelerator_count=1,\n",
         "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
         "    )\n",
-        "    return model, endpoint"
+        "    return model, endpoint\n",
+        "\n",
+        "\n",
+        "def get_bucket_and_blob_name(filepath):\n",
+        "    # The gcs path is of the form gs://<bucket-name>/<blob-name>\n",
+        "    gs_suffix = filepath.split(\"gs://\", 1)[1]\n",
+        "    return tuple(gs_suffix.split(\"/\", 1))\n",
+        "\n",
+        "\n",
+        "def upload_local_dir_to_gcs(local_dir_path, gcs_dir_path):\n",
+        "    \"\"\"Uploads files in a local directory to a GCS directory.\"\"\"\n",
+        "    client = storage.Client()\n",
+        "    bucket_name = gcs_dir_path.split(\"/\")[2]\n",
+        "    bucket = client.get_bucket(bucket_name)\n",
+        "    for local_file in glob.glob(local_dir_path + \"/**\"):\n",
+        "        if not os.path.isfile(local_file):\n",
+        "            continue\n",
+        "        filename = local_file[1 + len(local_dir_path) :]\n",
+        "        gcs_file_path = os.path.join(gcs_dir_path, filename)\n",
+        "        _, blob_name = get_bucket_and_blob_name(gcs_file_path)\n",
+        "        blob = bucket.blob(blob_name)\n",
+        "        blob.upload_from_filename(local_file)\n",
+        "        print(\"Copied {} to {}.\".format(local_file, gcs_file_path))"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "e70e3519ff8b"
@@ -357,6 +502,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "0dc65d8f0689"
@@ -381,11 +527,12 @@
         "!gdown --folder https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ\n",
         "\n",
         "# Upload data to Cloud Storage bucket.\n",
-        "!gsutil -m cp -r dog/* gs://{GCS_BUCKET}/dreambooth/dog/\n",
-        "!gsutil -m cp -r dog/* gs://{GCS_BUCKET}/dreambooth/dog_class/"
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog\")\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog_class\")"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "969cfeb79317"
@@ -455,6 +602,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "bf7f82732e61"
@@ -464,6 +612,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "1cc26e68d7b0"
@@ -475,6 +624,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "cd7b56421392"
@@ -484,6 +634,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6d331b1ea337"
@@ -504,13 +655,14 @@
       },
       "outputs": [],
       "source": [
-        "# Set the model_id to a GCS path, like \"gs://GCS_BUCKET/dreambooth/output\", to load the dreambooth finetuned model above.\n",
+        "# Set the model_id to \"runwayml/stable-diffusion-v1-5\" to load the OSS pre-trained model.\n",
         "model, endpoint = deploy_model(\n",
-        "    model_id=\"runwayml/stable-diffusion-v1-5\", task=\"text-to-image\"\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/dreambooth/output\", task=\"text-to-image\"\n",
         ")"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "80b3fd2ace09"
@@ -539,6 +691,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "af21a3cff1e0"
@@ -563,6 +716,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "c1e51f764a60"
@@ -572,6 +726,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "fa686a54047c"
@@ -595,6 +750,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "80b3fd2ace09"
@@ -627,6 +783,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "ed3795d474b9"

notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb

@@ -142,9 +142,7 @@
       "outputs": [],
       "source": [
         "# Install gdown for downloading example training images.\n",
-        "!pip install gdown\n",
-        "# Install gsutil for downloading/uploading data from/to Cloud Storage buckets.\n",
-        "!pip install gsutil"
+        "!pip install gdown"
       ]
     },
     {
@@ -184,7 +182,9 @@
         "\n",
         "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
         "\n",
-        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs."
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
       ]
     },
     {
@@ -210,8 +210,14 @@
         "# The region you want to launch jobs in.\n",
         "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
         "\n",
-        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
-        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+        "# The Cloud Storage bucket for storing experiments output.\n",
+        "# Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model.\n",
+        "# The service account looks like:\n",
+        "# '<account_name>@<project>.iam.gserviceaccount.com'\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -271,19 +277,20 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": null,
       "metadata": {
         "id": "8759e624ebc0"
       },
       "outputs": [],
       "source": [
         "import base64\n",
+        "import glob\n",
         "import os\n",
         "from datetime import datetime\n",
         "from io import BytesIO\n",
         "\n",
         "import requests\n",
-        "from google.cloud import aiplatform\n",
+        "from google.cloud import aiplatform, storage\n",
         "from PIL import Image\n",
         "\n",
         "\n",
@@ -326,8 +333,6 @@
         "        \"MODEL_ID\": model_id,\n",
         "        \"TASK\": task,\n",
         "    }\n",
-        "    # If the model_id is a GCS path, use artifact_uri to pass it to serving docker.\n",
-        "    artifact_uri = model_id if model_id.startswith(\"gs://\") else None\n",
         "    model = aiplatform.Model.upload(\n",
         "        display_name=model_name,\n",
         "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
@@ -335,7 +340,6 @@
         "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
         "        serving_container_health_route=\"/ping\",\n",
         "        serving_container_environment_variables=serving_env,\n",
-        "        artifact_uri=artifact_uri,\n",
         "    )\n",
         "    model.deploy(\n",
         "        endpoint=endpoint,\n",
@@ -343,8 +347,31 @@
         "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
         "        accelerator_count=1,\n",
         "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
         "    )\n",
-        "    return model, endpoint"
+        "    return model, endpoint\n",
+        "\n",
+        "\n",
+        "def get_bucket_and_blob_name(filepath):\n",
+        "    # The gcs path is of the form gs://<bucket-name>/<blob-name>\n",
+        "    gs_suffix = filepath.split(\"gs://\", 1)[1]\n",
+        "    return tuple(gs_suffix.split(\"/\", 1))\n",
+        "\n",
+        "\n",
+        "def upload_local_dir_to_gcs(local_dir_path, gcs_dir_path):\n",
+        "    \"\"\"Uploads files in a local directory to a GCS directory.\"\"\"\n",
+        "    client = storage.Client()\n",
+        "    bucket_name = gcs_dir_path.split(\"/\")[2]\n",
+        "    bucket = client.get_bucket(bucket_name)\n",
+        "    for local_file in glob.glob(local_dir_path + \"/**\"):\n",
+        "        if not os.path.isfile(local_file):\n",
+        "            continue\n",
+        "        filename = local_file[1 + len(local_dir_path) :]\n",
+        "        gcs_file_path = os.path.join(gcs_dir_path, filename)\n",
+        "        _, blob_name = get_bucket_and_blob_name(gcs_file_path)\n",
+        "        blob = bucket.blob(blob_name)\n",
+        "        blob.upload_from_filename(local_file)\n",
+        "        print(\"Copied {} to {}.\".format(local_file, gcs_file_path))"
       ]
     },
     {
@@ -381,17 +408,8 @@
         "!gdown --folder https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ\n",
         "\n",
         "# Upload data to Cloud Storage bucket.\n",
-        "!gsutil -m cp -r dog/* gs://{GCS_BUCKET}/dreambooth/dog/\n",
-        "!gsutil -m cp -r dog/* gs://{GCS_BUCKET}/dreambooth/dog_class/"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "969cfeb79317"
-      },
-      "source": [
-        "**NOTE**: If the upload step fails due to lacking of permission, you need to [grant the Storage Object Admin role](https://cloud.google.com/storage/docs/access-control/using-iam-permissions) for the Cloud account of the notebook."
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog\")\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog_class\")"
       ]
     },
     {
@@ -504,9 +522,9 @@
       },
       "outputs": [],
       "source": [
-        "# Set the model_id to a GCS path, like \"gs://GCS_BUCKET/dreambooth/output\", to load the dreambooth finetuned model above.\n",
+        "# Set the model_id to \"runwayml/stable-diffusion-inpainting\" to load the OSS pre-trained model.\n",
         "model, endpoint = deploy_model(\n",
-        "    model_id=\"runwayml/stable-diffusion-inpainting\", task=\"image-inpainting\"\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/dreambooth/output\", task=\"image-inpainting\"\n",
         ")"
       ]
     },

