debug: internal error

* Cleanup proprietary IOD notebook

* lint

* fix: aip to aiplatform

.cloud-build/execute_changed_notebooks_cli.py

@@ -121,6 +121,13 @@ parser.add_argument(
     default=True,
     help="Should run notebooks in parallel.",
 )
+parser.add_argument(
+    "--concurrent_notebooks",
+    type=int,
+    help="Maximum number of parallel notebook executions per minute",
+    default=10,
+    required=False,
+)
 parser.add_argument(
     "--dry_run",
     type=str2bool,
@@ -168,5 +175,6 @@ else:
         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,
+        concurrent_notebooks=args.concurrent_notebooks,
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -36,7 +36,6 @@ import execute_notebook_helper
 import execute_notebook_remote
 import nbformat
 from google.cloud.devtools.cloudbuild_v1.types import BuildOperationMetadata
-from ratemate import RateLimit
 from tabulate import tabulate
 from utils import NotebookProcessors, util
 
@@ -234,7 +233,6 @@ def _create_tag(filepath: str) -> str:
     return tag
 
 
-rate_limit = RateLimit(max_count=10, per=60, greedy=False)
 
 
 def process_and_execute_notebook(
@@ -250,7 +248,6 @@ def process_and_execute_notebook(
     notebook: str,
     should_get_tail_logs: bool = False,
 ) -> NotebookExecutionResult:
-    rate_limit.wait()  # wait before creating the task
 
     print(f"Running notebook: {notebook}")
 
@@ -461,6 +458,7 @@ def process_and_execute_notebooks(
     variable_service_account: str,
     variable_vpc_network: Optional[str] = None,
     private_pool_id: Optional[str] = None,
+    concurrent_notebooks: Optional[int] = 10,
 ):
     """
     Run the notebooks that exist under the folders defined in the test_paths_file.
@@ -491,6 +489,7 @@ def process_and_execute_notebooks(
             Required. Should run notebooks in parallel using a thread pool as opposed to in sequence.
         timeout (str):
             Required. Timeout string according to https://cloud.google.com/build/docs/build-config-file-schema#timeout.
+        concurrent_notebooks (int): Max number of notebooks per minute to run in parallel.
     """
 
     # Calculate deadline
@@ -507,7 +506,9 @@ def process_and_execute_notebooks(
             print(
                 "Running notebooks in parallel, so no logs will be displayed. Please wait..."
             )
-            with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
+
+
+            with concurrent.futures.ThreadPoolExecutor(max_workers=concurrent_notebooks) as executor:
                 print(f"Max workers: {executor._max_workers}")
 
                 notebook_execution_results = list(

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

.github/workflows/linter/run_linter.sh

@@ -84,7 +84,7 @@ if [ ${#notebooks[@]} -gt 0 ]; then
                 # python3 -m nbqa black "$notebook" --check
                 # BLACK_RTN=$?
                 echo "Running pyupgrade..."
-                python3 -m nbqa pyupgrade "$notebook"
+                python3 -m nbqa pyupgrade --exit-zero-even-if-changed "$notebook"
                 PYUPGRADE_RTN=$?
                 echo "Running isort..."
                 python3 -m nbqa isort "$notebook" --check
@@ -97,7 +97,7 @@ if [ ${#notebooks[@]} -gt 0 ]; then
                 python3 -m nbqa black "$notebook"
                 BLACK_RTN=$?
                 echo "Running pyupgrade..."
-                python3 -m nbqa pyupgrade "$notebook"
+                python3 -m nbqa pyupgrade --exit-zero-even-if-changed "$notebook"
                 PYUPGRADE_RTN=$?
                 echo "Running isort..."
                 python3 -m nbqa isort "$notebook"

community-content/CODEOWNERS

@@ -12,3 +12,4 @@
 /prediction_featurestore_integration @googleapis/vertex-prediction-team
 /vertex_vision_model_garden/model_oss/util @weigary
 /vertex_vision_model_garden/model_oss/diffusers @weigary
+/vertex_vision_model_garden/model_oss/transformers @dstnluong-google

community-content/vertex_vision_model_garden/.pylintrc

@@ -0,0 +1,4 @@
+[MASTER]
+
+generated-members=get_concrete_function,cv2.*
+ignored-modules=tensorflow,google.cloud

community-content/vertex_vision_model_garden/model_oss/diffusers/dockerfile/serve.Dockerfile

@@ -4,8 +4,8 @@
 # docker build -f model_oss/diffusers/dockerfile/serve.Dockerfile . -t ${YOUR_IMAGE_TAG}
 #
 # To push to gcr:
-# docker tag ${YOUR_IMAGE_TAG} gcr.io/{YOUR_PROJECT}/${YOUR_IMAGE_TAG}
-# docker push gcr.io/{YOUR_PROJECT}/${YOUR_IMAGE_TAG}
+# docker tag ${YOUR_IMAGE_TAG} gcr.io/${YOUR_PROJECT}/${YOUR_IMAGE_TAG}
+# docker push gcr.io/${YOUR_PROJECT}/${YOUR_IMAGE_TAG}
 
 FROM pytorch/torchserve:0.7.0-gpu
 
@@ -34,11 +34,9 @@ RUN pip install absl-py==1.4.0
 RUN apt-get update && apt-get install wget
 RUN wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/LICENSE
 
-# The latest released diffusers library doesn't include ControlNet yet.
-# Install diffusers from main branch source code but with a pinned commit.
-RUN git clone https://github.com/huggingface/diffusers.git
+# Install diffusers from main branch source code with a pinned commit.
+RUN git clone --depth 1 --branch v0.18.1 https://github.com/huggingface/diffusers.git
 WORKDIR diffusers
-RUN git reset --hard 7ce3fa010a5019ed35d5a89572d3f68646b2a8d9
 RUN pip install -e .
 
 # Copy model artifacts.

community-content/vertex_vision_model_garden/model_oss/diffusers/dockerfile/train.Dockerfile

@@ -4,8 +4,8 @@
 # docker build -f model_oss/diffusers/dockerfile/train.Dockerfile . -t ${YOUR_IMAGE_TAG}
 #
 # To push to gcr:
-# docker tag ${YOUR_IMAGE_TAG} gcr.io/{YOUR_PROJECT}/${YOUR_IMAGE_TAG}
-# docker push gcr.io/{YOUR_PROJECT}/${YOUR_IMAGE_TAG}
+# docker tag ${YOUR_IMAGE_TAG} gcr.io/${YOUR_PROJECT}/${YOUR_IMAGE_TAG}
+# docker push gcr.io/${YOUR_PROJECT}/${YOUR_IMAGE_TAG}
 
 # Base on pytorch-cuda image.
 FROM pytorch/pytorch:1.13.0-cuda11.6-cudnn8-runtime
@@ -31,7 +31,14 @@ RUN pip install Jinja2==3.1.2
 RUN pip install ftfy==6.1.1
 RUN pip install cloudml-hypertune==0.1.0.dev6
 RUN pip install tensorboard==2.12.0
-RUN pip install diffusers==0.17.1
+
+# Install diffusers from main branch source code with a pinned commit.
+RUN git clone --depth 1 --branch v0.18.1 https://github.com/huggingface/diffusers.git
+WORKDIR diffusers
+RUN pip install -e .
+
+# Switch to diffusers examples folder.
+WORKDIR examples
 
 # Config accelerate.
 COPY model_oss/diffusers/train.sh train.sh

community-content/vertex_vision_model_garden/model_oss/diffusers/handler.py

@@ -4,10 +4,9 @@
 # pylint: disable=logging-fstring-interpolation
 
 import base64
-import io
 import logging
 import os
-from typing import Any, List, Sequence, Tuple
+from typing import Any, List, Tuple
 
 from diffusers import ControlNetModel
 from diffusers import DiffusionPipeline
@@ -21,14 +20,15 @@ from diffusers import StableDiffusionPipeline
 from diffusers import StableDiffusionUpscalePipeline
 from diffusers import TextToVideoZeroPipeline
 from diffusers import UniPCMultistepScheduler
-import imageio
 import numpy as np
 from PIL import Image
 import torch
 from ts.torch_handler.base_handler import BaseHandler
 
-from google3.cloud.ml.applications.vision.model_garden.model_oss.util import constants
-from google3.cloud.ml.applications.vision.model_garden.model_oss.util import fileutils
+from util import constants
+from util import fileutils
+from util import image_format_converter
+from video_util import video_format_converter
 
 STABLE_DIFFUSION_MODEL = "runwayml/stable-diffusion-v1-5"
 
@@ -43,13 +43,6 @@ TEXT_TO_VIDEO_ZERO_SHOT = "text-to-video-zero-shot"
 TEXT_TO_VIDEO = "text-to-video"
 
 
-def frames_to_video_bytes(frames: Sequence[np.ndarray], fps: int) -> bytes:
-  images = [Image.fromarray(array) for array in frames]
-  io_obj = io.BytesIO()
-  imageio.mimsave(io_obj, images, format=".mp4", fps=fps)
-  return io_obj.getvalue()
-
-
 class DiffusersHandler(BaseHandler):
   """Custom handler for TIMM models."""
 
@@ -175,18 +168,6 @@ class DiffusersHandler(BaseHandler):
     self.initialized = True
     logging.info("Handler initialization done.")
 
-  def _image_to_base64(self, image: Image.Image) -> str:
-    """Convert a PIL image to a base64 string."""
-    buffer = io.BytesIO()
-    image.save(buffer, format="JPEG")
-    image_str = base64.b64encode(buffer.getvalue()).decode("utf-8")
-    return image_str
-
-  def _base64_to_image(self, image_str: str) -> Image.Image:
-    """Convert a base64 string to a PIL image."""
-    image = Image.open(io.BytesIO(base64.b64decode(image_str)))
-    return image
-
   def preprocess(self, data: Any) -> Tuple[Any, Any, Any]:
     """Preprocess input data."""
     prompts = [item["prompt"] for item in data]
@@ -194,9 +175,14 @@ class DiffusersHandler(BaseHandler):
     mask_images = None
 
     if "image" in data[0]:
-      images = [self._base64_to_image(item["image"]) for item in data]
+      images = [
+          image_format_converter.base64_to_image(item["image"]) for item in data
+      ]
     if "mask_image" in data[0]:
-      mask_images = [self._base64_to_image(item["mask_image"]) for item in data]
+      mask_images = [
+          image_format_converter.base64_to_image(item["mask_image"])
+          for item in data
+      ]
     return prompts, images, mask_images
 
   def inference(self, data: Any, *args, **kwargs) -> List[Image.Image]:
@@ -223,15 +209,13 @@ class DiffusersHandler(BaseHandler):
     elif self.task == TEXT_TO_VIDEO_ZERO_SHOT:
       # For each given prompt, generate a short video.
       # The pipeline doesn't support multiple prompts in one run yet.
-      # vv-docker:google3-begin(internal)
-      # TODO(b/286955587): Improve zero-shot text-to-video by exporting video
-      #   files to customer provided gcs path and tuning the model quality.
-      # vv-docker:google3-end
       videos = []
       for prompt in prompts:
         numpy_arrays = self.pipeline(prompt=prompt).images
         numpy_arrays = [(i * 255).astype("uint8") for i in numpy_arrays]
-        videos.append(frames_to_video_bytes(numpy_arrays, fps=4))
+        videos.append(
+            video_format_converter.frames_to_video_bytes(numpy_arrays, fps=4)
+        )
       return videos
     elif self.task == TEXT_TO_VIDEO:
       predicted_images = np.asarray(self.pipeline(prompt=prompts).frames)
@@ -240,7 +224,8 @@ class DiffusersHandler(BaseHandler):
       # Therefore we need to split the output into different videos.
       predicted_images = np.array_split(predicted_images, len(prompts), axis=2)
       videos = [
-          frames_to_video_bytes(images, fps=8) for images in predicted_images
+          video_format_converter.frames_to_video_bytes(images, fps=8)
+          for images in predicted_images
       ]
       return videos
     else:
@@ -255,7 +240,7 @@ class DiffusersHandler(BaseHandler):
         # This is the video bytes.
         outputs.append(base64.b64encode(prediction).decode("utf-8"))
       else:
-        outputs.append(self._image_to_base64(prediction))
+        outputs.append(image_format_converter.image_to_base64(prediction))
     return outputs
 
 

community-content/vertex_vision_model_garden/model_oss/transformers/dockerfile/serve.Dockerfile

@@ -0,0 +1,79 @@
+# Dockerfile for serving dockers for transformers.
+#
+# To build:
+# docker build -f model_oss/transformers/dockerfile/serve.Dockerfile . -t ${YOUR_IMAGE_TAG}
+#
+# To push to gcr:
+# docker tag ${YOUR_IMAGE_TAG} gcr.io/${YOUR_PROJECT}/${YOUR_IMAGE_TAG}
+# docker push gcr.io/${YOUR_PROJECT}/${YOUR_IMAGE_TAG}
+# Switch to this base image for gpu serve.
+
+FROM pytorch/torchserve:0.7.0-gpu
+
+USER root
+
+ENV infer_port=7080
+ENV mng_port=7081
+ENV model_name="transformers_serving"
+ENV PATH="/home/model-server/:${PATH}"
+
+# Install libraries.
+ENV PIP_ROOT_USER_ACTION=ignore
+RUN python3 -m pip install --upgrade pip
+RUN pip install torch==1.13.1
+RUN pip install torchvision==0.14.1
+RUN pip install transformers==4.27.4
+RUN pip install datasets==2.9.0
+RUN pip install accelerate==0.17.0
+RUN pip install triton==2.0.0.dev20221120
+RUN pip install xformers==0.0.16
+RUN pip install google-cloud-storage==2.7.0
+RUN pip install absl-py==1.4.0
+
+# Install libraries for document-question-answering.
+RUN apt-get update
+RUN apt-get install -y --no-install-recommends tesseract-ocr
+RUN pip install tesseract==0.1.3
+RUN pip install pytesseract==0.3.10
+
+# Install tools.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        curl \
+        wget \
+        vim
+
+# Copy license.
+RUN wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/LICENSE
+
+# Copy model artifacts.
+COPY model_oss/transformers/handler.py /home/model-server/handler.py
+COPY model_oss/util/ /home/model-server/util/
+ENV PYTHONPATH /home/model-server/
+
+# Create torchserve configuration file.
+RUN echo \
+    "default_response_timeout=1800\n" \
+    "service_envelope=json\n" \
+    "inference_address=http://0.0.0.0:${infer_port}\n"  \
+    "management_address=http://0.0.0.0:${mng_port}" >> /home/model-server/config.properties
+
+# Expose ports.
+EXPOSE ${infer_port}
+EXPOSE ${mng_port}
+
+# Archive model artifacts and dependencies.
+# Do not set --model-file and --serialized-file because model and checkpoint will be dynamically loaded in handler.py.
+RUN torch-model-archiver \
+--model-name=${model_name} \
+--version=1.0 \
+--handler=/home/model-server/handler.py \
+--runtime=python3 \
+--export-path=/home/model-server/model-store \
+--archive-format=default \
+--force
+
+# Run Torchserve HTTP serve to respond to prediction requests.
+CMD ["torchserve", "--start", \
+     "--ts-config", "/home/model-server/config.properties", \
+     "--models", "${model_name}=${model_name}.mar", \
+     "--model-store", "/home/model-server/model-store"]

