Update image serving notebook to Keras 3

[takumiohym]

Update Summary:

• Updated the code to Keras 3
• Updated SavedModel saving/loading from tf.saved_model to Keras native methods.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[gemini-code-assist]

Summary of Changes

Hello @takumiohym, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request updates the notebooks/image_models/labs/serving.ipynb notebook to align with Keras 3, migrating model definition, SavedModel export/load mechanisms, and tensor operations to Keras native APIs. It also refines the notebook's content and exercises to reflect these changes and updates the Vertex AI serving container image.

Highlights

• Keras 3 API Adoption: The notebook now fully leverages Keras 3, including new imports (keras, keras_hub) and Keras-native operations (keras.ops).
• Modernized Model Architecture: The model definition has been updated to use keras_hub.models.Backbone.from_preset and Keras functional API components for a more streamlined and Keras 3-idiomatic approach.
• Enhanced SavedModel Handling: The process for exporting and loading SavedModels has been revised to utilize Keras 3's transfer_model.export() and keras.export.ExportArchive, providing more robust and flexible model serialization.
• Streamlined Preprocessing: Image preprocessing and tensor manipulations now consistently use keras.ops functions, simplifying the code and ensuring compatibility with Keras 3's multi-backend capabilities.
• Updated Deployment Configuration: The Vertex AI serving container image URI has been updated to the latest version, ensuring compatibility with current deployment practices.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request does a great job of updating the image serving notebook to Keras 3. The changes are thorough, covering API updates from tensorflow_hub to keras_hub, modernizing model saving and loading with .keras and ExportArchive, and adopting keras.ops. The notebook is now much more aligned with current Keras 3 best practices. I've identified a couple of minor issues: a redundant line of code and an incorrect directory path in a shell command. Addressing these will make the notebook even better.