notebooks/community/model_garden/model_garden_pytorch_timm.ipynb

@@ -104,7 +104,9 @@
         "\n",
         "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
         "\n",
-        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component)."
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
       ]
     },
     {
@@ -193,13 +195,18 @@
         "# The region for running jobs.\n",
         "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
         "\n",
-        "# The model you want to train and serve.\n",
+        "# The model you want to train and serve. Please select a model from the verified model list above.\n",
         "# We use a ViT model as the example.\n",
         "MODEL_NAME = \"vit_tiny_patch16_224\"  # @param {type:\"string\"}\n",
         "\n",
         "# The Cloud Storage bucket name without gs:// prefix for training outputs.\n",
         "# For example: test_bucket\n",
-        "GCS_BUCKET = \"\"  # @param {type:\"string\"}"
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model. It looks like:\n",
+        "# '<account_name>@<project>.iam.gserviceaccount.com'\n",
+        "# Follow step 6 above to create this account.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -225,7 +232,7 @@
       },
       "outputs": [],
       "source": [
-        "# The training docker uri.\n",
+        "# The prebuilt training docker uri.\n",
         "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-timm-train\"\n",
         "\n",
         "# The path to data directory on Cloud Storage without gs:// prefix.\n",
@@ -265,8 +272,8 @@
         "# Single node with multiple GPUs.\n",
         "machine_type = \"n1-highmem-32\"\n",
         "num_nodes = 1\n",
-        "gpu_type = \"NVIDIA_TESLA_P100\"\n",
-        "num_gpus = 4\n",
+        "gpu_type = \"NVIDIA_TESLA_P100\"  # @param {type:\"string\"}\n",
+        "num_gpus = 4  # @param {type:\"integer\"}\n",
         "\n",
         "# Model specific config.\n",
         "job_name = f\"pytorch-{MODEL_NAME}\"\n",
@@ -336,8 +343,8 @@
         "# Worker pool spec.\n",
         "machine_type = \"n1-highmem-16\"\n",
         "num_nodes = 1\n",
-        "gpu_type = \"NVIDIA_TESLA_V100\"\n",
-        "num_gpus = 2\n",
+        "gpu_type = \"NVIDIA_TESLA_V100\"  # @param {type:\"string\"}\n",
+        "num_gpus = 2  # @param {type:\"integer\"}\n",
         "worker_pool_specs = [\n",
         "    {\n",
         "        \"machine_spec\": {\n",
@@ -408,19 +415,14 @@
       },
       "outputs": [],
       "source": [
-        "# The serve docker uri.\n",
+        "# The prebuilt serving docker uri.\n",
         "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-timm-serve\"\n",
         "# The port number used by torchserve traffic.\n",
         "SERVE_PORT = 7080\n",
         "# The path to model checkpoint file, including gs:// prefix.\n",
         "MODEL_PT_PATH = \"gs://path_to_model_best.pth.tar\"  # @param {type:\"string\"}\n",
         "# [Optional] the path to index_to_name.json, including gs:// prefix.\n",
-        "INDEX_TO_NAME_FILE = \"gs://path_to_index_to_name.json\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# Converts gs:// uris to /gcs/ to use GCS Fuse.\n",
-        "# See https://github.com/GoogleCloudPlatform/gcsfuse.\n",
-        "MODEL_PT_PATH = MODEL_PT_PATH.replace(\"gs://\", \"/gcs/\")\n",
-        "INDEX_TO_NAME_FILE = INDEX_TO_NAME_FILE.replace(\"gs://\", \"/gcs/\")"
+        "INDEX_TO_NAME_FILE = \"gs://path_to_index_to_name.json\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -469,6 +471,7 @@
         "    accelerator_type=\"NVIDIA_TESLA_T4\",\n",
         "    accelerator_count=1,\n",
         "    traffic_percentage=100,\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
         ")"
       ]
     },
@@ -506,10 +509,10 @@
         "# endpoint = aiplatform.Endpoint('projects/816369962409/locations/us-central1/endpoints/8809168414485512192')\n",
         "\n",
         "# Please upload an image and enter its filename below.\n",
-        "IMAGE_FILENAME = \"cat.jpg\"  # @param {type:\"string\"}\n",
+        "IMAGE_FILENAME = \"test.jpg\"  # @param {type:\"string\"}\n",
         "\n",
-        "# Alternatively, uncomment the follow line to download a cat image for demonstration.\n",
-        "# ! wget http://images.cocodataset.org/val2017/000000039769.jpg -O cat.jpg\n",
+        "# Alternatively, uncomment the following line to download a cat image for demonstration.\n",
+        "# ! wget http://images.cocodataset.org/val2017/000000039769.jpg -O test.jpg\n",
         "\n",
         "with open(IMAGE_FILENAME, \"rb\") as f:\n",
         "    image_b64 = base64.b64encode(f.read()).decode(\"utf-8\")\n",

notebooks/community/model_garden/model_garden_tfvision_image_classification.ipynb