community-content/vertex_vision_model_garden/model_oss/transformers/handler.py

@@ -0,0 +1,233 @@
+"""Custom handler for huggingface/transformers models."""
+
+# pylint: disable=g-multiple-import
+# pylint: disable=g-importing-member
+
+import logging
+import os
+from typing import Any, List, Optional, Tuple
+
+from PIL import Image
+import torch
+from transformers import (
+    AutoProcessor,
+    AutoTokenizer,
+    Blip2ForConditionalGeneration,
+    Blip2Processor,
+    BlipForConditionalGeneration,
+    BlipForQuestionAnswering,
+    BlipProcessor,
+    CLIPModel,
+)
+from transformers import pipeline
+from ts.torch_handler.base_handler import BaseHandler
+
+from util import constants
+from util import fileutils
+from util import image_format_converter
+
+DEFAULT_MODEL_ID = "openai/clip-vit-base-patch32"
+SALESFORCE_BLIP = "Salesforce/blip"
+SALESFORCE_BLIP2 = "Salesforce/blip2"
+FLAN_T5 = "flan-t5"
+BART_LARGE_CNN = "facebook/bart-large-cnn"
+
+ZERO_CLASSIFICATION = "zero-shot-image-classification"
+FEATURE_EMBEDDING = "feature-embedding"
+ZERO_DETECTION = "zero-shot-object-detection"
+IMAGE_CAPTIONING = "image-to-text"
+VQA = "visual-question-answering"
+DQA = "document-question-answering"
+SUMMARIZATION = "summarization"
+SUMMARIZATION_TEMPLATE = (
+    "Summarize the following news article:\n{input}\nSummary:\n"
+)
+
+
+class TransformersHandler(BaseHandler):
+  """Custom handler for huggingface/transformers models."""
+
+  def initialize(self, context: Any):
+    """Custom initialize."""
+
+    properties = context.system_properties
+    self.map_location = (
+        "cuda"
+        if torch.cuda.is_available() and properties.get("gpu_id") is not None
+        else "cpu"
+    )
+    self.device = torch.device(
+        self.map_location + ":" + str(properties.get("gpu_id"))
+        if torch.cuda.is_available() and properties.get("gpu_id") is not None
+        else self.map_location
+    )
+
+    self.manifest = context.manifest
+    # The model id is can be either:
+    # 1) a huggingface model card id, like "Salesforce/blip", or
+    # 2) a GCS path to the model files, like "gs://foo/bar".
+    # If it's a model card id, the model will be loaded from huggingface.
+    self.model_id = (
+        DEFAULT_MODEL_ID
+        if os.environ.get("MODEL_ID") is None
+        else os.environ["MODEL_ID"]
+    )
+    # Else it will be downloaded from GCS to local first.
+    # Since the transformers from_pretrained API can't read from GCS.
+    if self.model_id.startswith(constants.GCS_URI_PREFIX):
+      gcs_path = self.model_id[len(constants.GCS_URI_PREFIX) :]
+      local_model_dir = os.path.join(constants.LOCAL_MODEL_DIR, gcs_path)
+      logging.info("Download %s to %s", self.model_id, local_model_dir)
+      fileutils.download_gcs_dir_to_local(self.model_id, local_model_dir)
+      self.model_id = local_model_dir
+
+    self.task = (
+        ZERO_CLASSIFICATION
+        if os.environ.get("TASK") is None
+        else os.environ["TASK"]
+    )
+    logging.info(
+        "Handler initializing task:%s, model:%s", self.task, self.model_id
+    )
+
+    if SALESFORCE_BLIP in self.model_id:
+      # pipeline() hasn't been ready for Salesforce/blip models.
+      self.salesforce_blip = True
+      self._create_blip_model()
+    else:
+      self.salesforce_blip = False
+      if self.task == FEATURE_EMBEDDING:
+        self.model = CLIPModel.from_pretrained(self.model_id).to(
+            self.map_location
+        )
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_id)
+        self.processor = AutoProcessor.from_pretrained(self.model_id)
+      elif self.task == SUMMARIZATION and FLAN_T5 in self.model_id:
+        self.pipeline = pipeline(
+            task=self.task,
+            model=self.model_id,
+            torch_dtype=torch.bfloat16,
+            device_map="auto",
+        )
+      else:
+        self.pipeline = pipeline(
+            task=self.task, model=self.model_id, device=self.device
+        )
+
+    self.initialized = True
+    logging.info("Handler initialization done.")
+
+  def _create_blip_model(self):
+    """A helper for creating BLIP and BLIP2 models."""
+    if SALESFORCE_BLIP2 in self.model_id:
+      self.torch_type = torch.float16
+      self.processor = Blip2Processor.from_pretrained(self.model_id)
+      self.model = Blip2ForConditionalGeneration.from_pretrained(
+          self.model_id, torch_dtype=self.torch_type
+      ).to(self.map_location)
+    else:
+      self.torch_type = torch.float32
+      self.processor = BlipProcessor.from_pretrained(self.model_id)
+      if self.task == IMAGE_CAPTIONING:
+        self.model = BlipForConditionalGeneration.from_pretrained(
+            self.model_id
+        ).to(self.map_location)
+      elif self.task == VQA:
+        self.model = BlipForQuestionAnswering.from_pretrained(self.model_id).to(
+            self.map_location
+        )
+
+  def _reformat_detection_result(self, data: List[Any]) -> List[Any]:
+    """Reformat zero-shot-object-detection output."""
+    if not data:
+      return [data]
+    boxes = {}
+    boxes["label"] = data[0]["label"]
+    boxes["boxes"] = []
+    for item in data:
+      box = {}
+      box["score"] = item["score"]
+      box.update(item["box"])
+      boxes["boxes"].append(box)
+    outputs = [boxes]
+    return outputs
+
+  def preprocess(
+      self, data: Any
+  ) -> Tuple[Optional[List[str]], Optional[List[Image.Image]]]:
+    """Preprocess input data."""
+    texts = None
+    images = None
+    if "text" in data[0]:
+      texts = [item["text"] for item in data]
+    if "image" in data[0]:
+      images = [
+          image_format_converter.base64_to_image(item["image"]) for item in data
+      ]
+    return texts, images
+
+  def inference(self, data: Any, *args, **kwargs) -> List[Any]:
+    """Run the inference."""
+    texts, images = data
+    preds = None
+    if self.task == ZERO_CLASSIFICATION:
+      preds = self.pipeline(images=images, candidate_labels=texts)
+    elif self.task == ZERO_DETECTION:
+      # The object detection pipeline doesn't support batch prediction.
+      preds = self.pipeline(image=images[0], candidate_labels=texts[0])
+    elif self.task == IMAGE_CAPTIONING:
+      if self.salesforce_blip:
+        inputs = self.processor(images[0], return_tensors="pt").to(
+            self.map_location, self.torch_type
+        )
+        preds = self.model.generate(**inputs)
+        preds = [
+            self.processor.decode(preds[0], skip_special_tokens=True).strip()
+        ]
+      else:
+        preds = self.pipeline(images=images)
+    elif self.task == VQA:
+      # The VQA pipelines doesn't support batch prediction.
+      if self.salesforce_blip:
+        inputs = self.processor(images[0], texts[0], return_tensors="pt").to(
+            self.map_location, self.torch_type
+        )
+        preds = self.model.generate(**inputs)
+        preds = [
+            self.processor.decode(preds[0], skip_special_tokens=True).strip()
+        ]
+      else:
+        preds = self.pipeline(image=images[0], question=texts[0])
+    elif self.task == DQA:
+      # The DQA pipelines doesn't support batch prediction.
+      preds = self.pipeline(image=images[0], question=texts[0])
+    elif self.task == FEATURE_EMBEDDING:
+      preds = {}
+      if texts:
+        inputs = self.tokenizer(
+            text=texts, padding=True, return_tensors="pt"
+        ).to(self.map_location)
+        text_features = self.model.get_text_features(**inputs)
+        preds["text_features"] = text_features.detach().cpu().numpy().tolist()
+      if images:
+        inputs = self.processor(images=images, return_tensors="pt").to(
+            self.map_location
+        )
+        image_features = self.model.get_image_features(**inputs)
+        preds["image_features"] = image_features.detach().cpu().numpy().tolist()
+      preds = [preds]
+    elif self.task == SUMMARIZATION and FLAN_T5 in self.model_id:
+      texts = [SUMMARIZATION_TEMPLATE.format(input=text) for text in texts]
+      preds = self.pipeline(texts, max_length=130)
+    elif self.task == SUMMARIZATION and self.model_id == BART_LARGE_CNN:
+      preds = self.pipeline(
+          texts[0], max_length=130, min_length=30, do_sample=False
+      )
+    else:
+      raise ValueError(f"Invalid TASK: {self.task}")
+    return preds
+
+  def postprocess(self, data: Any) -> List[Any]:
+    if self.task == ZERO_DETECTION:
+      data = self._reformat_detection_result(data)
+    return data

community-content/vertex_vision_model_garden/model_oss/util/fileutils.py

@@ -6,7 +6,7 @@ import os
 from absl import logging
 from google.cloud import storage
 
-from google3.cloud.ml.applications.vision.model_garden.model_oss.util import constants
+from util import constants
 
 
 def download_gcs_file_to_local(gcs_uri: str, local_path: str):

community-content/vertex_vision_model_garden/model_oss/util/image_format_converter.py

@@ -0,0 +1,20 @@
+"""Image format converter util lib."""
+
+import base64
+import io
+
+from PIL import Image
+
+
+def image_to_base64(image: Image.Image) -> str:
+  """Convert a PIL image to a base64 string."""
+  buffer = io.BytesIO()
+  image.save(buffer, format="JPEG")
+  image_str = base64.b64encode(buffer.getvalue()).decode("utf-8")
+  return image_str
+
+
+def base64_to_image(image_str: str) -> Image.Image:
+  """Convert a base64 string to a PIL image."""
+  image = Image.open(io.BytesIO(base64.b64decode(image_str)))
+  return image

community-content/vertex_vision_model_garden/model_oss/video_util/video_format_converter.py

@@ -0,0 +1,14 @@
+"""Video format converter util lib."""
+
+import io
+from typing import Sequence
+import imageio
+import numpy as np
+from PIL import Image
+
+
+def frames_to_video_bytes(frames: Sequence[np.ndarray], fps: int) -> bytes:
+  images = [Image.fromarray(array) for array in frames]
+  io_obj = io.BytesIO()
+  imageio.mimsave(io_obj, images, format=".mp4", fps=fps)
+  return io_obj.getvalue()

notebooks/community/CODEOWNERS

@@ -51,6 +51,7 @@
 /notebooks/community/model_garden/model_garden_tfvision_image_object_detection.ipynb @genquan9
 /notebooks/community/model_garden/model_garden_tfvision_image_segmentation.ipynb @genquan9
 /notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb @xiangxu-google
+/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_2_1.ipynb @bingatgoogle
 /notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb @xiangxu-google
 /notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb @xiangxu-google
 /notebooks/community/model_garden/model_garden_pytorch_controlnet.ipynb @xiangxu-google
@@ -72,3 +73,4 @@
 /notebooks/community/bigquery_ml_inference/bq_ml_with_vision_translation_nlp.ipynb @deaconsmith
 /notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb @genquan9
 /notebooks/community/model_garden/model_garden_pytorch_sam.ipynb @huguensjean
+/notebooks/community/model_garden/model_garden_pytorch_peft.ipynb @genquan9

notebooks/community/model_garden/model_garden_keras_stable_diffusion.ipynb

@@ -322,7 +322,7 @@
         "    deploy_model_name = get_job_name_with_datetime(DEPLOY_JOB_PREFIX)\n",
         "    print(\"The deployed job name is: \", deploy_model_name)\n",
         "    serving_env = {\n",
-        "        \"MODEL_PATH\": model_path,\n",
+        "        \"MODEL_PATH\": f\"{model_path}\",\n",
         "        \"IMAGE_WIDTH\": f\"{RESOLUTION}\",\n",
         "        \"IMAGE_HEIGHT\": f\"{RESOLUTION}\",\n",
         "    }\n",

notebooks/community/model_garden/model_garden_mediapipe_image_classification.ipynb

@@ -72,7 +72,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook demonstrates how to use [MediaPipe ModelMaker](https://developers.google.com/mediapipe/solutions/model_maker) in Vertex AI Model Garden.\n",
+        "This notebook demonstrates how to use [MediaPipe Model Maker](https://developers.google.com/mediapipe/solutions/model_maker) to train an on-device image classification model in Vertex AI Model Garden.\n",
         "\n",
         "### Objective\n",
         "\n",
@@ -112,7 +112,7 @@
         "id": "z__i0w0lCAsW"
       },
       "source": [
-        "### Colab Only\n",
+        "### Colab only\n",
         "Run the following commands to install dependencies and to authenticate with Google Cloud if running on Colab."
       ]
     },
@@ -126,7 +126,9 @@
       "source": [
         "! pip3 install --upgrade pip\n",
         "\n",
-        "if \"google.colab\" in str(get_ipython()):\n",
+        "import sys\n",
+        "\n",
+        "if \"google.colab\" in sys.modules:\n",
         "    ! pip3 install --upgrade google-cloud-aiplatform\n",
         "\n",
         "    # Automatically restart kernel after installs\n",
@@ -236,6 +238,15 @@
         "TRAINING_ACCELERATOR_COUNT = 2"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-rsdAcBV-vlf"
+      },
+      "source": [
+        "## Train your customized models"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -244,9 +255,9 @@
       "source": [
         "### Prepare input data for training\n",
         "\n",
-        "Retraining a model for image classification requires a dataset that includes all kinds of items, or classes, that you want the completed model to be able to identify. You can do this by trimming down a public dataset to only the classes that are relevant to your usecase, compiling your own data, or some combination of both. The dataset can be significantly smaller that what would be required to train a new model. For example, the [ImageNet](https://www.image-net.org/) dataset used to train many reference models contains millions of images with thousands of categories. Transfer learning with Model Maker can retrain an existing model with a smaller dataset and still perform well, depending on your inference accuracy goals.\n",
+        "Finetuning a model for image classification requires a dataset that includes all kinds of items, or classes, that you want the completed model to be able to identify. You can do this by trimming down a public dataset to only the classes that are relevant to your usecase, compiling your own data, or some combination of both. The dataset can be significantly smaller than what would be required to train a new model from scratch. For example, the [ImageNet](https://www.image-net.org/) dataset used to train many reference models contains millions of images with thousands of categories. Transfer learning with Model Maker can finetune an existing model with a smaller dataset and still perform well, depending on your inference accuracy goals.\n",
         "\n",
-        "You can re-use an existing dataset such as `gs://cloud-samples-data-us-central1/vision/automl_classification/flowers` to re-train the model or you can upload your own dataset to GCS. If you are using your own dataset, ensure that your image directory contains several subdirectories, each corresponding to specific class labels. Your training data should also follow this pattern: <image_path>/<label_name>/<image_names>.*."
+        "You can re-use an existing dataset such as `gs://cloud-samples-data-us-central1/vision/automl_classification/flowers` to finetune the model or you can upload your own dataset to GCS. If you are using your own dataset, ensure that your image directory contains several subdirectories, each corresponding to specific class labels. Your training data should also follow this pattern: <image_path>/<label_name>/<image_names>.*."
       ]
     },
     {
@@ -258,7 +269,7 @@
       "outputs": [],
       "source": [
         "training_data_path = \"gs://cloud-samples-data-us-central1/vision/automl_classification/flowers\"  # @param {type:\"string\"}\n",
-        "split_ratio = \"0.6,0.1,0.1\"  # @param {type:\"string\"}"
+        "split_ratio = \"0.8,0.1,0.1\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -267,9 +278,9 @@
         "id": "aaff6f5be7f6"
       },
       "source": [
-        "### Set retraining options\n",
+        "### Set fine-tuning options\n",
         "\n",
-        "There are a few required settings to run a retraining aside from your training dataset: output directory for the model and the model architecture. Use HParams object export_dir parameter to specify a model output directory. Use the SupportedModels class to specify the model architecture. The image classifier solution supports the following model architectures:\n",
+        "There are a few required settings to run fine-tuning aside from your training dataset: output directory for the model and the model architecture. Use HParams object export_dir parameter to specify a model output directory. Use the SupportedModels class to specify the model architecture. The image classifier solution supports the following model architectures:\n",
         "\n",
         "*   MobileNet-V2\n",
         "*   EfficientNet-Lite0\n",
@@ -322,10 +333,10 @@
         "id": "HwcCjwlBTQIz"
       },
       "source": [
-        "#### Run retraining\n",
-        "With your training dataset and retraining options prepared, you are ready to start the retraining process. This process is resource intensive and can take a few minutes to a few hours depending on your available compute resources. On Vertex AI with GPU processing, the example retraining below takes between 4-6 minutes to train on approximately 3700 images.\n",
+        "### Run fine-tuning\n",
+        "With your training dataset and fine-tuning options prepared, you are ready to start the fine-tuning process. This process is resource intensive and can take a few minutes to a few hours depending on your available compute resources. On Vertex AI with GPU processing, the example fine-tuning below takes between 4-6 minutes to train on approximately 3700 images.\n",
         "\n",
-        "To begin the retraining process, use the following code:\n"
+        "To begin the fine-tuning process, use the following code:\n"
       ]
     },
     {
@@ -387,6 +398,15 @@
         "training_job.run()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "rXMF2tnV_WS0"
+      },
+      "source": [
+        "## Evaluate and export model"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -395,7 +415,7 @@
       "source": [
         "### Evaluate performance\n",
         "\n",
-        "After retraining the model, we evaluate the training result on a test dataset, which is typically a portion of your original dataset not used during training. Accuracy levels between 0.8 and 0.9 are generally considered very good, but your use case requirements may differ. You should also consider how fast the model can produce an inference. Higher accuracy frequently comes at the cost of longer inference times.\n"
+        "After fine-tuning the model, we evaluate the training result on a test dataset, which is typically a portion of your original dataset not used during training. Accuracy levels between 0.8 and 0.9 are generally considered very good, but your use case requirements may differ. You should also consider how fast the model can produce an inference. Higher accuracy frequently comes at the cost of longer inference times.\n"
       ]
     },
     {
@@ -433,8 +453,8 @@
         "id": "g0BGaofgsMsy"
       },
       "source": [
-        "## Export model\n",
-        "After retraining and evaluating the model, you can save the Tensorflow Lite model, try it out in the [Image Classification](https://mediapipe-studio.webapps.google.com/demo/image_classifier) demo in MediaPipe Studio or integrate it with your application by following the [Image classification task guide](https://developers.google.com/mediapipe/solutions/vision/image_classifier). The exported model contains the generates required model metadata, as well as a classification label file."
+        "### Export model\n",
+        "After finetuning and evaluating the model, you can save the Tensorflow Lite model, try it out in the [Image Classification](https://mediapipe-studio.webapps.google.com/demo/image_classifier) demo in MediaPipe Studio or integrate it with your on-device application by following the [Image classification task guide](https://developers.google.com/mediapipe/solutions/vision/image_classifier). The exported model contains the generates required model metadata, as well as a classification label file."
       ]
     },
     {
@@ -445,12 +465,14 @@
       },
       "outputs": [],
       "source": [
+        "import sys\n",
+        "\n",
         "def copy_model(model_source, model_dest):\n",
         "    ! gsutil cp {model_source} {model_dest}\n",
         "\n",
         "copy_model(EXPORTED_MODEL_OUTPUT_FILE, \"image_classification_model.tflite\")\n",
         "\n",
-        "if \"google.colab\" in str(get_ipython()):\n",
+        "if \"google.colab\" in sys.modules:\n",
         "    from google.colab import files\n",
         "\n",
         "    files.download(\"image_classification_model.tflite\")"