@@ -118,7 +118,7 @@
       },
       "source": [
         "### Colab Only\n",
-        "Run the following commands for colab and skip this section if you use workbench."
+        "Run the following commands for Colab and skip this section if you use Workbench."
       ]
     },
     {
@@ -181,7 +181,16 @@
         "# The project and bucket are for experiments below.\n",
         "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
         "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
-        "REGION = \"us-central1\"\n",
+        "\n",
+        "# You can choose a region from https://cloud.google.com/about/locations.\n",
+        "# Only regions prefixed by \"us\", \"asia\", or \"europe\" are supported.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "REGION_PREFIX = REGION.split(\"-\")[0]\n",
+        "assert REGION_PREFIX in (\n",
+        "    \"us\",\n",
+        "    \"europe\",\n",
+        "    \"asia\",\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"asia\", or \"europe\".'\n",
         "\n",
         "! gcloud config set project $PROJECT_ID\n",
         "\n",
@@ -231,13 +240,13 @@
         "\n",
         "# Data converter constants.\n",
         "DATA_CONVERTER_JOB_PREFIX = \"data_converter\"\n",
-        "DATA_CONVERTER_CONTAINER = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter:latest\"\n",
+        "DATA_CONVERTER_CONTAINER = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter\"\n",
         "DATA_CONVERTER_MACHINE_TYPE = \"n1-highmem-8\"\n",
         "\n",
         "\n",
         "# Training constants.\n",
         "TRAINING_JOB_PREFIX = \"train\"\n",
-        "TRAIN_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss:latest\"\n",
+        "TRAIN_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss\"\n",
         "TRAIN_MACHINE_TYPE = \"n1-highmem-16\"\n",
         "TRAIN_ACCELERATOR_TYPE = \"NVIDIA_TESLA_P100\"\n",
         "TRAIN_NUM_GPU = 1\n",
@@ -247,7 +256,7 @@
         "\n",
         "# Export constants.\n",
         "EXPORT_JOB_PREFIX = \"export\"\n",
-        "EXPORT_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving:latest\"\n",
+        "EXPORT_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving\"\n",
         "EXPORT_MACHINE_TYPE = \"n1-highmem-8\"\n",
         "\n",
         "# Prediction constants.\n",
@@ -256,9 +265,7 @@
         "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
         "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
         "# You can adjust accelerator types and machine types to get faster predictions.\n",
-        "PREDICTION_CONTAINER_URI = (\n",
-        "    \"us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
-        ")\n",
+        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
         "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
         "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
         "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
@@ -307,10 +314,9 @@
         "    endpoint_id: str,\n",
         "    instances: Union[Dict, List[Dict]],\n",
         "    location: str = \"us-central1\",\n",
-        "    api_endpoint: str = \"us-central1-aiplatform.googleapis.com\",\n",
         "):\n",
         "    # The AI Platform services require regional API endpoints.\n",
-        "    client_options = {\"api_endpoint\": api_endpoint}\n",
+        "    client_options = {\"api_endpoint\": f\"{location}-aiplatform.googleapis.com\"}\n",
         "    # Initialize client that will be used to create and send requests.\n",
         "    # This client only needs to be created once, and can be reused for multiple requests.\n",
         "    client = aiplatform.gapic.PredictionServiceClient(client_options=client_options)\n",
@@ -536,7 +542,7 @@
         "# input_train_data_path = ''\n",
         "# input_validation_data_path = ''\n",
         "\n",
-        "experiment = \"ViT-s16\"  # @param [\"ResNet-50\",\"ResNet-RS-50\",\"Efficientnetv2-m\",\"ViT-ti16\",\"ViT-s16\",\"ViT-b16\",\"ViT-l16\"]\n",
+        "experiment = \"ResNet-50\"  # @param [\"ResNet-50\",\"ResNet-RS-50\",\"Efficientnetv2-m\",\"ViT-ti16\",\"ViT-s16\",\"ViT-b16\",\"ViT-l16\"]\n",
         "\n",
         "train_job_name = get_job_name_with_datetime(TRAINING_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
         "model_dir = os.path.join(BUCKET_URI, train_job_name)\n",
@@ -562,6 +568,7 @@
         "        **{\n",
         "            \"experiment\": \"resnet_imagenet\",\n",
         "            \"config_file\": os.path.join(CONFIG_DIR, \"imagenet_resnet50_gpu.yaml\"),\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/resnet/resnet-50-i224.tar.gz\",\n",
         "        },\n",
         "    ),\n",
         "    \"ResNet-RS-50\": dict(\n",

notebooks/community/model_garden/model_garden_tfvision_image_object_detection.ipynb

@@ -118,7 +118,7 @@
       },
       "source": [
         "### Colab Only\n",
-        "Run the following commands for colab and skip this section if you use workbench."
+        "Run the following commands for Colab and skip this section if you are using Workbench."
       ]
     },
     {
@@ -181,27 +181,37 @@
         "# The project and bucket are for experiments below.\n",
         "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
         "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
-        "REGION = \"us-central1\"\n",
+        "\n",
+        "# You can choose a region from https://cloud.google.com/about/locations.\n",
+        "# Only regions prefixed by \"us\", \"asia\", or \"europe\" are supported.\n",
+        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
+        "REGION_PREFIX = REGION.split(\"-\")[0]\n",
+        "assert REGION_PREFIX in (\n",
+        "    \"us\",\n",
+        "    \"europe\",\n",
+        "    \"asia\",\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"asia\", or \"europe\".'\n",
         "\n",
         "! gcloud config set project $PROJECT_ID\n",
         "\n",
         "STAGING_BUCKET = os.path.join(BUCKET_URI, \"temporal\")\n",
+        "CHECKPOINT_BUCKET = os.path.join(BUCKET_URI, \"ckpt\")\n",
         "\n",
         "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=STAGING_BUCKET)\n",
         "\n",
         "# Download config files.\n",
         "CONFIG_DIR = os.path.join(BUCKET_URI, \"config\")\n",
         "! wget https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/retinanet/coco_spinenet49_gpu_multiworker_mirrored.yaml\n",
-        "! gsutil cp coco_spinenet49_gpu_multiworker_mirrored.yaml $CONFIG_DIR\n",
+        "! gsutil cp coco_spinenet49_gpu_multiworker_mirrored.yaml $CONFIG_DIR/\n",
         "\n",
         "! wget https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/retinanet/coco_spinenet96_gpu_multiworker_mirrored.yaml\n",
-        "! gsutil cp coco_spinenet96_gpu_multiworker_mirrored.yaml $CONFIG_DIR\n",
+        "! gsutil cp coco_spinenet96_gpu_multiworker_mirrored.yaml $CONFIG_DIR/\n",
         "\n",
         "! wget https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/retinanet/coco_spinenet143_gpu_multiworker_mirrored.yaml\n",
-        "! gsutil cp coco_spinenet143_gpu_multiworker_mirrored.yaml $CONFIG_DIR\n",
+        "! gsutil cp coco_spinenet143_gpu_multiworker_mirrored.yaml $CONFIG_DIR/\n",
         "\n",
         "! wget https://raw.githubusercontent.com/tensorflow/models/master/official/projects/yolo/configs/experiments/yolov4/detection/scaled_yolov4_1280_gpu.yaml\n",
-        "! gsutil cp scaled_yolov4_1280_gpu.yaml $CONFIG_DIR"
+        "! gsutil cp scaled_yolov4_1280_gpu.yaml $CONFIG_DIR/"
       ]
     },
     {
@@ -225,13 +235,13 @@
         "\n",
         "# Data converter constants.\n",
         "DATA_CONVERTER_JOB_PREFIX = \"data_converter\"\n",
-        "DATA_CONVERTER_CONTAINER = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter:latest\"\n",
+        "DATA_CONVERTER_CONTAINER = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter\"\n",
         "DATA_CONVERTER_MACHINE_TYPE = \"n1-highmem-8\"\n",
         "\n",
         "\n",
         "# Training constants.\n",
         "TRAINING_JOB_PREFIX = \"train\"\n",
-        "TRAIN_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss:latest\"\n",
+        "TRAIN_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss\"\n",
         "TRAIN_MACHINE_TYPE = \"n1-highmem-16\"\n",
         "TRAIN_ACCELERATOR_TYPE = \"NVIDIA_TESLA_V100\"\n",
         "TRAIN_NUM_GPU = 2\n",
@@ -251,7 +261,7 @@
         "\n",
         "# Export constants.\n",
         "EXPORT_JOB_PREFIX = \"export\"\n",
-        "EXPORT_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving:latest\"\n",
+        "EXPORT_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving\"\n",
         "EXPORT_MACHINE_TYPE = \"n1-highmem-8\"\n",
         "\n",
         "# Prediction constants.\n",
@@ -260,9 +270,7 @@
         "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
         "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
         "# You can adjust accelerator types and machine types to get faster predictions.\n",
-        "PREDICTION_CONTAINER_URI = (\n",
-        "    \"us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
-        ")\n",
+        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
         "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
         "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
         "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
@@ -313,10 +321,9 @@
         "    endpoint_id: str,\n",
         "    instances: Union[Dict, List[Dict]],\n",
         "    location: str = \"us-central1\",\n",
-        "    api_endpoint: str = \"us-central1-aiplatform.googleapis.com\",\n",
         "):\n",
         "    # The AI Platform services require regional API endpoints.\n",
-        "    client_options = {\"api_endpoint\": api_endpoint}\n",
+        "    client_options = {\"api_endpoint\": f\"{location}-aiplatform.googleapis.com\"}\n",