notebooks/community/model_garden/model_garden_mediapipe_object_detection.ipynb

@@ -72,7 +72,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook demonstrates how to use [MediaPipe ModelMaker](https://developers.google.com/mediapipe/solutions/model_maker) in Vertex AI Model Garden.\n",
+        "This notebook demonstrates how to use [MediaPipe Model Maker](https://developers.google.com/mediapipe/solutions/model_maker) in Vertex AI Model Garden.\n",
         "\n",
         "### Objective\n",
         "\n",
@@ -126,7 +126,9 @@
       "source": [
         "! pip3 install --upgrade pip\n",
         "\n",
-        "if \"google.colab\" in str(get_ipython()):\n",
+        "import sys\n",
+        "\n",
+        "if \"google.colab\" in sys.modules:\n",
         "    ! pip3 install --upgrade google-cloud-aiplatform\n",
         "\n",
         "    # Automatically restart kernel after installs\n",
@@ -236,6 +238,15 @@
         "TRAINING_ACCELERATOR_COUNT = 2"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XDq9TiRUc7dV"
+      },
+      "source": [
+        "## Train your customized models"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -244,9 +255,9 @@
       "source": [
         "### Prepare input data for training\n",
         "\n",
-        "Retraining a model for object detection requires a dataset that includes the items, or classes, that you want the completed model to be able to identify. You can do this by trimming down a public dataset to only the classes that are relevant to your usecase, compiling your own dataset, or some combination of both, The dataset can be significantly smaller than what would be required to train a new model. For example, the [COCO](https://cocodataset.org/) dataset used to train many reference models contains hundreds of thousands of images with 91 classes of objects. Transfer learning with Model Maker can retrain an existing model with a smaller dataset and still perform well, depending on your inference accuracy goals. These instructions use a smaller dataset containing 2 types of android figurines, or 2 classes, with 62 total training images.\n",
+        "Fine-tuning a model for object detection requires a dataset that includes the items, or classes, that you want the completed model to be able to identify. You can do this by trimming down a public dataset to only the classes that are relevant to your usecase, compiling your own dataset, or some combination of both, The dataset can be significantly smaller than what would be required to train a new model from scratch. For example, the [COCO](https://cocodataset.org/) dataset used to train many reference models contains hundreds of thousands of images with 91 classes of objects. Transfer learning with Model Maker can finetune an existing model with a smaller dataset and still perform well, depending on your inference accuracy goals. These instructions use a smaller dataset containing 2 types of android figurines, or 2 classes, with 62 total training images.\n",
         "\n",
-        "You can re-use an existing dataset such as `gs://mediapipe-tasks/object_detector/android_figurine` to re-train the model. The directory contains two subdirectories for the training and validation datasets, located in android_figurine/train and android_figurine/validation respectively. Each of the train and validation datasets follow the COCO Dataset format described below. If you are using your own dataset, ensure that that it adheres to the format specifications before uploading it to Google Cloud Storage.\n",
+        "You can re-use an existing dataset such as `gs://mediapipe-tasks/object_detector/android_figurine` to finetune the model. The directory contains two subdirectories for the training and validation datasets, located in android_figurine/train and android_figurine/validation respectively. Each of the train and validation datasets follow the COCO Dataset format described below. If you are using your own dataset, ensure that that it adheres to the format specifications before uploading it to Google Cloud Storage.\n",
         "\n",
         "\n",
         "### Supported dataset formats\n",
@@ -319,9 +330,9 @@
         "id": "O32DU5RRGhdV"
       },
       "source": [
-        "### Retrain model\n",
+        "### Configure training dataset\n",
         "\n",
-        "Once you have completed preparing your data, you can begin retraining a model to recognize the new objects, or classes, defined by your training data. The instructions below use the data prepared in the previous section to retrain an object detection model to recognize the two types of android figurines.\n",
+        "Once you have completed preparing your data, you can begin fine-tuning a model to recognize the new objects, or classes, defined by your training data. The instructions below use the data prepared in the previous section to finetune an object detection model to recognize the two types of android figurines.\n",
         "\n",
         "You can leave the path to the test data empty if you do not have a separate test data set."
       ]
@@ -346,9 +357,9 @@
         "id": "aaff6f5be7f6"
       },
       "source": [
-        "### Set retraining options\n",
+        "### Set fine-tuning options\n",
         "\n",
-        "There are a few required settings to run retraining aside from your training dataset: output directory for the model, and the model architecture. Use HParams to specify the export_dir parameter for the output directory. Use the SupportedModels class to specify the model architecture. The object detector solution supports the following model architectures:\n",
+        "There are a few required settings to run fine-tuning aside from your training dataset: output directory for the model, and the model architecture. Use HParams to specify the export_dir parameter for the output directory. Use the SupportedModels class to specify the model architecture. The object detector solution supports the following model architectures:\n",
         "\n",
         "*   MobileNet-V2\n",
         "*   MobileNet-MultiHW-AVG\n",
@@ -401,10 +412,10 @@
         "id": "HwcCjwlBTQIz"
       },
       "source": [
-        "#### Run retraining\n",
-        "With your training dataset and retraining options prepared, you are ready to start the retraining process. This process is resource intensive and can take a few minutes to a few hours depending on your available compute resources. This process is resource intensive and can take a few minutes to a few hours depending on your available compute resources. On Vertex AI with GPU processing, the example retraining below takes about 3 to 4 minutes.\n",
+        "### Run fine-tuning\n",
+        "With your training dataset and fine-tuning options prepared, you are ready to start the fine-tuning process. This process is resource intensive and can take a few minutes to a few hours depending on your available compute resources. This process is resource intensive and can take a few minutes to a few hours depending on your available compute resources. On Vertex AI with GPU processing, the example fine-tuning below takes about 3 to 4 minutes.\n",
         "\n",
-        "To begin the retraining process, use the following code:\n"
+        "To begin the fine-tuning process, use the following code:\n"
       ]
     },
     {
@@ -469,6 +480,15 @@
         "training_job.run()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zcKzIa5QeIIU"
+      },
+      "source": [
+        "## Evaluate and export model"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -511,8 +531,8 @@
         "id": "g0BGaofgsMsy"
       },
       "source": [
-        "## Export model\n",
-        "After retraining and evaluating the model, you can save it as Tensorflow Lite model, try it out in the [Object Detector](https://mediapipe-studio.webapps.google.com/demo/object_detector) demo in MediaPipe Studio or integrate it with your application by following the [Object detection task guide](https://developers.google.com/mediapipe/solutions/vision/object_detector). The exported model also includes metadata and the label map."
+        "### Export model\n",
+        "After fine-tuning and evaluating the model, you can save it as Tensorflow Lite model, try it out in the [Object Detector](https://mediapipe-studio.webapps.google.com/demo/object_detector) demo in MediaPipe Studio or integrate it with your application by following the [Object detection task guide](https://developers.google.com/mediapipe/solutions/vision/object_detector). The exported model also includes metadata and the label map."
       ]
     },
     {
@@ -523,12 +543,15 @@
       },
       "outputs": [],
       "source": [
+        "import sys\n",
+        "\n",
+        "\n",
         "def copy_model(model_source, model_dest):\n",
         "    ! gsutil cp {model_source} {model_dest}\n",
         "\n",
         "copy_model(EXPORTED_MODEL_OUTPUT_FILE, \"object_detection_model.tflite\")\n",
         "\n",
-        "if \"google.colab\" in str(get_ipython()):\n",
+        "if \"google.colab\" in sys.modules:\n",
         "    from google.colab import files\n",
         "\n",
         "    files.download(\"object_detection_model.tflite\")"

notebooks/community/model_garden/model_garden_proprietary_image_classification.ipynb

@@ -75,14 +75,14 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook demonstrates how to use Google proprietary image classification models traning/deployment in Vertex AI Model Garden.\n",
+        "This notebook demonstrates how to use Google proprietary image classification model training/deployment in [Vertex AI Model Garden](https://cloud.google.com/model-garden).\n",
         "\n",
         "### Objective\n",
         "\n",
         "* Train new models using Vertex SDK\n",
         "\n",
         "* Test trained models\n",
-        "  * View the trained model in Vertex Model Registry\n",
+        "  * View the trained model in [Vertex Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction)\n",
         "  * Deploy uploaded models\n",
         "  * Run predictions\n",
         "\n",
@@ -116,17 +116,6 @@
         "## Before you begin"
       ]
     },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "z__i0w0lCAsW"
-      },
-      "source": [
-        "### Colab Only\n",
-        "Run the following commands for Colab and skip this section if you use Workbench."
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -135,15 +124,14 @@
       },
       "outputs": [],
       "source": [
+        "! pip3 install --upgrade google-cloud-aiplatform\n",
+        "\n",
+        "# Automatically restart kernel after installs\n",
+        "import IPython\n",
+        "\n",
+        "app = IPython.Application.instance()\n",
+        "app.kernel.do_shutdown(True)\n",
         "if \"google.colab\" in str(get_ipython()):\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
-        "\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)\n",
-        "\n",
         "    from google.colab import auth as google_auth\n",
         "\n",
         "    google_auth.authenticate_user()"
@@ -164,6 +152,10 @@
         "\n",
         "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
         "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
@@ -187,13 +179,14 @@
         "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
         "\n",
         "# You can choose a region from https://cloud.google.com/about/locations.\n",
-        "# Only regions prefixed by \"us\", or \"europe\" are supported.\n",
+        "# Only regions prefixed by \"us\", \"europe\", or \"asia\" 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",
-        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"asia\", or \"europe\".'\n",
+        "    \"asia\",\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"europe\", or \"asia\".'\n",
         "\n",
         "! gcloud config set project $PROJECT_ID\n",
         "\n",
@@ -227,7 +220,8 @@
         "\n",
         "# Training constants.\n",
         "TRAINING_JOB_PREFIX = \"train\"\n",
-        "# The image classification flowers dataset used to train the model\n",
+        "\n",
+        "# The image classification flowers dataset used to train the model.\n",
         "DATASET_FILE = (\n",
         "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
         ")\n",
@@ -236,13 +230,8 @@
         "EVALUATION_METRIC = \"accuracy\"\n",
         "\n",
         "# Prediction constants.\n",
-        "# You can deploy models with\n",
-        "#   pre-build-dockers: https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers.\n",
-        "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
         "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
         "# You can adjust accelerator types and machine types to get faster predictions.\n",
-        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
-        "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
         "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
         "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
         "DEPLOY_JOB_PREFIX = \"deploy\""
@@ -268,6 +257,7 @@
       "source": [
         "import base64\n",
         "from datetime import datetime\n",
+        "from io import BytesIO\n",
         "\n",
         "import matplotlib.pyplot as plt\n",
         "import numpy\n",
@@ -384,8 +374,8 @@
         "### Create and run training pipeline\n",
         "\n",
         "To train an AutoML model, you perform two steps:\n",
-        "1.  create a training pipeline\n",
-        "2.  run the pipeline.\n",
+        "1.  Create a training pipeline.\n",
+        "2.  Run the pipeline.\n",
         "\n",
         "#### Create training pipeline\n",
         "\n",
@@ -395,42 +385,44 @@
         "- `prediction_type`: The type task to train the model for.\n",
         "  - `classification`: An image classification model.\n",
         "  - `object_detection`: An image object detection model.\n",
-        "- `multi_label`: If a classification task, whether single (`False`) or multi-labeled (`True`).\n",
+        "- `multi_label`: If a classification task is single (`False`) or multi-labeled (`True`).\n",
         "- `model_type`: The type of model for deployment.\n",
-        "  - `EFFICIENTNET`: A model that, available in Vertex Model Garden image classification training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
-        "  - `MAXVIT`: A model that, available in Vertex Model Garden image classification training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
-        "  - `COCA`: A model that, available in Vertex Model Garden image classification training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
+        "  - `EFFICIENTNET`: A model that is available in Vertex Model Garden image classification training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
+        "  - `MAXVIT`: A model that is available in Vertex Model Garden image classification training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
+        "  - `COCA`: A model that is available in Vertex Model Garden image classification training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
         "- `checkpoint_name`: Optional. The field is reserved for Model Garden model training, based on the provided pre-trained model checkpoint.\n",
-        "- `trainer_config`: Optional. The field is usually used together with the Model Garden model training, when passing the customized configs for the trainer.\n",
+        "- `trainer_config`: Optional. The field is usually used together with the Model Garden model training when passing the customized configs for the trainer.\n",
         "\n",
         "  Example with all supported parameters:\n",
-        "\n",
-        "  trainer_config = { \\\n",
-        "    'global_batch_size': '8', \\\n",
-        "    'learning_rate': '0.001', \\\n",
-        "    'optimizer_type': 'sgd', \\\n",
-        "    'optimizer_momentum': '0.9', \\\n",
-        "    'train_steps': '10000', \\\n",
-        "    'accelerator_count': '1', \\\n",
+        "```\n",
+        "  trainer_config = {\n",
+        "    'global_batch_size': '8',\n",
+        "    'learning_rate': '0.001',\n",
+        "    'optimizer_type': 'sgd',\n",
+        "    'optimizer_momentum': '0.9',\n",
+        "    'train_steps': '10000',\n",
+        "    'accelerator_count': '1',\n",
         "  }\n",
-        "- `metric_spec`: Dictionary representing metrics to optimize. The dictionary key is the metric_id, which is reported by your training job, with possible values be ('loss', 'accuracy') and the dictionary value is the optimization goal of the metric('minimize' or 'maximize').\n",
-        "For example:  metric_spec = {'loss': 'minimize', 'accuracy': 'maximize'}\n",
-        "- `parameter_spec`:Dictionary representing parameters to optimize. The dictionary key is the `metric_id`, which is passed into your training job as a command line key word argument, and the dictionary value is the parameter\n",
+        "```\n",
+        "- `metric_spec`: Dictionary representing metrics to optimize. The dictionary key is the `metric_id`, which is reported by your training job, with possible values being ('loss', 'accuracy') and the dictionary value is the optimization goal of the metric ('minimize' or 'maximize').\n",
+        "For example:  `metric_spec = {'loss': 'minimize', 'accuracy': 'maximize'}`\n",
+        "- `parameter_spec`: Dictionary representing parameters to optimize. The dictionary key is the `metric_id`, which is passed into your training job as a command line key word argument, and the dictionary value is the parameter\n",
         "specification of the metric. Supported parameter specifications can be found in aiplatform.hyperparameter_tuning.\n",
-        "\n",
+        "```\n",
         "  from google.cloud.aiplatform.aiplatform import hpt as hpt\n",
         "\n",
-        "  parameter_spec = { \\\n",
-        "    'learning_rate': hpt.DoubleParameterSpec(min=1e-7, max=1, scale='linear'), \\\n",
+        "  parameter_spec = {\n",
+        "    'learning_rate': hpt.DoubleParameterSpec(min=1e-7, max=1, scale='linear'),\n",
         "  }\n",
+        "```\n",
         "- `search_algorithm`: The search algorithm specified for the Study. Accepts one of the following:\n",
-        "  - `None` - If you do not specify an algorithm, your job uses the default\n",
+        "  - `None`: If you do not specify an algorithm, your job uses the default\n",
         "  Vertex AI algorithm. The default algorithm applies Bayesian optimization\n",
         "  to arrive at the optimal solution with a more effective search over the\n",
         "  parameter space.\n",
-        "  - `grid` - A simple grid search within the feasible space. This option is\n",
+        "  - `grid`: A simple grid search within the feasible space. This option is\n",
         "  particularly useful if you want to specify a quantity of trials that is greater than the number of points in the feasible space. In such cases, if you do not specify a grid search, the Vertex AI default algorithm may generate duplicate suggestions. To use grid search, all parameter specs must be of type `IntegerParameterSpec`, `CategoricalParameterSpec`, or `DiscreteParameterSpec`.\n",
-        "  - `random` - A simple random search within the feasible space.\n",
+        "  - `random`: A simple random search within the feasible space.\n",
         "- `measurement_selection`: This indicates which measurement to use\n",
         "if/when the service automatically selects the final measurement from\n",
         "previously reported intermediate measurements.\n",
@@ -470,7 +462,7 @@
         "job = aiplatform.AutoMLImageTrainingJob(\n",
         "    display_name=get_job_name_with_datetime(TRAINING_JOB_PREFIX),\n",
         "    prediction_type=\"classification\",\n",
-        "    multi_label=True,\n",
+        "    multi_label=False,\n",
         "    model_type=MODEL_TYPE,\n",
         "    base_model=None,\n",
         "    trainer_config=TRAINER_CONFIG,\n",
@@ -494,19 +486,19 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
         "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
-        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
         "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
         "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
-        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "- `disable_early_stopping`: If `True`, training may be completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
         "\n",
-        "The `run` method when completed returns the `Model` resource.\n",
+        "The `run` method, when completed, returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline take up to 1 hour."
+        "The execution of the training pipeline will take up to 60 minutes."
       ]
     },
     {
@@ -538,8 +530,8 @@
       },
       "source": [
         "## Test trained models\n",
-        "This section shows how to test with trained models.\n",
-        "1. Deploy models from model registry\n",
+        "This section shows how to test the trained models.\n",
+        "1. Deploy model from Model Registry\n",
         "2. Run online predictions"
       ]
     },
@@ -551,7 +543,7 @@
       },
       "outputs": [],
       "source": [
-        "# @title Deploy model from model registry\n",
+        "# @title Deploy model from Model Registry\n",
         "\n",
         "deploy_model_name = get_job_name_with_datetime(DEPLOY_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
         "print(\"The deployed job name is: \", deploy_model_name)\n",
@@ -580,9 +572,6 @@
       "source": [
         "# @title Run online predictions\n",
         "\n",
-        "# endpoint_id was generated in the section above (`Upload and deploy models`).\n",
-        "endpoint_id = endpoint.name\n",
-        "\n",
         "# test image file path from a GCS bucket\n",
         "test_filepath = \"\"  # @param {type:\"string\"}\n",
         "\n",

notebooks/community/model_garden/model_garden_proprietary_image_object_detection.ipynb