         "    # Initialize client that will be used to create and send requests.\n",
         "    # This client only needs to be created once, and can be reused for multiple requests.\n",
         "    client = aiplatform.gapic.PredictionServiceClient(client_options=client_options)\n",
@@ -469,7 +476,30 @@
         "                font,\n",
         "                display_str_list=[display_str],\n",
         "            )\n",
-        "    return image"
+        "    return image\n",
+        "\n",
+        "\n",
+        "def upload_checkpoint_to_gcs(checkpoint_url):\n",
+        "    filename = os.path.basename(checkpoint_url)\n",
+        "    checkpoint_name = filename.replace(\".tar.gz\", \"\")\n",
+        "    print(\"Download checkpoint from\", checkpoint_url, \"and store to\", CHECKPOINT_BUCKET)\n",
+        "    ! wget $checkpoint_url -O $filename\n",
+        "    ! mkdir -p $checkpoint_name\n",
+        "    ! tar -xvzf $filename -C $checkpoint_name\n",
+        "\n",
+        "    # Search for relative path to the checkpoint.\n",
+        "    checkpoint_path = None\n",
+        "    for root, dirs, files in os.walk(checkpoint_name):\n",
+        "        for file in files:\n",
+        "            if file.endswith(\".index\"):\n",
+        "                checkpoint_path = os.path.join(root, os.path.splitext(file)[0])\n",
+        "                checkpoint_path = os.path.relpath(checkpoint_path, checkpoint_name)\n",
+        "                break\n",
+        "\n",
+        "    ! gsutil cp -r $checkpoint_name $CHECKPOINT_BUCKET/\n",
+        "    checkpoint_uri = os.path.join(CHECKPOINT_BUCKET, checkpoint_name, checkpoint_path)\n",
+        "    print(\"Checkpoint uploaded to\", checkpoint_uri)\n",
+        "    return checkpoint_uri"
       ]
     },
     {
@@ -621,8 +651,8 @@
         "    \"objective\": OBJECTIVE,\n",
         "    \"model_dir\": model_dir,\n",
         "    \"num_classes\": num_classes,\n",
-        "    \"global_batch_size\": 4,\n",
-        "    \"prefetch_buffer_size\": 12,\n",
+        "    \"global_batch_size\": 2,\n",
+        "    \"prefetch_buffer_size\": 6,\n",
         "    \"train_steps\": 2000,\n",
         "    \"input_size\": \"1024,1024\",\n",
         "}\n",
@@ -661,9 +691,19 @@
         "        **{\n",
         "            \"experiment\": \"scaled_yolo\",\n",
         "            \"config_file\": TRAIN_YOLOV4_CONFIG,\n",
+        "            \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/yolo/scaled-yolov4/scaled-yolov4-l-p6-i1280.tar.gz\",\n",
+        "            \"input_size\": \"1280,1280\",\n",
         "        },\n",
         "    ),\n",
         "}\n",
+        "experiment_container_args = experiment_container_args_dict[experiment]\n",
+        "\n",
+        "# Copy checkpoint to GCS bucket if specified.\n",
+        "init_checkpoint = experiment_container_args.get(\"init_checkpoint\")\n",
+        "if init_checkpoint:\n",
+        "    experiment_container_args[\"init_checkpoint\"] = upload_checkpoint_to_gcs(\n",
+        "        init_checkpoint\n",
+        "    )\n",
         "\n",
         "params_override = \"runtime.num_gpus=%s\" % TRAIN_NUM_GPU\n",
         "eval_params_override = \"runtime.num_gpus=1,runtime.distribution_strategy=mirrored\"\n",
@@ -681,10 +721,7 @@
         "                \"--mode=train\",\n",
         "                \"--params_override=%s\" % params_override,\n",
         "            ]\n",
-        "            + [\n",
-        "                \"--{}={}\".format(k, v)\n",
-        "                for k, v in experiment_container_args_dict[experiment].items()\n",
-        "            ],\n",
+        "            + [\"--{}={}\".format(k, v) for k, v in experiment_container_args.items()],\n",
         "        },\n",
         "    },\n",
         "    {},\n",
@@ -702,10 +739,7 @@
         "                \"--mode=continuous_eval\",\n",
         "                \"--params_override=%s\" % eval_params_override,\n",
         "            ]\n",
-        "            + [\n",
-        "                \"--{}={}\".format(k, v)\n",
-        "                for k, v in experiment_container_args_dict[experiment].items()\n",
-        "            ],\n",
+        "            + [\"--{}={}\".format(k, v) for k, v in experiment_container_args.items()],\n",
         "        },\n",
         "    },\n",
         "]\n",
@@ -807,8 +841,7 @@
         "            \"args\": [\n",
         "                \"--objective=%s\" % OBJECTIVE,\n",
         "                \"--input_image_size=1024,1024\",\n",
-        "                \"--experiment=%s\"\n",
-        "                % experiment_container_args_dict[experiment][\"experiment\"],\n",
+        "                \"--experiment=%s\" % experiment_container_args[\"experiment\"],\n",
         "                \"--config_file=%s/params.yaml\" % best_trial_dir,\n",
         "                \"--checkpoint_path=%s/best_ckpt\" % best_trial_dir,\n",
         "                \"--export_dir=%s/best_model\" % model_dir,\n",

notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb

@@ -119,7 +119,7 @@
       "source": [
         "### Colab Only\n",
         "\n",
-        "Run the following commands for colab and skip this section if you use workbench."
+        "Run the following commands for Colab and skip this section if you use Workbench."
       ]
     },
     {
@@ -182,18 +182,28 @@
         "# The project and bucket are for experiments below.\n",
         "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
         "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
-        "REGION = \"us-central1\"\n",
+        "\n",
+        "# You can choose a region from https://cloud.google.com/about/locations.\n",
+        "# Only regions prefixed by \"us\", \"asia\", or \"europe\" are supported.\n",
+        "REGION = \"europe-west4\"  # @param {type:\"string\"}\n",
+        "REGION_PREFIX = REGION.split(\"-\")[0]\n",
+        "assert REGION_PREFIX in (\n",
+        "    \"us\",\n",
+        "    \"europe\",\n",
+        "    \"asia\",\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"asia\", or \"europe\".'\n",
         "\n",
         "! gcloud config set project $PROJECT_ID\n",
         "\n",
         "STAGING_BUCKET = os.path.join(BUCKET_URI, \"temporal\")\n",
+        "CHECKPOINT_BUCKET = os.path.join(BUCKET_URI, \"ckpt\")\n",
         "\n",
         "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=STAGING_BUCKET)\n",
         "\n",
         "# Download config files.\n",
         "CONFIG_DIR = os.path.join(BUCKET_URI, \"config\")\n",
         "! wget https://raw.githubusercontent.com/tensorflow/models/master/official/vision/configs/experiments/semantic_segmentation/deeplabv3plus_resnet101_cityscapes_gpu_multiworker_mirrored.yaml\n",
-        "! gsutil cp deeplabv3plus_resnet101_cityscapes_gpu_multiworker_mirrored.yaml $CONFIG_DIR"
+        "! gsutil cp deeplabv3plus_resnet101_cityscapes_gpu_multiworker_mirrored.yaml $CONFIG_DIR/"
       ]
     },
     {
@@ -217,13 +227,13 @@
         "\n",
         "# Data converter constants.\n",
         "DATA_CONVERTER_JOB_PREFIX = \"data_converter\"\n",
-        "DATA_CONVERTER_CONTAINER = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter:latest\"\n",
+        "DATA_CONVERTER_CONTAINER = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/data-converter\"\n",
         "DATA_CONVERTER_MACHINE_TYPE = \"n1-highmem-8\"\n",
         "\n",
         "\n",
         "# Training constants.\n",
         "TRAINING_JOB_PREFIX = \"train\"\n",
-        "TRAIN_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss:latest\"\n",
+        "TRAIN_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-oss\"\n",
         "TRAIN_MACHINE_TYPE = \"n1-highmem-16\"\n",
         "TRAIN_ACCELERATOR_TYPE = \"NVIDIA_TESLA_V100\"\n",
         "TRAIN_NUM_GPU = 2\n",
@@ -236,7 +246,7 @@
         "\n",
         "# Export constants.\n",
         "EXPORT_JOB_PREFIX = \"export\"\n",
-        "EXPORT_CONTAINER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving:latest\"\n",
+        "EXPORT_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/tfvision-serving\"\n",
         "EXPORT_MACHINE_TYPE = \"n1-highmem-8\"\n",
         "\n",
         "# Prediction constants.\n",
@@ -245,9 +255,7 @@
         "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
         "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
         "# You can adjust accelerator types and machine types to get faster predictions.\n",
-        "PREDICTION_CONTAINER_URI = (\n",
-        "    \"us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
-        ")\n",
+        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
         "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
         "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
         "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
@@ -298,10 +306,9 @@
         "    endpoint_id: str,\n",
         "    instances: Union[Dict, List[Dict]],\n",
         "    location: str = \"us-central1\",\n",
-        "    api_endpoint: str = \"us-central1-aiplatform.googleapis.com\",\n",
         "):\n",
         "    # The AI Platform services require regional API endpoints.\n",
-        "    client_options = {\"api_endpoint\": api_endpoint}\n",
+        "    client_options = {\"api_endpoint\": f\"{location}-aiplatform.googleapis.com\"}\n",
         "    # Initialize client that will be used to create and send requests.\n",
         "    # This client only needs to be created once, and can be reused for multiple requests.\n",
         "    client = aiplatform.gapic.PredictionServiceClient(client_options=client_options)\n",
@@ -508,7 +515,30 @@
         "        ]\n",
         "    category_image_color = Image.fromarray(category_image_color_np)\n",
         "\n",
-        "    return score_image_grayscale, category_image_color"
+        "    return score_image_grayscale, category_image_color\n",
+        "\n",
+        "\n",
+        "def upload_checkpoint_to_gcs(checkpoint_url):\n",
+        "    filename = os.path.basename(checkpoint_url)\n",
+        "    checkpoint_name = filename.replace(\".tar.gz\", \"\")\n",
+        "    print(\"Download checkpoint from\", checkpoint_url, \"and store to\", CHECKPOINT_BUCKET)\n",
+        "    ! wget $checkpoint_url -O $filename\n",
+        "    ! mkdir -p $checkpoint_name\n",
+        "    ! tar -xvzf $filename -C $checkpoint_name\n",
+        "\n",
+        "    # Search for relative path to the checkpoint.\n",
+        "    checkpoint_path = None\n",
+        "    for root, dirs, files in os.walk(checkpoint_name):\n",
+        "        for file in files:\n",
+        "            if file.endswith(\".index\"):\n",
+        "                checkpoint_path = os.path.join(root, os.path.splitext(file)[0])\n",
+        "                checkpoint_path = os.path.relpath(checkpoint_path, checkpoint_name)\n",
+        "                break\n",
+        "\n",
+        "    ! gsutil cp -r $checkpoint_name $CHECKPOINT_BUCKET/\n",
+        "    checkpoint_uri = os.path.join(CHECKPOINT_BUCKET, checkpoint_name, checkpoint_path)\n",
+        "    print(\"Checkpoint uploaded to\", checkpoint_uri)\n",
+        "    return checkpoint_uri"
       ]
     },
     {
@@ -665,8 +695,17 @@
         "        \"prefetch_buffer_size\": 12,\n",
         "        \"train_steps\": 500,\n",
         "        \"output_size\": \"1024,2048\",\n",
+        "        \"init_checkpoint\": \"https://storage.googleapis.com/tf_model_garden/vision/deeplabv3plus/dilated-resnet-101-deeplabv3plus.tar.gz\",\n",
         "    }\n",
         "}\n",
+        "experiment_container_args = experiment_container_args_dict[experiment]\n",
+        "\n",
+        "# Copy checkpoint to GCS bucket if specified.\n",
+        "init_checkpoint = experiment_container_args.get(\"init_checkpoint\")\n",
+        "if init_checkpoint:\n",
+        "    experiment_container_args[\"init_checkpoint\"] = upload_checkpoint_to_gcs(\n",
+        "        init_checkpoint\n",
+        "    )\n",
         "\n",
         "worker_pool_specs = [\n",
         "    {\n",
@@ -681,10 +720,7 @@
         "            \"args\": [\n",
         "                \"--mode=train_and_eval\",\n",
         "            ]\n",
-        "            + [\n",
-        "                \"--{}={}\".format(k, v)\n",
-        "                for k, v in experiment_container_args_dict[experiment].items()\n",
-        "            ],\n",
+        "            + [\"--{}={}\".format(k, v) for k, v in experiment_container_args.items()],\n",
         "        },\n",
         "    },\n",
         "]\n",
@@ -787,13 +823,11 @@
         "            \"command\": [],\n",
         "            \"args\": [\n",
         "                \"--objective=%s\" % OBJECTIVE,\n",
-        "                \"--experiment=%s\"\n",
-        "                % experiment_container_args_dict[experiment][\"experiment\"],\n",
+        "                \"--experiment=%s\" % experiment_container_args[\"experiment\"],\n",
         "                \"--config_file=%s/params.yaml\" % best_trial_dir,\n",
         "                \"--checkpoint_path=%s/best_ckpt\" % best_trial_dir,\n",
         "                \"--export_dir=%s/best_model\" % model_dir,\n",
-        "                \"--input_image_size=%s\"\n",
-        "                % experiment_container_args_dict[experiment][\"output_size\"],\n",
+        "                \"--input_image_size=%s\" % experiment_container_args[\"output_size\"],\n",
         "            ],\n",
         "        },\n",
         "    }\n",

notebooks/community/vertex_endpoints/optimized_tensorflow_runtime/tabular_optimized_online_prediction.ipynb

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

notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb

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

notebooks/official/experiments/delete_outdated_tensorboard_experiments.ipynb

@@ -0,0 +1,669 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ur8xi4C7S06n"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2022 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "JAPoU8Sm5E6e"
+      },
+      "source": [
+        "# Delete Outdated Experiments in Vertex AI TensorBoard\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/delete_outdated_tensorboard_experiments.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/delete_outdated_tensorboard_experiments.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/vertex-ai-samples/main/notebooks/official/experiments/delete_outdated_tensorboard_experiments.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "24743cf4a1e1"
+      },
+      "source": [
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.9"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "Vertex AI will have a new Vertex AI TensorBoard billing model. From August 2023, it will change from monthly `$300/user` to monthly `$10/GB`. In preparation for this change, users need to delete old Vertex AI TensorBoard Experiments to avoid unnecessary storage costs when the pricing change takes place.\n",
+        "\n",
+        "Learn more about [Vertex AI TensorBoard](https://cloud.google.com/vertex-ai/docs/experiments/tensorboard-overview)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d975e698c9a4"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to delete outdated TensorBoard Experiments to avoid unnecessary storage costs.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services and resources:\n",
+        "\n",
+        "- Vertex AI Tensorboard\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- How to delete the TB Experiment with a predefined key-value label pair `<label_key, label_value>`\n",
+        "\n",
+        "- How to delete the TB Experiments created before the  `create_time`\n",
+        "\n",
+        "- How to delete the TB Experiments created before the  `update_time`"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "08d289fa873f"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "No dataset is used."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "aed92deeb4a0"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), and [Cloud Storage pricing](https://cloud.google.com/storage/pricing),\n",
+        "and use the [Pricing Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "i7EUnXsZhAGF"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the following packages required to execute this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2b4ef9b72d43"
+      },
+      "outputs": [],
+      "source": [
+        "# Install the packages\n",
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    USER = \"--user\"\n",
+        "else:\n",
+        "    USER = \"\"\n",
+        "! pip3 install {USER} --upgrade google-cloud-aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "58707a750154"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f200f10a1da3"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
+        "\n",
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "3. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WReHDGG5g0XY"
+      },
+      "source": [
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "oM1iC_MfAts1"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "QAup21nz6LHk"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "sBCra4QMA2wR"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "74ccc9e52986"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "de775a3773ba"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "254614fa0c46"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ef21552ccea8"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "603adbbf0532"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f6b2ccc891ed"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant permissions to your service account at https://cloud.google.com/marketplace/docs/grant-service-account-access."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "960505627ddf"
+      },
+      "source": [
+        "### Import libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PyQmSRbKA8r-"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "NUJOpq7_-nt6"
+      },
+      "source": [
+        "### Define constants\n",
+        "\n",
+        "Define variables you use in this tutorial. In particular, you set\n",
+        "\n",
+        "- `CREATE_TIME_CUT` : delete tensorboard experiments that were created before CREATE_TIME_CUT. For example, `2022-12-31`.\n",
+        "\n",
+        "- `UPDATE_TIME_CUT` : delete tensorboard experiments that were created before UPDATE_TIME_CUT. For example, `2022-12-31`.\n",
+        "\n",
+        "- `DETAILED_LOG` : a booled variable to see Tensorboard deletion progress. If True, it shows progress by experiments. Otherwise, it reports progress per 100 experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0AkyoMre-qe5"
+      },
+      "outputs": [],
+      "source": [
+        "CREATE_TIME_CUT = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "UPDATE_TIME_CUT = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "DETAILED_LOG = True  # @param {type: \"boolean\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "n68J5KJ4ERbF"
+      },
+      "source": [
+        "### Define Helpers"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "JIXC-tVrETET"
+      },
+      "outputs": [],
+      "source": [
+        "def clean_up_by_label(tensorboard_instance, label_key, label_value):\n",
+        "    \"\"\"Delete the TB Experiment with the key-value label pair <label_key, label_value>\"\"\"\n",
+        "    # List tensorboard experiments\n",
+        "    tensorboard_experiments = aiplatform.TensorboardExperiment.list(\n",
+        "        tensorboard_name=tensorboard_instance.resource_name\n",
+        "    )\n",
+        "    # Get the number of tensorboard experiments\n",
+        "    num_tensorboard_experiments = len(tensorboard_experiments)\n",
+        "    # For each experiment\n",
+        "    for i in range(num_tensorboard_experiments):\n",
+        "        tensorboard_experiment = tensorboard_experiments[i]\n",
+        "        if detailed_log or (i % 100 == 0):\n",
+        "            print(\n",
+        "                f\">>>checking TB experiment [{i + 1}/{num_tensorboard_experiments}]: {tensorboard_experiment.resource_name}\"\n",
+        "            )\n",
+        "        # Get experiment labels\n",
+        "        labels = tensorboard_experiment.labels\n",
+        "        # Filter by label\n",
+        "        if label_key in labels and labels[label_key] == label_value:\n",
+        "            # Delete experiment\n",
+        "            tensorboard_experiment.delete()\n",
+        "\n",
+        "\n",
+        "def clean_up_by_create_time(tensorboard_instance, create_time_cut):\n",
+        "    \"\"\"Delete the TB Experiment with the `create_time`\"\"\"\n",
+        "    # List tensorboard experiments\n",
+        "    tensorboard_experiments = aiplatform.TensorboardExperiment.list(\n",
+        "        tensorboard_name=tensorboard_instance.resource_name, order_by=\"create_time\"\n",