@@ -75,14 +75,14 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook demonstrates how to use Google proprietary image object detection models traning/deployment in Vertex AI Model Garden.\n",
+        "This notebook demonstrates how to use Google proprietary image object detection model training/deployment in [Vertex AI Model Garden](https://cloud.google.com/model-garden).\n",
         "\n",
         "### Objective\n",
         "\n",
         "* Train new models using Vertex SDK\n",
         "\n",
         "* Test trained models\n",
-        "  * View the trained model in Vertex Model Registry\n",
+        "  * View the trained model in [Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction)\n",
         "  * Deploy uploaded models\n",
         "  * Run predictions\n",
         "\n",
@@ -116,17 +116,6 @@
         "## Before you begin"
       ]
     },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "z__i0w0lCAsW"
-      },
-      "source": [
-        "### Colab Only\n",
-        "Run the following commands for Colab and skip this section if you are using Workbench."
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -135,16 +124,14 @@
       },
       "outputs": [],
       "source": [
+        "! pip3 install --upgrade google-cloud-aiplatform\n",
+        "\n",
+        "# Automatically restart kernel after installs\n",
+        "import IPython\n",
+        "\n",
+        "app = IPython.Application.instance()\n",
+        "app.kernel.do_shutdown(True)\n",
         "if \"google.colab\" in str(get_ipython()):\n",
-        "    # ! pip3 install --upgrade google-cloud-aiplatform\n",
-        "    ! pip3 install --upgrade --quiet git+https://github.com/googleapis/python-aiplatform.git@copybara_525509891 --force-reinstall\n",
-        "\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)\n",
-        "\n",
         "    from google.colab import auth as google_auth\n",
         "\n",
         "    google_auth.authenticate_user()"
@@ -166,6 +153,7 @@
         "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
         "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
         "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
         "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
@@ -191,13 +179,14 @@
         "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
         "\n",
         "# You can choose a region from https://cloud.google.com/about/locations.\n",
-        "# Only regions prefixed by \"us\", or \"europe\" are supported.\n",
+        "# Only regions prefixed by \"us\", \"europe\", or \"asia\" are supported.\n",
         "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
-        "REGION_PREFIX = REGION.split(\"-\")[0]\n",
+        "REGION_PREFIX = REGION.split('-')[0]\n",
         "assert REGION_PREFIX in (\n",
         "    \"us\",\n",
         "    \"europe\",\n",
-        "), f'{REGION} is not supported. It must be prefixed by \"us\" or \"europe\".'\n",
+        "    \"asia\"\n",
+        "), f'{REGION} is not supported. It must be prefixed by \"us\", \"europe\", or \"asia\".'\n",
         "\n",
         "! gcloud config set project $PROJECT_ID\n",
         "\n",
@@ -238,13 +227,7 @@
         "EVALUATION_METRIC = \"AP50\"\n",
         "\n",
         "# Prediction constants.\n",
-        "# You can deploy models with\n",
-        "#   pre-build-dockers: https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers.\n",
-        "#   and optimized tensorflow runtime dockers: https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
-        "# The example in this notebook uses optimized tensorflow runtime dockers.\n",
         "# You can adjust accelerator types and machine types to get faster predictions.\n",
-        "PREDICTION_CONTAINER_URI = f\"{REGION_PREFIX}-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest\"\n",
-        "SERVING_CONTAINER_ARGS = [\"--allow_precompilation\", \"--allow_compression\"]\n",
         "PREDICTION_ACCELERATOR_TYPE = \"NVIDIA_TESLA_T4\"\n",
         "PREDICTION_MACHINE_TYPE = \"n1-standard-4\"\n",
         "DEPLOY_JOB_PREFIX = \"deploy\""
@@ -429,7 +412,7 @@
         "dataset = aiplatform.ImageDataset.create(\n",
         "    display_name=DATASET_PREFIX + \"_salads\",\n",
         "    gcs_source=[DATASET_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.image.bounding_box,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.bounding_box,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -447,8 +430,8 @@
         "### Create and run training pipeline\n",
         "\n",
         "To train an AutoML model, you perform two steps:\n",
-        "1.  create a training pipeline\n",
-        "2.  run the pipeline.\n",
+        "1.  Create a training pipeline.\n",
+        "2.  Run the pipeline.\n",
         "\n",
         "#### Create training pipeline\n",
         "\n",
@@ -459,40 +442,42 @@
         "  - `classification`: An image classification model.\n",
         "  - `object_detection`: An image object detection model.\n",
         "- `model_type`: The type of model for deployment. For image object detection, we current support the following:\n",
-        "  - `SPINENET`: A model that, available in Vertex Model Garden image object detection training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
-        "  - `YOLO`: A model that, available in Vertex Model Garden image object detection training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
+        "  - `SPINENET`: A model that is available in Vertex Model Garden image object detection training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
+        "  - `YOLO`: A model that is available in Vertex Model Garden image object detection training with customizable hyperparameters. Best tailored to be used within Google Cloud, and cannot be exported externally.\n",
         "- `checkpoint_name`: Optional. The field is reserved for Model Garden model training, based on the provided pre-trained model checkpoint.\n",
-        "- `trainer_config`: Optional. The field is usually used together with the Model Garden model training, when passing the customized configs for the trainer.\n",
+        "- `trainer_config`: Optional. The field is usually used together with the Model Garden model training, when passing the customized configs for the trainer. `anchor_size` cannot be used with `YOLO`.\n",
         "\n",
         "  Example with all supported parameters:\n",
-        "\n",
-        "  trainer_config = { \\\n",
-        "    'global_batch_size': '8', \\\n",
-        "    'learning_rate': '0.001', \\\n",
-        "    'optimizer_type': 'sgd', \\\n",
-        "    'optimizer_momentum': '0.9', \\\n",
-        "    'train_steps': '10000', \\\n",
-        "    'accelerator_count': '1', \\\n",
-        "    'anchor_size': '8', \\\n",
+        "```\n",
+        "  trainer_config = {\n",
+        "    'global_batch_size': '8',\n",
+        "    'learning_rate': '0.001',\n",
+        "    'optimizer_type': 'sgd',\n",
+        "    'optimizer_momentum': '0.9',\n",
+        "    'train_steps': '10000',\n",
+        "    'accelerator_count': '1',\n",
+        "    'anchor_size': '8',\n",
         "  }\n",
-        "- `metric_spec`: Dictionary representing metrics to optimize. The dictionary key is the metric_id, which is reported by your training job, with possible values be ('loss', 'AP50') and the dictionary value is the optimization goal of the metric('minimize' or 'maximize').\n",
-        "For example:  metric_spec = {'loss': 'minimize', 'AP50': 'maximize'}\n",
+        "```\n",
+        "- `metric_spec`: Dictionary representing metrics to optimize. The dictionary key is the metric_id, which is reported by your training job, with possible values being ('loss', 'AP50') and the dictionary value is the optimization goal of the metric('minimize' or 'maximize').\n",
+        "For example:  `metric_spec = {'loss': 'minimize', 'AP50': 'maximize'}`\n",
         "- `parameter_spec`:Dictionary representing parameters to optimize. The dictionary key is the `metric_id`, which is passed into your training job as a command line key word argument, and the dictionary value is the parameter\n",
         "specification of the metric. Supported parameter specifications can be found in aiplatform.hyperparameter_tuning.\n",
-        "\n",
+        "```\n",
         "  from google.cloud.aiplatform.aiplatform import hpt as hpt\n",
         "\n",
-        "  parameter_spec = { \\\n",
+        "  parameter_spec = {\n",
         "    'learning_rate': hpt.DoubleParameterSpec(min=1e-7, max=1, scale='linear'), \\\n",
         "  }\n",
+        "```\n",
         "- `search_algorithm`: The search algorithm specified for the Study. Accepts one of the following:\n",
-        "  - `None` - If you do not specify an algorithm, your job uses the default\n",
+        "  - `None`: If you do not specify an algorithm, your job uses the default\n",
         "  Vertex AI algorithm. The default algorithm applies Bayesian optimization\n",
         "  to arrive at the optimal solution with a more effective search over the\n",
         "  parameter space.\n",
-        "  - `grid` - A simple grid search within the feasible space. This option is\n",
+        "  - `grid`: A simple grid search within the feasible space. This option is\n",
         "  particularly useful if you want to specify a quantity of trials that is greater than the number of points in the feasible space. In such cases, if you do not specify a grid search, the Vertex AI default algorithm may generate duplicate suggestions. To use grid search, all parameter specs must be of type `IntegerParameterSpec`, `CategoricalParameterSpec`, or `DiscreteParameterSpec`.\n",
-        "  - `random` - A simple random search within the feasible space.\n",
+        "  - `random`: A simple random search within the feasible space.\n",
         "- `measurement_selection`: This indicates which measurement to use\n",
         "if/when the service automatically selects the final measurement from\n",
         "previously reported intermediate measurements.\n",
@@ -543,16 +528,15 @@
         "    }\n",
         "else:\n",
         "    PARAMETER_SPEC = {\n",
-        "        \"anchor_size\": hpt.DiscreteParameterSpec(values=[2, 4], scale=\"reverse_log\"),\n",
         "        \"learning_rate\": hpt.DiscreteParameterSpec(\n",
         "            values=[0.001, 0.01], scale=\"linear\"\n",
         "        ),\n",
+        "        \"anchor_size\": hpt.DiscreteParameterSpec(values=[2, 4], scale=\"reverse_log\"),\n",
         "    }\n",
         "\n",
         "job = aiplatform.AutoMLImageTrainingJob(\n",
         "    display_name=get_job_name_with_datetime(TRAINING_JOB_PREFIX),\n",
         "    prediction_type=\"object_detection\",\n",
-        "    multi_label=False,\n",
         "    model_type=MODEL_TYPE,\n",
         "    base_model=None,\n",
         "    trainer_config=TRAINER_CONFIG,\n",
@@ -574,7 +558,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -582,7 +566,7 @@
         "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
         "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
         "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
-        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "- `disable_early_stopping`: If `True`, training may be completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
@@ -618,8 +602,8 @@
       },
       "source": [
         "## Test trained models\n",
-        "This section shows how to test with trained models.\n",
-        "1. Deploy models from model registry\n",
+        "This section shows how to test the trained models.\n",
+        "1. Deploy models from Model Registry\n",
         "2. Run online predictions"
       ]
     },
@@ -631,7 +615,7 @@
       },
       "outputs": [],
       "source": [
-        "# @title Deploy model from model registry\n",
+        "# @title Deploy model from Model Registry\n",
         "\n",
         "deploy_model_name = get_job_name_with_datetime(DEPLOY_JOB_PREFIX + \"_\" + OBJECTIVE)\n",
         "print(\"The deployed job name is: \", deploy_model_name)\n",
@@ -660,9 +644,6 @@
       "source": [
         "# @title Run online predictions\n",
         "\n",
-        "# endpoint_id was generated in the section above (`Upload and deploy models`).\n",
-        "endpoint_id = endpoint.name\n",
-        "\n",
         "# test image file path from a GCS bucket\n",
         "test_filepath = \"\"  # @param {type:\"string\"}\n",
         "\n",

notebooks/community/model_garden/model_garden_pytorch_blip2.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_blip_image_captioning.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_blip_vqa.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_clip.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_flan_t5_xxl.ipynb

@@ -1,433 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "7d9bbf86da5e"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2023 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# You may obtain a copy of the License at\n",
-        "#\n",
-        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
-        "#\n",
-        "# Unless required by applicable law or agreed to in writing, software\n",
-        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-        "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "99c1c3fc2ca5"
-      },
-      "source": [
-        "# Vertex AI Model Garden - Fan-T5-XXL\n",
-        "\n",
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_flan_t5_xxl.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_flan_t5_xxl.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_flan_t5_xxl.ipynb\">\n",
-        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
-        "Open in Vertex AI Workbench\n",
-        "    </a>\n",
-        "    (a Python-3 GPU notebook with preinstalled HuggingFace/transformer libraries is recommended)\n",
-        "  </td>\n",
-        "</table>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3de7470326a2"
-      },
-      "source": [
-        "## Overview\n",
-        "\n",
-        "This notebook demonstrates finetuning [google/flan-t5-xxl](https://huggingface.co/google/flan-t5-xxl) with [cnn_dailymail](https://huggingface.co/datasets/cnn_dailymail) dataset and deploying it on Vertex AI for online prediction.\n",
-        "\n",
-        "### Objective\n",
-        "\n",
-        "- Finetune the flan-t5-xxl model with [Vertex AI custom training](https://cloud.google.com/vertex-ai/docs/training/overview).\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 summarization task.\n",
-        "\n",
-        "### Costs\n",
-        "\n",
-        "This tutorial uses billable components of Google Cloud:\n",
-        "\n",
-        "* Vertex AI\n",
-        "* Cloud Storage\n",
-        "\n",
-        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "264c07757582"
-      },
-      "source": [
-        "## Setup environment\n",
-        "\n",
-        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "d73ffa0c0b83"
-      },
-      "source": [
-        "### Colab only"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "2707b02ef5df"
-      },
-      "outputs": [],
-      "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
-        "\n",
-        "google_auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "bb7adab99e41"
-      },
-      "source": [
-        "### Setup Google Cloud project\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
-        "\n",
-        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
-        "\n",
-        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "6c460088b873"
-      },
-      "source": [
-        "Fill following variables for experiments environment:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "855d6b96f291"
-      },
-      "outputs": [],
-      "source": [
-        "# Cloud project id.\n",
-        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# The region you want to launch jobs in.\n",
-        "REGION = \"us-central1\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
-        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# The service account for deploying fine tuned model.\n",
-        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e828eb320337"
-      },
-      "source": [
-        "### Initialize Vertex AI 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": "12cd25839741"
-      },
-      "outputs": [],
-      "source": [
-        "from google.cloud import aiplatform\n",
-        "\n",
-        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2cc825514deb"
-      },
-      "source": [
-        "### Define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b42bd4fa2b2d"
-      },
-      "outputs": [],
-      "source": [
-        "# The pre-built training docker image. It contains training scripts and models.\n",
-        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-flan-t5-train\"\n",
-        "\n",
-        "# The pre-built serving docker image. It contains serving scripts and models.\n",
-        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-transformers-serve\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0c250872074f"
-      },
-      "source": [
-        "### Define common functions"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "354da31189dc"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "from datetime import datetime\n",
-        "\n",
-        "\n",
-        "# Create a job name string with a prefix.\n",
-        "def create_job_name(prefix):\n",
-        "    user = os.environ.get(\"USER\")\n",
-        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
-        "    job_name = f\"{prefix}-{user}-{now}\"\n",
-        "    return job_name\n",
-        "\n",
-        "\n",
-        "# Deploy a model to Vertex AI endpoint.\n",
-        "def deploy_model(model_id, task):\n",
-        "    model_name = \"flan-t5-xxl\"\n",
-        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-{task}-endpoint\")\n",
-        "    serving_env = {\n",
-        "        \"MODEL_ID\": model_id,\n",
-        "        \"TASK\": task,\n",
-        "    }\n",
-        "    model = aiplatform.Model.upload(\n",
-        "        display_name=model_name,\n",
-        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
-        "        serving_container_ports=[7080],\n",
-        "        serving_container_predict_route=\"/predictions/transformers_serving\",\n",
-        "        serving_container_health_route=\"/ping\",\n",
-        "        serving_container_environment_variables=serving_env,\n",
-        "    )\n",
-        "    model.deploy(\n",
-        "        endpoint=endpoint,\n",
-        "        machine_type=\"a2-highgpu-1g\",\n",
-        "        accelerator_type=\"NVIDIA_TESLA_A100\",\n",
-        "        accelerator_count=1,\n",
-        "        deploy_request_timeout=1800,\n",
-        "        service_account=SERVICE_ACCOUNT,\n",
-        "    )\n",
-        "    return model, endpoint"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e70e3519ff8b"
-      },
-      "source": [
-        "## Fine tune model\n",
-        "\n",
-        "This section fine tunes the Flan-t5-XXL model with [cnn_dailymail](https://huggingface.co/datasets/cnn_dailymail) dataset for the text summarization task.\n",
-        "\n",
-        "One `a2-highgpu-8g` machine with 8 `NVIDIA_TESLA_A100` is required to run the fine-tuning job. The fine-tuning job takes about 11.5 hours to complete.\n",
-        "\n",
-        "The fine-tuned model will be saved after the job finishs and it can then be loaded for inference."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "65467b361315"
-      },
-      "outputs": [],
-      "source": [
-        "machine_type = \"a2-highgpu-8g\"\n",
-        "gpu_type = \"NVIDIA_TESLA_A100\"\n",
-        "num_gpus = 8\n",
-        "\n",
-        "job_name = create_job_name(\"flan-t5-xxl\")\n",
-        "output_dir = f\"/gcs/{GCS_BUCKET}/flan-t5-xxl\"\n",
-        "\n",
-        "job = aiplatform.CustomContainerTrainingJob(\n",
-        "    display_name=job_name, container_uri=TRAIN_DOCKER_URI, command=[\"torchrun\"]\n",
-        ")\n",
-        "\n",
-        "job.run(\n",
-        "    args=[\n",
-        "        \"--nnodes=1\",\n",
-        "        \"--node_rank=0\",\n",
-        "        f\"--nproc-per-node={num_gpus}\",\n",
-        "        \"train.py\",\n",
-        "        f\"--output_dir={output_dir}\",\n",
-        "        \"--bf16=True\",\n",
-        "        \"--model_id=google/flan-t5-xxl\",\n",
-        "        \"--data_path=cnn_dailymail\",\n",
-        "        \"--data_name=3.0.0\",\n",
-        "        \"--gradient_checkpointing=True\",\n",
-        "        \"--train_epochs=3\",\n",
-        "        \"--train_batch_size=8\",\n",
-        "        \"--eval_batch_size=8\",\n",
-        "        \"--lr=1e-4\",\n",
-        "        \"--checkpoint_strategy=no\",\n",
-        "    ],\n",
-        "    boot_disk_size_gb=600,\n",
-        "    replica_count=1,\n",
-        "    machine_type=machine_type,\n",
-        "    accelerator_type=gpu_type,\n",
-        "    accelerator_count=num_gpus,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "bf7f82732e61"
-      },
-      "source": [
-        "## Upload and Deploy models\n",
-        "\n",
-        "This section uploads the fine-tuned model to Model Registry and deploys it on the Endpoint.\n",
-        "\n",
-        "One `a2-highgpu-1g` machine with 1 `NVIDIA_TESLA_A100` is required to deploy Flan-t5-XXL model.\n",
-        "\n",
-        "The model deployment step will take ~20 minutes to complete."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "bf55e38815dc"
-      },
-      "outputs": [],
-      "source": [
-        "# Set the model_id to \"google/flan-t5-xxl\" to load the OSS pre-trained model.\n",
-        "model, endpoint = deploy_model(\n",
-        "    model_id=f\"gs://{GCS_BUCKET}/flan-t5-xxl/release\", task=\"summarization\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "80b3fd2ace09"
-      },
-      "source": [
-        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4ab04da3ec9a"
-      },
-      "outputs": [],
-      "source": [
-        "text = \"LONDON, England (Reuters) -- Harry Potter star Daniel Radcliffe gains access to a reported £20 million ($41.1 million) fortune as he turns 18 on Monday, but he insists the money won't cast a spell on him. Daniel Radcliffe as Harry Potter in 'Harry Potter and the Order of the Phoenix' To the disappointment of gossip columnists around the world, the young actor says he has no plans to fritter his cash away on fast cars, drink and celebrity parties. 'I don't plan to be one of those people who, as soon as they turn 18, suddenly buy themselves a massive sports car collection or something similar,' he told an Australian interviewer earlier this month. 'I don't think I'll be particularly extravagant. 'The things I like buying are things that cost about 10 pounds -- books and CDs and DVDs.' At 18, Radcliffe will be able to gamble in a casino, buy a drink in a pub or see the horror film 'Hostel: Part II,' currently six places below his number one movie on the UK box office chart. Details of how he'll mark his landmark birthday are under wraps. His agent and publicist had no comment on his plans. 'I'll definitely have some sort of party,' he said in an interview. 'Hopefully none of you will be reading about it.' Radcliffe's earnings from the first five Potter films have been held in a trust fund which he has not been able to touch. Despite his growing fame and riches, the actor says he is keeping his feet firmly on the ground. 'People are always looking to say 'kid star goes off the rails,'' he told reporters last month. 'But I try very hard not to go that way because it would be too easy for them.' His latest outing as the boy wizard in 'Harry Potter and the Order of the Phoenix' is breaking records on both sides of the Atlantic and he will reprise the role in the last two films. Watch I-Reporter give her review of Potter's latest » . There is life beyond Potter, however. The Londoner has filmed a TV movie called 'My Boy Jack,' about author Rudyard Kipling and his son, due for release later this year. He will also appear in 'December Boys,' an Australian film about four boys who escape an orphanage. Earlier this year, he made his stage debut playing a tortured teenager in Peter Shaffer's 'Equus.' Meanwhile, he is braced for even closer media scrutiny now that he's legally an adult: 'I just think I'm going to be more sort of fair game,' he told Reuters. E-mail to a friend . Copyright 2007 Reuters. All rights reserved.This material may not be published, broadcast, rewritten, or redistributed.\"\n",
-        "instances = [\n",
-        "    {\n",
-        "        \"text\": text,\n",
-        "    }\n",
-        "]\n",
-        "response = endpoint.predict(instances=instances).predictions\n",
-        "print(response)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "af21a3cff1e0"
-      },
-      "source": [
-        "Clean up resources:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "911406c1561e"
-      },
-      "outputs": [],
-      "source": [
-        "# Undeploy model and delete endpoint.\n",
-        "endpoint.delete(force=True)\n",
-        "\n",
-        "# Delete models.\n",
-        "model.delete()"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "model_garden_pytorch_flan_t5_xxl.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/model_garden/model_garden_pytorch_instructpix2pix.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_layoutml_document_qa.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_owlvit.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_peft.ipynb