+        "    )\n",
+        "    # Get the number of tensorboard experiments\n",
+        "    num_tensorboard_experiments = len(tensorboard_experiments)\n",
+        "    # For each experiment\n",
+        "    for i in range(num_tensorboard_experiments):\n",
+        "        tensorboard_experiment = tensorboard_experiments[i]\n",
+        "        if detailed_log or (i % 100 == 0):\n",
+        "            print(\n",
+        "                f\">>> checking TB experiment [{i + 1}/{num_tensorboard_experiments}]: {tensorboard_experiment.resource_name}\"\n",
+        "            )\n",
+        "        # Filter by create_time\n",
+        "        if str(tensorboard_experiment.create_time) < create_time_cut:\n",
+        "            # Delete experiment\n",
+        "            tensorboard_experiment.delete()\n",
+        "        else:\n",
+        "            break\n",
+        "\n",
+        "\n",
+        "def clean_up_by_update_time(tensorboard_instance, update_time_cut):\n",
+        "    \"\"\"Delete the TB Experiment with with the `update_time`\"\"\"\n",
+        "    # List tensorboard experiments\n",
+        "    tensorboard_experiments = aiplatform.TensorboardExperiment.list(\n",
+        "        tensorboard_name=tensorboard_instance.resource_name, order_by=\"update_time\"\n",
+        "    )\n",
+        "    # Get the number of tensorboard experiments\n",
+        "    num_tensorboard_experiments = len(tensorboard_experiments)\n",
+        "    # For each experiment\n",
+        "    for i in range(num_tensorboard_experiments):\n",
+        "        tensorboard_experiment = tensorboard_experiments[i]\n",
+        "        if detailed_log or (i % 100 == 0):\n",
+        "            print(\n",
+        "                f\">>> checking TB experiment [{i + 1}/{num_tensorboard_experiments}]: {tensorboard_experiment.resource_name}\"\n",
+        "            )\n",
+        "        # Filter by update_time\n",
+        "        if str(tensorboard_experiment.update_time) < update_time_cut:\n",
+        "            tensorboard_experiment.delete()\n",
+        "        else:\n",
+        "            break"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UCUOlTLYCT0B"
+      },
+      "source": [
+        "## Delete outdated Vertex AI TensorBoard Experiments"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EGfFVHhWDjkl"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G1l-7Wft3jb6"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e4672ef33691"
+      },
+      "source": [
+        "### Set delete outdated TensorBoard experiments \n",
+        "\n",
+        "Initialize a flag variable to start deleting outdated TensorBoard experiments and a flag variable to choose the deleting method. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8cdc326c9823"
+      },
+      "outputs": [],
+      "source": [
+        "delete_tb_experiments = False  # @param {type: \"boolean\"}\n",
+        "\n",
+        "delete_method = \"\"  # @param [\"by_label\", \"by_create_time\", \"by_update_time\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "JjJVARe5V-MG"
+      },
+      "source": [
+        "### Delete an TensorBoard instance\n",
+        "\n",
+        "To delete a Tensorboard instance, you need `TENSORBOARD_INSTANCE` ID which uniquely identifies the Tensorboard instance where you run experiments.\n",
+        "\n",
+        "To get the Tensorboard instance ID, you can either\n",
+        "\n",
+        "- go to the cloud console UI, Vertex AI > Experiments > Tensorboard Instances, or\n",
+        "- use the list command below to list all TensorBoard instances for your project and region.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "eqM2pIO8_4Y7"
+      },
+      "outputs": [],
+      "source": [
+        "tensorboard_instances = aiplatform.Tensorboard.list(project=PROJECT_ID, location=REGION)\n",
+        "print(tensorboard_instances)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "wT_uPArACMPX"
+      },
+      "source": [
+        "Set the tensorboard instance id for which you want to delete experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "hUync8E9CLcm"
+      },
+      "outputs": [],
+      "source": [
+        "if delete_tb_experiments:\n",
+        "\n",
+        "    TENSORBOARD_INSTANCE_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "    TENSORBOARD_INSTANCE = aiplatform.Tensorboard(\n",
+        "        project=PROJECT_ID, location=REGION, tensorboard_name=TENSORBOARD_INSTANCE_ID\n",
+        "    )\n",
+        "    print(TENSORBOARD_INSTANCE)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OOp22fxdHqmT"
+      },
+      "source": [
+        "### Delete a TensorBoard Experiment with the key-value label pair\n",
+        "\n",
+        "You delete a TensorBoard experiment using a predefined `label_key` and `label_value`. For example, you may have assigned `delete` label key and `true` label value to indicate all Tensorboard experiments you want to delete.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "N7KajCsjij1g"
+      },
+      "outputs": [],
+      "source": [
+        "LABEL_KEY = \"delete\"  # @param {type:\"string\"}\n",
+        "LABEL_VALUE = \"true\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "N45samDzWBO2"
+      },
+      "outputs": [],
+      "source": [
+        "if delete_tb_experiments and delete_method == \"by_label\":\n",
+        "    clean_up_by_label(TENSORBOARD_INSTANCE, LABEL_KEY, LABEL_VALUE)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XrEVqlgSIL6K"
+      },
+      "source": [
+        "### Delete a TensorBoard Experiment with `create_time`\n",
+        "\n",
+        "You delete a TensorBoard experiment using `create_time` field"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4_bjNeQ7p87A"
+      },
+      "outputs": [],
+      "source": [
+        "if delete_tb_experiments and delete_method == \"by_create_time\":\n",
+        "    clean_up_by_create_time(TENSORBOARD_INSTANCE, CREATE_TIME_CUT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZGNlSbIrIP_o"
+      },
+      "source": [
+        "### Delete a TensorBoard Experiment with `update_time`\n",
+        "\n",
+        "You delete a TensorBoard Experiment using a predefined `update_time` field"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "SDyc_a8XwEve"
+      },
+      "outputs": [],
+      "source": [
+        "if delete_tb_experiments and delete_method == \"by_update_time\":\n",
+        "    clean_up_by_update_time(TENSORBOARD_INSTANCE, UPDATE_TIME_CUT)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "delete_outdated_tensorboard_experiments.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/experiments/get_started_with_vertex_experiments_autologging.ipynb

@@ -34,18 +34,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/autologging.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/get_started_with_vertex_experiments_autologging.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/autologging.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/experiments/get_started_with_vertex_experiments_autologging.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/experiments/autologging.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/experiments/get_started_with_vertex_experiments_autologging.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",