@@ -0,0 +1,954 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "99c1c3fc2ca5"
+      },
+      "source": [
+        "# Vertex AI Model Garden - PEFT\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_peft.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_peft.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_peft.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> (A Python-3 CPU notebook is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3de7470326a2"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates finetuning models with performance efficient finetuning libaries ([PEFT](https://github.com/huggingface/peft)), and running inferences with containers in Vertex AI. There are various models supported in [PEFT](https://github.com/huggingface/peft). This notebook shows examples with some models, such as OpenLLaMA, Falcon-instruct, BERT, RoBERTa-large, and XLM-RoBERTa-large, etc.\n",
+        "\n",
+        "### Objective\n",
+        "\n",
+        "- Finetune causal language models with PEFT and run inferences with Vertex AI, supporting\n",
+        "\n",
+        "| Models | LoRA |\n",
+        "| :- | :- |\n",
+        "| [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) | Y |\n",
+        "| [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b) | Y |\n",
+        "| [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b) | Y |\n",
+        "\n",
+        "- Finetune instruct models with PEFT and run inferences with Vertex AI, supporting\n",
+        "\n",
+        "| Models | LoRA |\n",
+        "| :- | :- |\n",
+        "| [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) | Y |\n",
+        "| [tiiuae/falcon-40b-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) | Y |\n",
+        "\n",
+        "\n",
+        "- Finetune sequence classification models with PEFT and run inferences with Vertex AI, supporting\n",
+        "\n",
+        "| Models | LoRA |\n",
+        "| :- | :- |\n",
+        "| [bert-base-uncase](https://huggingface.co/bert-base-uncased) | Y |\n",
+        "| [RoBERTa-large](https://huggingface.co/roberta-large) | Y |\n",
+        "| [XLM-RoBERTa-large](https://huggingface.co/xlm-roberta-large) | Y |\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ioensNKM8ned"
+      },
+      "source": [
+        "### Colab only\n",
+        "Run the following commands for Colab and skip this section if you are using Workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "\n",
+        "if \"google.colab\" in sys.modules:\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()\n",
+        "    # Install gdown for downloading example training images.\n",
+        "    ! pip3 install gdown\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bb7adab99e41"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c460088b873"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "855d6b96f291"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output.\n",
+        "BUCKET_URI = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "! gcloud config set project $PROJECT_ID\n",
+        "\n",
+        "import os\n",
+        "\n",
+        "STAGING_BUCKET = os.path.join(BUCKET_URI, \"temporal\")\n",
+        "EXPERIMENT_BUCKET = os.path.join(BUCKET_URI, \"peft\")\n",
+        "DATA_BUCKET = os.path.join(EXPERIMENT_BUCKET, \"data\")\n",
+        "MODEL_BUCKET = os.path.join(EXPERIMENT_BUCKET, \"model\")\n",
+        "\n",
+        "# The service account looks like:\n",
+        "# '@.iam.gserviceaccount.com'\n",
+        "# Please go to https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console\n",
+        "# and create service account with `Vertex AI User` and `Storage Object Admin` roles.\n",
+        "# The service account for deploying fine tuned model.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e828eb320337"
+      },
+      "source": [
+        "### Initialize Vertex AI API"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "12cd25839741"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=STAGING_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2cc825514deb"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b42bd4fa2b2d"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built training and serving docker images.\n",
+        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-peft-train\"\n",
+        "PREDICTION_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-peft-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c250872074f"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "354da31189dc"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from datetime import datetime\n",
+        "\n",
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "\n",
+        "def get_job_name_with_datetime(prefix: str):\n",
+        "    \"\"\"Gets the job name with date time when triggering training or deployment\n",
+        "    jobs in Vertex AI.\n",
+        "    \"\"\"\n",
+        "    return prefix + datetime.now().strftime(\"_%Y%m%d_%H%M%S\")\n",
+        "\n",
+        "\n",
+        "def deploy_model(\n",
+        "    model_name,\n",
+        "    base_model_id,\n",
+        "    finetuned_lora_model_path,\n",
+        "    service_account,\n",
+        "    task,\n",
+        "    machine_type=\"n1-standard-8\",\n",
+        "    accelerator_type=\"NVIDIA_TESLA_V100\",\n",
+        "):\n",
+        "    \"\"\"Deploys trained models into Vertex AI.\"\"\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"BASE_MODEL_ID\": base_model_id,\n",
+        "        \"FINETUNED_LORA_MODEL_PATH\": finetuned_lora_model_path,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=PREDICTION_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/peft_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=machine_type,\n",
+        "        accelerator_type=accelerator_type,\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "        service_account=service_account,\n",
+        "    )\n",
+        "    return model, endpoint"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e70e3519ff8b"
+      },
+      "source": [
+        "## Casual Language Modeling + PEFT\n",
+        "\n",
+        "This section demonstrates how to finetune OpenLLaMA with PEFT LoRA, including [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b), [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b), and [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "iWGwJHqI7LMs"
+      },
+      "source": [
+        "### Finetune with LoRA"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5qCrm_kJH5cz"
+      },
+      "source": [
+        "Set the base model id."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "N3UBLiYrM3sU"
+      },
+      "outputs": [],
+      "source": [
+        "base_model_id = \"openlm-research/open_llama_3b\"  # @param [\"openlm-research/open_llama_3b\", \"openlm-research/open_llama_7b\", \"openlm-research/open_llama_13b\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KKEYoRfiHDVv"
+      },
+      "source": [
+        "Use the Vertex AI SDK to create and run the custom training jobs with Vertex AI Model Garden training images.\n",
+        "\n",
+        "This example uses the dataset [Abirate/english_quotes](https://huggingface.co/datasets/Abirate/english_quotes).\n",
+        "\n",
+        "In order to make the finetunig efficiently, we enabled quantization (8bits) when loading pretrained models for finetuning LoRA models. The peak GPU memory usages are ~7G, ~10G and ~16G for finetuning LoRA models for [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b), [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b), and [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b) separately with default training parameters and the example dataset. In theory, open_llama_3b and open_llama_7b can be finetuned on 1 V100, and open_llama_13b can be finetuned on 1 A100 (40G). We choose to use 1 A100 (40G) by default to support all these models in this notebook for simplicity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65467b361315"
+      },
+      "outputs": [],
+      "source": [
+        "dataset_name = \"Abirate/english_quotes\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "# machine_type = \"n1-standard-8\"\n",
+        "# accelerator_type = \"NVIDIA_TESLA_V100\"\n",
+        "machine_type = \"a2-highgpu-1g\"\n",
+        "accelerator_type = \"NVIDIA_TESLA_A100\"\n",
+        "replica_count = 1\n",
+        "accelerator_count = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = get_job_name_with_datetime(\"openllama-lora-train\")\n",
+        "train_job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "output_dir = os.path.join(MODEL_BUCKET, job_name)\n",
+        "output_dir_gcsfuse = output_dir.replace(\"gs://\", \"/gcs/\")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "train_job.run(\n",
+        "    args=[\n",
+        "        \"--task=causal-language-modeling-lora\",\n",
+        "        f\"--pretrained_model_id={base_model_id}\",\n",
+        "        f\"--dataset_name={dataset_name}\",\n",
+        "        f\"--output_dir={output_dir_gcsfuse}\",\n",
+        "        \"--lora_rank=16\",\n",
+        "        \"--lora_alpha=32\",\n",
+        "        \"--lora_dropout=0.05\",\n",
+        "        \"--warmup_steps=10\",\n",
+        "        \"--max_steps=10\",\n",
+        "        \"--learning_rate=2e-4\",\n",
+        "    ],\n",
+        "    replica_count=replica_count,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=accelerator_type,\n",
+        "    accelerator_count=accelerator_count,\n",
+        "    boot_disk_size_gb=500,\n",
+        ")\n",
+        "\n",
+        "print(\"Trained models were saved in: \", output_dir)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "jqmCtkGnhDmp"
+      },
+      "source": [
+        "### Run inferences with serving images\n",
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "The peak GPU memory usages for [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b), [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b), and [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b) with LoRA weights are ~5.3G, ~8.7G and ~15.2G separately with the default settings. We use V100 in deployments for simplicity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bf55e38815dc"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_name=get_job_name_with_datetime(prefix=\"openllama-peft-serve\"),\n",
+        "    base_model_id=base_model_id,\n",
+        "    finetuned_lora_model_path=output_dir,\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
+        "    task=\"causal-language-modeling-lora\",\n",
+        ")\n",
+        "print(\"endpoint_name:\", endpoint.name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint.\n",
+        "\n",
+        "Once deployment succeeds, you can send requests to the endpoint with text prompts."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4ab04da3ec9a"
+      },
+      "outputs": [],
+      "source": [
+        "# # Loads an existing endpoint as below.\n",
+        "# endpoint_name = endpoint.name\n",
+        "# aip_endpoint_name = (\n",
+        "#     f\"projects/{PROJECT_ID}/locations/{REGION}/endpoints/{endpoint_name}\"\n",
+        "# )\n",
+        "# endpoint = aiplatform.Endpoint(aip_endpoint_name)\n",
+        "instances = [\n",
+        "    {\"prompt\": \"Hi, Google.\"},\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "\n",
+        "for prediction in response.predictions[0]:\n",
+        "    print(prediction[\"generated_text\"])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "af21a3cff1e0"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "911406c1561e"
+      },
+      "outputs": [],
+      "source": [
+        "# Delete custom train jobs.\n",
+        "train_job.delete()\n",
+        "\n",
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "W2USaHtQbE-l"
+      },
+      "source": [
+        "## Instruct + PEFT\n",
+        "\n",
+        "This section demonstrates how to finetune Falcon-instruct with PEFT LoRA, including [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct), and [tiiuae/falcon-40b-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "PwluMqvYbLu9"
+      },
+      "source": [
+        "### Finetune with LoRA"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ap1pQd-ckAAb"
+      },
+      "source": [
+        "Set the base model id."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vVTfG2bpbR90"
+      },
+      "outputs": [],
+      "source": [
+        "base_model_id = \"tiiuae/falcon-7b-instruct\"  # @param [\"tiiuae/falcon-7b-instruct\", \"tiiuae/falcon-40b-instruct\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "iJe_us8mkZEV"
+      },
+      "source": [
+        "Use the Vertex AI SDK to create and run the custom training jobs with Vertex AI Model Garden training images.\n",
+        "\n",
+        "This example uses the dataset [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco).\n",
+        "\n",
+        "The peak GPU memory usages are ~11G and ~34G for finetuning LoRA models for [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct), and [tiiuae/falcon-40b-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) separately with default training parameters and the example dataset. In theory, falcon-7b-instruct can be finetuned on 1 P100/V100, and falcon-40b-instruct can be finetuned on 1 A100 (40G). We choose to use 1 A100 (40G) by default to support all these models in this notebook for simplicity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-i4M7mWPbV8s"
+      },
+      "outputs": [],
+      "source": [
+        "dataset_name = \"timdettmers/openassistant-guanaco\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "machine_type = \"a2-highgpu-1g\"\n",
+        "accelerator_type = \"NVIDIA_TESLA_A100\"\n",
+        "replica_count = 1\n",
+        "accelerator_count = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = get_job_name_with_datetime(\"falcon-instruct-lora-train\")\n",
+        "train_job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "output_dir = os.path.join(MODEL_BUCKET, job_name)\n",
+        "output_dir_gcsfuse = output_dir.replace(\"gs://\", \"/gcs/\")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "max_steps = 10\n",
+        "train_job.run(\n",
+        "    args=[\n",
+        "        \"--task=instruct-lora\",\n",
+        "        f\"--pretrained_model_id={base_model_id}\",\n",
+        "        f\"--dataset_name={dataset_name}\",\n",
+        "        f\"--output_dir={output_dir_gcsfuse}\",\n",
+        "        \"--lora_rank=64\",\n",
+        "        \"--lora_alpha=16\",\n",
+        "        \"--lora_dropout=0.1\",\n",
+        "        \"--warmup_ratio=0.03\",\n",
+        "        f\"--max_steps={max_steps}\",\n",
+        "        \"--max_seq_length=512\",\n",
+        "        \"--learning_rate=2e-4\",\n",
+        "    ],\n",
+        "    replica_count=replica_count,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=accelerator_type,\n",
+        "    accelerator_count=accelerator_count,\n",
+        "    boot_disk_size_gb=500,\n",
+        ")\n",
+        "\n",
+        "print(\"Trained models were saved in: \", output_dir)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "oCgivsdllZ1x"
+      },
+      "source": [
+        "### Run inferences with serving images"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_lNIFvielcyV"
+      },
+      "source": [
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "The peak GPU memory usages for [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct), and [tiiuae/falcon-40b-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) with LoRA weights are ~15.5G and ~38.2G separately with the default settings. We use V100 in deployments for simplicity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "inrBXzoxk53t"
+      },
+      "outputs": [],
+      "source": [
+        "# # If deploy finetuned falcon-40b-instruct models, please set\n",
+        "# machine_type = \"a2-highgpu-1g\",\n",
+        "# accelerator_type = \"NVIDIA_TESLA_A100\"\n",
+        "machine_type = \"n1-standard-8\",\n",
+        "accelerator_type = \"NVIDIA_TESLA_V100\"\n",
+        "\n",
+        "accelerator_type =\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_name=get_job_name_with_datetime(prefix=\"falcon-peft-serve\"),\n",
+        "    base_model_id=base_model_id,\n",
+        "    finetuned_lora_model_path=os.path.join(output_dir, \"checkpoint-\"+str(max_steps)),\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
+        "    task=\"instruct-lora\",\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=accelerator_type,\n",
+        ")\n",
+        "print(\"endpoint_name: \", endpoint.name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_dmO3XooliAs"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed after the above model deployment step succeeds and before you run the next step below. Otherwise you might see a ServiceUnavailable: 503 502:Bad Gateway error when you send requests to the endpoint.\n",
+        "\n",
+        "Once deployment succeeds, you can send requests to the endpoint with text prompts.\n",
+        "\n",
+        "Example:\n",
+        "\n",
+        "```\n",
+        "Human: What is a car?\n",
+        "Assistant:  A car, or a motor car, is a road-connected human-transportation system used to move people or goods from one place to another. The term also encompasses a wide range of vehicles, including motorboats, trains, and aircrafts. Cars typically have four wheels, a cabin for passengers, and an engine or motor. They have been around since the early 19th century and are now one of the most popular forms of transportation, used for daily commuting, shopping, and other purposes.\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "JrKsrffGl14T"
+      },
+      "outputs": [],
+      "source": [
+        "# # Loads an existing endpoint as below.\n",
+        "# endpoint_name = endpoint.name\n",
+        "# aip_endpoint_name = (\n",
+        "#     f\"projects/{PROJECT_ID}/locations/{REGION}/endpoints/{endpoint_name}\"\n",
+        "# )\n",
+        "# endpoint = aiplatform.Endpoint(aip_endpoint_name)\n",
+        "instances = [\n",
+        "    {\"prompt\": \"What is a car?\"},\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "\n",
+        "for prediction in response.predictions[0]:\n",
+        "    print(prediction[\"generated_text\"])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "uk-t69nFl9rr"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "CcIX2WAJmAI7"
+      },
+      "outputs": [],
+      "source": [
+        "# Delete custom train jobs.\n",
+        "train_job.delete()\n",
+        "\n",
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "og_s64QVmJDb"
+      },
+      "source": [
+        "## Sequence Classification + PEFT\n",
+        "\n",
+        "This section demonstrates how to finetune sequence classification models with PEFT LoRA, including [bert-base-uncased](https://huggingface.co/bert-base-uncased), [RoBERTa-large](https://huggingface.co/roberta-large), and [XLM-RoBERTa-large](https://huggingface.co/xlm-roberta-large)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "QqJcvCb2mn8l"
+      },
+      "source": [
+        "### Finetune with PEFT"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c0E7dfqloeBB"
+      },
+      "source": [
+        "Set the base model id."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "eru79ot6mtNG"
+      },
+      "outputs": [],
+      "source": [
+        "base_model_id = \"xlm-roberta-large\"  # @param [\"bert-base-uncased\", \"roberta-large\", \"xlm-roberta-large\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "y9n-qheaotS9"
+      },
+      "source": [
+        "Use the Vertex AI SDK to create and run the custom training jobs with Vertex AI Model Garden training images.\n",
+        "\n",
+        "This example uses the dataset [glue](https://huggingface.co/datasets/glue).\n",
+        "\n",
+        "The peak GPU memory usages are ~8.8G and ~15G for finetuning LoRA models for [RoBERTa-large](https://huggingface.co/roberta-large), and [XLM-RoBERTa-large](https://huggingface.co/xlm-roberta-large) separately with default training parameters and the example dataset. In theory, RoBERTa-large can be finetuned on 1 P100/V100, and XLM-RoBERTa-large can be finetuned on 1 A100 (40G). We choose to use 1 A100 (40G) by default to support all these models in this notebook for simplicity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OHeSYEKinfP3"
+      },
+      "outputs": [],
+      "source": [
+        "dataset_name = \"glue\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "# # Please switch to A100 or other powerful machines if you run out of memory.\n",
+        "# machine_type = \"a2-highgpu-1g\"\n",
+        "# accelerator_type = \"NVIDIA_TESLA_A100\"\n",
+        "machine_type = \"n1-standard-8\"\n",
+        "accelerator_type = \"NVIDIA_TESLA_V100\"\n",
+        "replica_count = 1\n",
+        "accelerator_count = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = get_job_name_with_datetime(os.path.basename(base_model_id) + \"-lora-train\")\n",
+        "train_job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "output_dir = os.path.join(MODEL_BUCKET, job_name)\n",
+        "output_dir_gcsfuse = output_dir.replace(\"gs://\", \"/gcs/\")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "train_job.run(\n",
+        "    args=[\n",
+        "        \"--task=sequence-classification-lora\",\n",
+        "        f\"--pretrained_model_id={base_model_id}\",\n",
+        "        f\"--dataset_name={dataset_name}\",\n",
+        "        f\"--output_dir={output_dir_gcsfuse}\",\n",
+        "        \"--lora_rank=8\",\n",
+        "        \"--lora_alpha=16\",\n",
+        "        \"--lora_dropout=0.1\",\n",
+        "        \"--num_epochs=20\",\n",
+        "        \"--batch_size=32\",\n",
+        "        \"--learning_rate=3e-4\",\n",
+        "    ],\n",
+        "    replica_count=replica_count,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=accelerator_type,\n",
+        "    accelerator_count=accelerator_count,\n",
+        "    boot_disk_size_gb=500,\n",
+        ")\n",
+        "\n",
+        "print(\"Trained models were saved in: \", output_dir)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kJuHaBCqoacg"
+      },
+      "source": [
+        "### Run inferences with serving images"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "jw1GFXydoft0"
+      },
+      "source": [
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete.\n",
+        "\n",
+        "The peak GPU memory usages for [RoBERTa-large](https://huggingface.co/roberta-large), and [XLM-RoBERTa-large](https://huggingface.co/xlm-roberta-large) with LoRA weights are ~2G and ~2.4G separately with the default settings. We use V100 in deployments for simplicity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "A5j0a3AZoj3h"
+      },
+      "outputs": [],
+      "source": [
+        "model, endpoint = deploy_model(\n",
+        "    model_name=get_job_name_with_datetime(prefix=\"sequence-classification-peft-serve\"),\n",
+        "    base_model_id=base_model_id,\n",
+        "    finetuned_lora_model_path=output_dir,\n",
+        "    service_account=SERVICE_ACCOUNT,\n",
+        "    task=\"sequence-classification-lora\",\n",
+        ")\n",
+        "print(\"endpoint_name:\", endpoint.name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6dR3-Hc7oqu-"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed after the above model deployment step succeeds and before you run the next step below. Otherwise you might see a ServiceUnavailable: 503 502:Bad Gateway error when you send requests to the endpoint.\n",
+        "\n",
+        "Once deployment succeeds, you can send requests to the endpoint with text prompts."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xAmULPegoyXl"
+      },
+      "outputs": [],
+      "source": [
+        "# # Loads an existing endpoint as below.\n",
+        "# endpoint_name = endpoint.name\n",
+        "# aip_endpoint_name = (\n",
+        "#     f\"projects/{PROJECT_ID}/locations/{REGION}/endpoints/{endpoint_name}\"\n",
+        "# )\n",
+        "# endpoint = aiplatform.Endpoint(aip_endpoint_name)\n",
+        "instances = [\n",
+        "    {\"prompt\": \"The cat sat on the mat.\"},\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "labels = [int(item) for item in response.predictions]\n",
+        "print(labels)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1Vg_b46Jo6C1"
+      },
+      "source": [
+        "### Clean up resources"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vNiTDL_VpAlp"
+      },
+      "outputs": [],
+      "source": [
+        "# Delete custom train jobs.\n",
+        "train_job.delete()\n",
+        "\n",
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "model_garden_pytorch_peft.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_sam.ipynb

@@ -263,6 +263,7 @@
         "import matplotlib.patches as patches\n",
         "import matplotlib.pyplot as plt\n",
         "import numpy as np\n",
+        "import pycocotools.mask as mask_util\n",
         "import requests\n",
         "from PIL import Image\n",
         "\n",

notebooks/community/model_garden/model_garden_pytorch_stable_diffusion.ipynb

@@ -24,6 +24,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "99c1c3fc2ca5"
@@ -54,6 +55,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "3de7470326a2"
@@ -82,6 +84,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "264c07757582"
@@ -93,6 +96,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "ioensNKM8ned"
@@ -102,6 +106,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "d73ffa0c0b83"
@@ -145,6 +150,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "fb671e75ca7b"
@@ -161,6 +167,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "bb7adab99e41"
@@ -180,6 +187,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6c460088b873"
@@ -210,6 +218,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "e828eb320337"
@@ -232,6 +241,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "2cc825514deb"
@@ -256,6 +266,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "0c250872074f"
@@ -364,6 +375,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "e8a42fa49305"
@@ -373,6 +385,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "1d5ebc91c786"
@@ -398,7 +411,7 @@
         "\n",
         "prompt = \"a photo of an astronaut riding a horse on mars\"\n",
         "\n",
-        "results = pipe(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5)\n",
+        "results = pipe(prompt=prompt, guidance_scale=7.5)\n",
         "images = results.images\n",
         "nsfw_detects = results.nsfw_content_detected\n",
         "display(images[0])\n",
@@ -406,6 +419,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "5aed5ed7b6f6"
@@ -448,6 +462,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "e70e3519ff8b"
@@ -457,6 +472,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "0dc65d8f0689"
@@ -486,6 +502,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "969cfeb79317"
@@ -555,6 +572,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "bf7f82732e61"
@@ -564,6 +582,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "1cc26e68d7b0"
@@ -575,6 +594,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "cd7b56421392"
@@ -584,6 +604,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6d331b1ea337"
@@ -611,6 +632,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "80b3fd2ace09"
@@ -639,6 +661,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "af21a3cff1e0"
@@ -663,6 +686,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "c1e51f764a60"
@@ -672,6 +696,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "fa686a54047c"
@@ -695,6 +720,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "SsjYFLvNymc0"
@@ -727,6 +753,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "ed3795d474b9"

notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_2_1.ipynb

@@ -0,0 +1,770 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7d9bbf86da5e"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2023 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "99c1c3fc2ca5"
+      },
+      "source": [
+        "# Vertex AI Model Garden - Stable Diffusion V2.1\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_2_1.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_2_1.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_2_1.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "    (a Python-3 GPU notebook with preinstalled HuggingFace/transformer libraries is recommended)\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3de7470326a2"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook demonstrates running local inference for [stabilityai/stable-diffusion-2-1](https://huggingface.co/stabilityai/stable-diffusion-2-1) on either [Colab](https://colab.research.google.com) or [Vertex AI Workbench](https://cloud.google.com/vertex-ai-workbench). This notebook also demonstrates finetuning stabilityai/stable-diffusion-2-1 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 stabilityai/stable-diffusion-2-1 model with [Dreambooth](https://huggingface.co/docs/diffusers/training/dreambooth).\n",
+        "- Upload the model to [Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
+        "- Deploy the model to a [Vertex AI Endpoint resource](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
+        "- Run online predictions for text-to-image and text-guided-image-to-image.\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264c07757582"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "**NOTE**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ioensNKM8ned"
+      },
+      "source": [
+        "### Setup notebook"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d73ffa0c0b83"
+      },
+      "source": [
+        "#### Colab only\n",
+        "Run the following commands for Colab and skip this section if you are using Workbench."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2707b02ef5df"
+      },
+      "outputs": [],
+      "source": [
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
+        "\n",
+        "    google_auth.authenticate_user()\n",
+        "    ! pip3 install --upgrade pip\n",
+        "    ! pip3 install torchvision==0.14.1\n",
+        "    ! pip3 install transformers==4.27.1\n",
+        "    ! pip3 install diffusers==0.15.1\n",
+        "    ! pip3 install datasets==2.9.0\n",
+        "    ! pip3 install accelerate==0.18.0\n",
+        "    ! pip3 install triton==2.0.0.dev20221120\n",
+        "    ! pip3 install xformers==0.0.16\n",
+        "    # Install gdown for downloading example training images.\n",
+        "    ! pip3 install gdown\n",
+        "    # Remove wrong cublas version.\n",
+        "    ! pip3 uninstall nvidia_cublas_cu11 --yes\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb671e75ca7b"
+      },
+      "source": [
+        "#### Workbench only\n",
+        "1.   Follow [this link](https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/model_garden/model_garden_pytorch_stable_diffusion_inpainting.ipynb) to deploy the notebook to a Vertex AI Workbench Instance.\n",
+        "2.   Select `Create a new Notebook`.\n",
+        "3.   Click `Advanced Options`.\n",
+        "4.   In the **Environment** tab, select `Debian 10` for **Operating System** and select `Custom Container` for **Environment**.\n",
+        "5.   Set `Docker container image` to `us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/transformers-notebook`.\n",
+        "6.   Under **Machine configuration**, select 1 `T4` GPU and select `Install NVIDIA GPU driver automatically for me`.\n",
+        "7.   Click `Create` to create the Vertex AI Workbench instance."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bb7adab99e41"
+      },
+      "source": [
+        "### Setup Google Cloud project\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs.\n",
+        "\n",
+        "1. [Create a service account](https://cloud.google.com/iam/docs/service-accounts-create#iam-service-accounts-create-console) with `Vertex AI User` and `Storage Object Admin` roles for deploying fine tuned model to Vertex AI endpoint."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c460088b873"
+      },
+      "source": [
+        "Fill following variables for experiments environment:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "855d6b96f291"
+      },
+      "outputs": [],
+      "source": [
+        "# Cloud project id.\n",
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The region you want to launch jobs in.\n",
+        "REGION = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The Cloud Storage bucket for storing experiments output. Fill it without the 'gs://' prefix.\n",
+        "GCS_BUCKET = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# The service account for deploying fine tuned model.\n",
+        "SERVICE_ACCOUNT = \"\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e828eb320337"
+      },
+      "source": [
+        "Initialize Vertex-AI API:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "12cd25839741"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=GCS_BUCKET)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2cc825514deb"
+      },
+      "source": [
+        "### Define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b42bd4fa2b2d"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-built training docker image. It contains training scripts and models.\n",
+        "TRAIN_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-train:latest\"\n",
+        "\n",
+        "# The pre-built serving docker image. It contains serving scripts and models.\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai-restricted/vertex-vision-model-garden-dockers/pytorch-diffusers-serve\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c250872074f"
+      },
+      "source": [
+        "### Define common functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "354da31189dc"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import glob\n",
+        "import os\n",
+        "from datetime import datetime\n",
+        "from io import BytesIO\n",
+        "\n",
+        "import requests\n",
+        "from google.cloud import aiplatform, storage\n",
+        "from PIL import Image\n",
+        "\n",
+        "\n",
+        "def create_job_name(prefix):\n",
+        "    user = os.environ.get(\"USER\")\n",
+        "    now = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
+        "    job_name = f\"{prefix}-{user}-{now}\"\n",
+        "    return job_name\n",
+        "\n",
+        "\n",
+        "def download_image(url):\n",
+        "    response = requests.get(url)\n",
+        "    return Image.open(BytesIO(response.content))\n",
+        "\n",
+        "\n",
+        "def image_to_base64(image, format=\"JPEG\"):\n",
+        "    buffer = BytesIO()\n",
+        "    image.save(buffer, format=format)\n",
+        "    image_str = base64.b64encode(buffer.getvalue()).decode(\"utf-8\")\n",
+        "    return image_str\n",
+        "\n",
+        "\n",
+        "def base64_to_image(image_str):\n",
+        "    image = Image.open(BytesIO(base64.b64decode(image_str)))\n",
+        "    return image\n",
+        "\n",
+        "\n",
+        "def image_grid(imgs, rows=2, cols=2):\n",
+        "    w, h = imgs[0].size\n",
+        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
+        "    for i, img in enumerate(imgs):\n",
+        "        grid.paste(img, box=(i % cols * w, i // cols * h))\n",
+        "    return grid\n",
+        "\n",
+        "\n",
+        "def deploy_model(model_id, task):\n",
+        "    model_name = \"stable-diffusion-v2\"\n",
+        "    endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-{task}-endpoint\")\n",
+        "    serving_env = {\n",
+        "        \"MODEL_ID\": model_id,\n",
+        "        \"TASK\": task,\n",
+        "    }\n",
+        "    model = aiplatform.Model.upload(\n",
+        "        display_name=model_name,\n",
+        "        serving_container_image_uri=SERVE_DOCKER_URI,\n",
+        "        serving_container_ports=[7080],\n",
+        "        serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
+        "        serving_container_health_route=\"/ping\",\n",
+        "        serving_container_environment_variables=serving_env,\n",
+        "    )\n",
+        "    model.deploy(\n",
+        "        endpoint=endpoint,\n",
+        "        machine_type=\"n1-standard-8\",\n",
+        "        accelerator_type=\"NVIDIA_TESLA_V100\",\n",
+        "        accelerator_count=1,\n",
+        "        deploy_request_timeout=1800,\n",
+        "        service_account=SERVICE_ACCOUNT,\n",
+        "    )\n",
+        "    return model, endpoint\n",
+        "\n",
+        "\n",
+        "def get_bucket_and_blob_name(filepath):\n",
+        "    # The gcs path is of the form gs://<bucket-name>/<blob-name>\n",
+        "    gs_suffix = filepath.split(\"gs://\", 1)[1]\n",
+        "    return tuple(gs_suffix.split(\"/\", 1))\n",
+        "\n",
+        "\n",
+        "def upload_local_dir_to_gcs(local_dir_path, gcs_dir_path):\n",
+        "    \"\"\"Uploads files in a local directory to a GCS directory.\"\"\"\n",
+        "    client = storage.Client()\n",
+        "    bucket_name = gcs_dir_path.split(\"/\")[2]\n",
+        "    bucket = client.get_bucket(bucket_name)\n",
+        "    for local_file in glob.glob(local_dir_path + \"/**\"):\n",
+        "        if not os.path.isfile(local_file):\n",
+        "            continue\n",
+        "        filename = local_file[1 + len(local_dir_path) :]\n",
+        "        gcs_file_path = os.path.join(gcs_dir_path, filename)\n",
+        "        _, blob_name = get_bucket_and_blob_name(gcs_file_path)\n",
+        "        blob = bucket.blob(blob_name)\n",
+        "        blob.upload_from_filename(local_file)\n",
+        "        print(\"Copied {} to {}.\".format(local_file, gcs_file_path))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e8a42fa49305"
+      },
+      "source": [
+        "## Run inferences locally"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1d5ebc91c786"
+      },
+      "source": [
+        "### Text-to-image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d39ed8c97cc5"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "from diffusers import DPMSolverMultistepScheduler, StableDiffusionPipeline\n",
+        "\n",
+        "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
+        "model_id = \"stabilityai/stable-diffusion-2-1\"\n",
+        "pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)\n",
+        "pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)\n",
+        "pipe = pipe.to(device)\n",
+        "pipe.enable_attention_slicing()\n",
+        "\n",
+        "prompt = \"\"\"\n",
+        "  a picture of the universe, showing sea of stars, Nebula and Supernova\n",
+        "  elegant, detailed digital painting\"\"\"\n",
+        "\n",
+        "results = pipe(prompt=prompt)\n",
+        "images = results.images\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5aed5ed7b6f6"
+      },
+      "source": [
+        "### Text-guided image-to-image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "faadabb7728f"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "from diffusers import (DPMSolverMultistepScheduler,\n",
+        "                       StableDiffusionImg2ImgPipeline)\n",
+        "\n",
+        "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
+        "model_id = \"stabilityai/stable-diffusion-2-1\"\n",
+        "pipe = StableDiffusionImg2ImgPipeline.from_pretrained(\n",
+        "    model_id, torch_dtype=torch.float16\n",
+        ")\n",
+        "pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)\n",
+        "pipe = pipe.to(device)\n",
+        "pipe.enable_attention_slicing()\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",
+        "results = pipe(prompt=prompt, image=init_image)\n",
+        "images = results.images\n",
+        "display(init_image)\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e70e3519ff8b"
+      },
+      "source": [
+        "## Finetune with Dreambooth"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0dc65d8f0689"
+      },
+      "source": [
+        "This section uses [dreambooth](https://dreambooth.github.io/) to finetune the [stable-diffusion-2-1](https://huggingface.co/stabilityai/stable-diffusion-2-1) model with [5 dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ) to personalize the text-to-image model.\n",
+        "\n",
+        "It finetunes both text encoder and unet of the stable diffusion model up to 800 steps. The whole finetuning job takes 45 minutes to finish using 1 A100 GPU.\n",
+        "\n",
+        "The full model will be saved after the finetuning job finishs and it can be loaded by the [StableDiffusionPipeline](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img) to run inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "34048707df5c"
+      },
+      "outputs": [],
+      "source": [
+        "# Download example training images.\n",
+        "!gdown --folder https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ\n",
+        "\n",
+        "# Upload data to Cloud Storage bucket.\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog\")\n",
+        "upload_local_dir_to_gcs(\"dog\", f\"gs://{GCS_BUCKET}/dreambooth/dog_class\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "969cfeb79317"
+      },
+      "source": [
+        "**NOTE**: If the upload step fails due to lacking of permission, you need to [grant the Storage Object Admin role](https://cloud.google.com/storage/docs/access-control/using-iam-permissions) for the Cloud account of the notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65467b361315"
+      },
+      "outputs": [],
+      "source": [
+        "# The pre-trained model to be loaded.\n",
+        "model_id = \"stabilityai/stable-diffusion-2-1\"\n",
+        "\n",
+        "# Input and output path.\n",
+        "instance_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/dog\"\n",
+        "class_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/dog_class\"\n",
+        "output_dir = f\"/gcs/{GCS_BUCKET}/dreambooth/output\"\n",
+        "\n",
+        "# Worker pool spec.\n",
+        "machine_type = \"a2-highgpu-1g\"\n",
+        "num_nodes = 1\n",
+        "gpu_type = \"NVIDIA_TESLA_A100\"\n",
+        "num_gpus = 1\n",
+        "\n",
+        "# Setup training job.\n",
+        "job_name = create_job_name(\"dreambooth-stable-diffusion\")\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
+        "    display_name=job_name,\n",
+        "    container_uri=TRAIN_DOCKER_URI,\n",
+        ")\n",
+        "\n",
+        "# Pass training arguments and launch job.\n",
+        "# See https://github.com/huggingface/diffusers/blob/v0.14.0/examples/dreambooth/train_dreambooth.py#L75\n",
+        "# for a full list of training arguments.\n",
+        "model = job.run(\n",
+        "    args=[\n",
+        "        \"dreambooth/train_dreambooth.py\",\n",
+        "        f\"--pretrained_model_name_or_path={model_id}\",\n",
+        "        \"--train_text_encoder\",\n",
+        "        f\"--instance_data_dir={instance_dir}\",\n",
+        "        f\"--class_data_dir={class_dir}\",\n",
+        "        f\"--output_dir={output_dir}\",\n",
+        "        \"--with_prior_preservation\",\n",
+        "        \"--prior_loss_weight=1.0\",\n",
+        "        \"--instance_prompt='a photo of sks dog'\",\n",
+        "        \"--class_prompt='a photo of dog'\",\n",
+        "        \"--resolution=512\",\n",
+        "        \"--train_batch_size=1\",\n",
+        "        \"--gradient_checkpointing\",\n",
+        "        \"--learning_rate=2e-6\",\n",
+        "        \"--lr_scheduler=constant\",\n",
+        "        \"--lr_warmup_steps=0\",\n",
+        "        \"--num_class_images=200\",\n",
+        "        \"--max_train_steps=800\",\n",
+        "    ],\n",
+        "    replica_count=num_nodes,\n",
+        "    machine_type=machine_type,\n",
+        "    accelerator_type=gpu_type,\n",
+        "    accelerator_count=num_gpus,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bf7f82732e61"
+      },
+      "source": [
+        "## Upload and Deploy models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1cc26e68d7b0"
+      },
+      "source": [
+        "This section uploads the model to Model Registry and deploys it on the Endpoint.\n",
+        "\n",
+        "The model deployment step will take ~15 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd7b56421392"
+      },
+      "source": [
+        "### Text-to-image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6d331b1ea337"
+      },
+      "source": [
+        "Deploy the stable diffusion model for the text-to-image task.\n",
+        "\n",
+        "Once deployed, you can send a batch of text prompts to the endpoint to generated images.\n",
+        "\n",
+        "When deployed on one V100 GPU, the averaged inference time of a request is ~20 seconds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bf55e38815dc"
+      },
+      "outputs": [],
+      "source": [
+        "# Set the model_id to \"stabilityai/stable-diffusion-2-1\" to load the OSS pre-trained model.\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_id=f\"gs://{GCS_BUCKET}/dreambooth/output\", task=\"text-to-image\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "80b3fd2ace09"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus upto 10 minutes of additional waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4ab04da3ec9a"
+      },
+      "outputs": [],
+      "source": [
+        "instances = [\n",
+        "    {\"prompt\": \"a deer in Matisse style\"},\n",
+        "    {\"prompt\": \"a sks dog in Van Gogh style\"},\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "image_grid(images)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "af21a3cff1e0"
+      },
+      "source": [
+        "Clean up resources:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "911406c1561e"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c1e51f764a60"
+      },
+      "source": [
+        "### Text-guided image-to-image"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fa686a54047c"
+      },
+      "source": [
+        "Deploy the stable diffusion model for the text-guided image-to-image task."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "65e32356fbd1"
+      },
+      "outputs": [],
+      "source": [
+        "# Set the model_id to a GCS path, like \"gs://GCS_BUCKET/dreambooth/output\", to load the dreambooth finetuned model above.\n",
+        "model, endpoint = deploy_model(\n",
+        "    model_id=\"stabilityai/stable-diffusion-2-1\", task=\"image-to-image\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "SsjYFLvNymc0"
+      },
+      "source": [
+        "NOTE: The model weights will be downloaded after the deployment succeeds. Thus additional 5 minutes of waiting time is needed **after** the above model deployment step succeeds and before you run the next step below. Otherwise you might see a `ServiceUnavailable: 503 502:Bad Gateway` error when you send requests to the endpoint."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "83a50fd4a1ed"
+      },
+      "outputs": [],
+      "source": [
+        "init_image = download_image(\n",
+        "    \"https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg\"\n",
+        ")\n",
+        "display(init_image)\n",
+        "instances = [\n",
+        "    {\n",
+        "        \"prompt\": \"A fantasy landscape, trending on artstation\",\n",
+        "        \"image\": image_to_base64(init_image),\n",
+        "    },\n",
+        "]\n",
+        "response = endpoint.predict(instances=instances)\n",
+        "images = [base64_to_image(image) for image in response.predictions]\n",
+        "display(images[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ed3795d474b9"
+      },
+      "source": [
+        "Clean up resources:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b53b883257b4"
+      },
+      "outputs": [],
+      "source": [
+        "# Undeploy model and delete endpoint.\n",
+        "endpoint.delete(force=True)\n",
+        "\n",
+        "# Delete models.\n",
+        "model.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "name": "model_garden_pytorch_stable_diffusion_2_1.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/model_garden/model_garden_pytorch_vilt_vqa.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/community/model_garden/model_garden_pytorch_vit_gpt2_image_captioning.ipynb

@@ -107,20 +107,17 @@
       },
       "outputs": [],
       "source": [
-        "!pip3 install --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b60a4d7100bf"
-      },
-      "outputs": [],
-      "source": [
-        "from google.colab import auth as google_auth\n",
+        "if \"google.colab\" in str(get_ipython()):\n",
+        "    ! pip3 install --upgrade google-cloud-aiplatform\n",
+        "    from google.colab import auth as google_auth\n",
         "\n",
-        "google_auth.authenticate_user()"
+        "    google_auth.authenticate_user()\n",
+        "\n",
+        "    # Restart the notebook kernel after installs.\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {

notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb

@@ -88,8 +88,8 @@
         "- Make a batch prediction with the BigQuery ML model.\n",
         "- Create a Vertex AI `Dataset` resource.\n",
         "- Train the Vertex AI Forecasting model.\n",
-        "- View the Model evaluation.\n",
-        "- Make a batch prediction with the Model.\n"
+        "- View the Vertex AI Model Evaluation results.\n",
+        "- Make a batch prediction with the Vertex AI Forecasting model.\n"
       ]
     },
     {

notebooks/official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb

@@ -50,7 +50,7 @@
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>                                                                                               \n",
-        "</table>"
+        "</table>\n"
       ]
     },
     {
@@ -132,55 +132,6 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ze4-nDLfK4pw"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gCuSR8GkAgzl"
-      },
-      "source": [
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to [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": {
@@ -189,7 +140,7 @@
       "source": [
         "### Install additional packages\n",
         "\n",
-        "Install additional package dependencies not installed in your notebook environment,TensorFlow or Vertex AI SDK. Use the latest major GA version of each package."
+        "Install additional package dependencies not installed in your notebook environment."
       ]
     },
     {
@@ -200,337 +151,170 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install {USER_FLAG} --upgrade joblib fsspec gcsfs scikit-learn -q\n",
-        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform -q"
+        "! pip3 install --upgrade --quiet joblib fsspec gcsfs scikit-learn \n",
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform "
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "hhq5zEbGg0XX"
+        "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "EzrelQZ22IZj"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "BF1j6f9HApxa"
+        "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 $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable APIs](https://console.cloud.google.com/flows/enableapi?apiid=cloudresourcemanager.googleapis.com,aiplatform.googleapis.com).\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "oM1iC_MfAts1"
+        "id": "set_project_id"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
         "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "riG_qUokg0XZ"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "wJyyYlKGYqaa"
-      },
-      "outputs": [],
-      "source": [
-        "!gcloud config set project $PROJECT_ID"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "88dd74c4c84e"
+        "id": "region"
       },
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "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": "5c615e53149f"
+        "id": "region"
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "06571eb4063b"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "697568e92bd6"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dr--iN2kAylZ"
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "sBCra4QMA2wR"
-      },
-      "source": [
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**Otherwise**, follow these steps:\n",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type and select\n",
-        "the following role into the filter box:\n",
-        "\n",
-        "    *   Storage Admin\n",
-        "    *   Storage Object Admin\n",
-        "    *   Service Account User\n",
-        "    *   Vertex AI Administrator\n",
-        "\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "PyQmSRbKA8r-"
+        "id": "ce6043da7b33"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "\n",
-        "IS_COLAB = False\n",
-        "\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",
-        "\n",
-        "        IS_COLAB = True\n",
-        "\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",
-        "\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# ! gcloud auth login"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "zgPO1eR3CYjk"
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:mbsdk"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "MzGDU7TWdts_"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cf221059d072"
-      },
-      "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": "-EcIXiGsCePi"
+        "id": "create_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -540,31 +324,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "NIq7R4HZCfIc"
+        "id": "create_bucket"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ucvCsknMCims"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "vhOb7YnwClBb"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "! gsutil mb -l {REGION} {BUCKET_URI}"
       ]
     },
     {
@@ -573,7 +337,7 @@
         "id": "0ljjTziu90rZ"
       },
       "source": [
-        "### Set project folder"
+        "### Set data folder"
       ]
     },
     {
@@ -585,7 +349,7 @@
       "outputs": [],
       "source": [
         "DATA_PATH = \"data\"\n",
-        "!mkdir -m 777 -p {DATA_PATH}"
+        "! mkdir -m 777 -p {DATA_PATH}"
       ]
     },
     {
@@ -606,21 +370,12 @@
       "outputs": [],
       "source": [
         "DATASET_URL = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00359/NewsAggregatorDataset.zip\"\n",
-        "!wget --no-parent {DATASET_URL} --directory-prefix={DATA_PATH}\n",
-        "!mkdir -m 777 -p {DATA_PATH}/temp {DATA_PATH}/raw\n",
-        "!unzip {DATA_PATH}/*.zip -d {DATA_PATH}/temp\n",
-        "!mv {DATA_PATH}/temp/*.csv {DATA_PATH}/raw && rm -Rf {DATA_PATH}/temp && rm -f {DATA_PATH}/*.zip"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "N-chqqLJAOpM"
-      },
-      "outputs": [],
-      "source": [
-        "!gsutil -m cp -R {DATA_PATH}/raw $BUCKET_URI/{DATA_PATH}/raw"
+        "! wget --no-parent {DATASET_URL} --directory-prefix={DATA_PATH}\n",
+        "! mkdir -m 777 -p {DATA_PATH}/temp {DATA_PATH}/raw\n",
+        "! unzip {DATA_PATH}/*.zip -d {DATA_PATH}/temp\n",
+        "! mv {DATA_PATH}/temp/*.csv {DATA_PATH}/raw && rm -Rf {DATA_PATH}/temp && rm -f {DATA_PATH}/*.zip\n",
+        "\n",
+        "! gsutil -m cp -R {DATA_PATH}/raw $BUCKET_URI/{DATA_PATH}/raw"
       ]
     },
     {
@@ -649,6 +404,7 @@
         "import collections\n",
         "import tempfile\n",
         "import time\n",
+        "import uuid\n",
         "from json import dumps\n",
         "\n",
         "collections.Iterable = collections.abc.Iterable\n",
@@ -674,6 +430,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "# Base\n",
         "DATASET_NAME = \"news_corpora\"\n",
         "DATASET_URI = f\"{BUCKET_URI}/{DATA_PATH}/raw/newsCorpora.csv\"\n",
@@ -681,7 +439,7 @@
         "# Experiments\n",
         "TASK = \"classification\"\n",
         "MODEL_TYPE = \"naivebayes\"\n",
-        "EXPERIMENT_NAME = f\"{TASK}-{MODEL_TYPE}-{UUID}\"\n",
+        "EXPERIMENT_NAME = f\"{TASK}-{MODEL_TYPE}-{uuid.uuid1()}\"\n",
         "EXPERIMENT_RUN_NAME = \"run-1\"\n",
         "\n",
         "# Preprocessing\n",
@@ -710,7 +468,7 @@
         "FEATURES = \"title\"\n",
         "TEST_SIZE = 0.2\n",
         "SEED = 8\n",
-        "TRAINED_MODEL_URI = f\"{BUCKET_URI}/deliverables/{UUID}\"\n",
+        "TRAINED_MODEL_URI = f\"{BUCKET_URI}/deliverables/{uuid.uuid1()}\"\n",
         "MODEL_NAME = f\"{EXPERIMENT_NAME}-model\""
       ]
     },
@@ -860,6 +618,8 @@
         "\"\"\"\n",
         "\n",
         "\n",
+        "import string\n",
+        "\n",
         "import pandas as pd\n",
         "\n",
         "\n",
@@ -1283,17 +1043,6 @@
         "\n",
         "!rm -Rf {DATA_PATH}"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3f00c455b930"
-      },
-      "outputs": [],
-      "source": [
-        "!rm -Rf {DATA_PATH}"
-      ]
     }
   ],
   "metadata": {

notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb

@@ -139,8 +139,8 @@
       },
       "outputs": [],
       "source": [
-        "! pip install --upgrade -q google-cloud-aiplatform \\\n",
-        "                            tensorflow -q"
+        "! pip install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                tensorflow==2.11"
       ]
     },
     {

notebooks/official/model_monitoring/get_started_with_model_monitoring_automl_image_batch.ipynb

@@ -383,7 +383,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l {REGION} -p {PROJECT_ID} {BUCKET_URI}"
       ]
     },
     {

notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb

@@ -338,6 +338,26 @@
         "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-EcIXiGsCePi"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NIq7R4HZCfIc"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l {REGION} -p {PROJECT_ID} {BUCKET_URI}"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -372,8 +392,6 @@
         "import sys\n",
         "\n",
         "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "\n",
-        "\n",
         "if (\n",
         "    SERVICE_ACCOUNT == \"\"\n",
         "    or SERVICE_ACCOUNT is None\n",

notebooks/official/pipelines/google_cloud_pipeline_components_model_upload_predict_evaluate.ipynb

@@ -61,7 +61,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook shows how to use the components defined in [`google_cloud_pipeline_components`](https://github.com/kubeflow/pipelines/tree/master/components/google-cloud) in conjunction with an experimental `evaluation` method, to build a [Vertex AI Pipelines](https://cloud.google.com/vertex-ai/docs/pipelines) workflow that uploads a tabular custom model as a `Model` resource, creates a `BatchPredictionJob` resource, and evaluates the `Model` resource with the `BatchPredictionJob` results to create an evaluation `system.Metrics` artifact.\n",
+        "This notebook shows how to use the components defined in [`google_cloud_pipeline_components`](https://github.com/kubeflow/pipelines/tree/master/components/google-cloud) in conjunction with an experimental `evaluation` method, to build a [Vertex AI Pipelines](https://cloud.google.com/vertex-ai/docs/pipelines) workflow that uploads a tabular custom model as a `Model` resource, creates a `BatchPredictionJob` resource, and evaluates the `Model` resource with the `BatchPredictionJob` results to create an evaluation `system.Metrics` artifact. \n",
         "\n",
         "Learn more about [Vertex AI Pipelines](https://cloud.google.com/vertex-ai/docs/pipelines/introduction) and [Vertex AI Model components](https://cloud.google.com/vertex-ai/docs/pipelines/model-endpoint-component)."
       ]
@@ -126,54 +126,12 @@
     {
       "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": {
-        "id": "install_aip:mbsdk"
+        "id": "i7EUnXsZhAGF"
       },
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI and google-cloud-pipeline-components SDK for Python."
+        "Install the following packages required to execute this notebook. "
       ]
     },
     {
@@ -184,157 +142,82 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
-        "                        'google-cloud-pipeline-components<2' \\\n",
-        "                        'kfp<2' $USER_FLAG -q"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 'google-cloud-pipeline-components<2' \\\n",
+        "                                 'kfp<2'"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "restart"
+        "id": "58707a750154"
       },
       "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": "a1WZ6PC7Bfb8"
+        "id": "f200f10a1da3"
       },
       "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": "check_versions"
+        "id": "BF1j6f9HApxa"
       },
       "source": [
-        "### Check package versions\n",
+        "## Before you begin\n",
         "\n",
-        "Check the versions of the packages you installed.  "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "check_versions:kfp,gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "! python3 -c \"import kfp; print('KFP SDK version: {}'.format(kfp.__version__))\"\n",
-        "! python3 -c \"import google_cloud_pipeline_components; print('google_cloud_pipeline_components version: {}'.format(google_cloud_pipeline_components.__version__))\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "d6a00c14b087"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "before_you_begin:nogpu"
-      },
-      "source": [
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "1. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "1. [Enable the Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "3. [Enable the Vertex AI API]\n",
         "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+        "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": "50756f65354f"
+        "id": "WReHDGG5g0XY"
       },
       "source": [
         "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_project_id"
+        "id": "oM1iC_MfAts1"
       },
       "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}"
       ]
     },
     {
@@ -345,30 +228,18 @@
       "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)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "mXqsucfBBfb_"
+        "id": "region"
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -410,104 +281,78 @@
       "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": "2q0yKPmeBfcA"
+        "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": "bucket:mbsdk"
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zgPO1eR3CYjk"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets.\n",
         "\n",
-        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "- *{Note to notebook author: For any user-provided strings that need to be unique (like bucket names or model ID's), append \"-unique\" to the end so proper testing can occur}*"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "bucket"
+        "id": "MzGDU7TWdts_"
       },
       "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\"}"
       ]
     },
     {
@@ -523,31 +368,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "Av2hiwHuBfcB"
+        "id": "NIq7R4HZCfIc"
       },
       "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": "00DHnc5dBfcB"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "! gsutil mb -l {REGION} -p {PROJECT_ID} {BUCKET_URI}"
       ]
     },
     {
@@ -582,6 +407,9 @@
       },
       "outputs": [],
       "source": [
+        "import sys\n",
+        "\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
         "if (\n",
         "    SERVICE_ACCOUNT == \"\"\n",
         "    or SERVICE_ACCOUNT is None\n",
@@ -1061,6 +889,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "delete_bucket = False\n",
         "\n",
         "# Delete the created model\n",

notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb

@@ -137,36 +137,17 @@
       ]
     },
     {
-      "cell_type": "markdown",
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
-        "id": "setup_local"
+        "id": "install_aip:mbsdk"
       },
+      "outputs": [],
       "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "If you are using Colab or Google Cloud Notebook, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
-        "\n",
-        "- The Cloud Storage SDK\n",
-        "- Git\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
-        "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
-        "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
-        "\n",
-        "3. [Install virtualenv](Ihttps://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.\n",
-        "\n",
-        "4. Activate that environment and run `pip3 install Jupyter` in a terminal shell to install Jupyter.\n",
-        "\n",
-        "5. Run `jupyter notebook` on the command line in a terminal shell to launch Jupyter.\n",
-        "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage \\\n",
+        "                                 'kfp<2' \\\n",
+        "                                 'google-cloud-pipeline-components<2' "
       ]
     },
     {
@@ -180,147 +161,77 @@
         "Install the packages required for executing this notebook."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
-        "! pip3 install -U google-cloud-storage {USER_FLAG} -q\n",
-        "! pip3 install {USER_FLAG} 'kfp<2' 'google-cloud-pipeline-components<2' --upgrade -q"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "restart"
+        "id": "58707a750154"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "### Colab only: Uncomment the following cell to restart the kernel."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "f200f10a1da3"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "check_versions"
-      },
-      "source": [
-        "Check the versions of the packages you installed.  The KFP SDK version should be >=1.6."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "check_versions:kfp,gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "! python3 -c \"import kfp; print('KFP SDK version: {}'.format(kfp.__version__))\"\n",
-        "! python3 -c \"import google_cloud_pipeline_components; print('google_cloud_pipeline_components version: {}'.format(google_cloud_pipeline_components.__version__))\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "BF1j6f9HApxa"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
-        "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "3. [Enable the Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "3. [Enable the Vertex AI API]\n",
         "\n",
-        "4. [The Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Google Cloud Notebook.\n",
+        "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WReHDGG5g0XY"
+      },
+      "source": [
+        "#### Set your project ID\n",
         "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_project_id"
+        "id": "oM1iC_MfAts1"
       },
       "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}"
       ]
     },
     {
@@ -331,16 +242,7 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -354,30 +256,6 @@
         "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -386,103 +264,78 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebook**, your environment is already authenticated. Skip this step.\n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\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": "bucket:mbsdk"
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zgPO1eR3CYjk"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
+        "Create a storage bucket to store intermediate artifacts such as datasets.\n",
         "\n",
-        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+        "- *{Note to notebook author: For any user-provided strings that need to be unique (like bucket names or model ID's), append \"-unique\" to the end so proper testing can occur}*"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "bucket"
+        "id": "MzGDU7TWdts_"
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
-        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -498,31 +351,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "NIq7R4HZCfIc"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_URI"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "! gsutil mb -l {REGION} -p {PROJECT_ID} {BUCKET_URI}"
       ]
     },
     {
@@ -555,6 +388,9 @@
       },
       "outputs": [],
       "source": [
+        "import sys\n",
+        "\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
         "if (\n",
         "    SERVICE_ACCOUNT == \"\"\n",
         "    or SERVICE_ACCOUNT is None\n",
@@ -961,7 +797,7 @@
       },
       "outputs": [],
       "source": [
-        "DISPLAY_NAME = \"shakespeare_\" + TIMESTAMP\n",
+        "DISPLAY_NAME = \"shakespeare\"\n",
         "\n",
         "job = aip.PipelineJob(\n",
         "    display_name=DISPLAY_NAME,\n",
@@ -1014,6 +850,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "delete_bucket = False\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",

notebooks/official/reduction_server/pytorch_distributed_training_reduction_server.ipynb

@@ -24,7 +24,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "title"
@@ -55,7 +54,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "overview:custom"
@@ -69,7 +67,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "objective:custom,training,online_prediction"
@@ -94,7 +91,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "dataset:custom,cifar10,icn"
@@ -106,7 +102,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "costs"
@@ -127,7 +122,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "install_aip"
@@ -150,7 +144,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "restart"
@@ -175,7 +168,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "d2qpIurSjmpT"
@@ -197,7 +189,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "project_id"
@@ -226,7 +217,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "a54f9d7c1876"
@@ -249,7 +239,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "R7eelnCv6EWn"
@@ -281,7 +270,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "5c0404984792"
@@ -293,7 +281,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "x2n5SeAAjmpU"
@@ -304,7 +291,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "6FDh38swjmpU"
@@ -325,7 +311,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "XUSL_JcpjmpU"
@@ -347,7 +332,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "TCPJ38n7jmpU"
@@ -358,7 +342,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "bucket:custom"
@@ -383,11 +366,10 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "create_bucket"
@@ -404,11 +386,10 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l {REGION} -p {PROJECT_ID} {BUCKET_URI}"
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "v3sbyPBU75CR"
@@ -429,7 +410,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "import_aip"
@@ -452,7 +432,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "tutorial_start:custom"
@@ -464,7 +443,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "train_custom_model"
@@ -483,7 +461,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "hBP_kLymhnYP"
@@ -512,7 +489,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "4387867f83f2"
@@ -548,7 +524,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "4NqTnsxaAdRp"
@@ -573,7 +548,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "3rpehVa0iFjY"
@@ -620,7 +594,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "jXlifmTtiTzy"
@@ -809,7 +782,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "uzmJxNOnix9O"
@@ -836,7 +808,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "gv0PB6WhjKsA"
@@ -864,7 +835,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "iy_OwOByjW1W"
@@ -895,7 +865,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "YimBZzZmAUwP"
@@ -946,7 +915,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "xErX0T7LHYjX"
@@ -982,7 +950,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "CA38ygH_jeJe"
@@ -994,7 +961,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "s6LpsQI1WpPz"
@@ -1017,7 +983,6 @@
       ]
     },
     {
-      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "cleanup:custom"

notebooks/official/sdk/SDK_Custom_Training_Python_Package_Managed_Text_Dataset_Tensorflow_Serving_Container.ipynb

@@ -683,7 +683,7 @@
         "            if file.endswith(\".txt\"):\n",
         "                class_name = root.split(\"/\")[-1]\n",
         "                file_fn = os.path.join(root, file)\n",
-        "                with open(file_fn, \"r\") as f:\n",
+        "                with open(file_fn) as f:\n",
         "                    content = f.readlines()\n",
         "                    lines = [x.strip().strip('\"') for x in content]\n",
         "                    writer.writerow((lines[0], class_name))\n",
@@ -1544,7 +1544,7 @@
         "            for file in files:\n",
         "                if file.endswith(\".txt\"):\n",
         "                    file_fn = os.path.join(root, file)\n",
-        "                    with open(file_fn, \"r\") as f:\n",
+        "                    with open(file_fn) as f:\n",
         "                        content = f.readlines()\n",
         "                        lines = [x.strip().strip('\"') for x in content]\n",
         "\n",