[Relax][NN] Add batch_flatten operator

[guan404ming]

Why

The batch_flatten operator was needed for CoreML backend support but was not implemented in Relax, causing the CoreML pattern and converter to be commented out.

How

• Add C++ operator relax.nn.batch_flatten with struct info inference
• Add Python wrapper in relax.op.nn
• Add legalization via topi.reshape
• Enable CoreML pattern and converter for nn.batch_flatten
• Add unit tests for operator, struct info inference, and legalization

[gemini-code-assist]

Summary of Changes

Hello @guan404ming, 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 implements the batch_flatten operator within the Relax framework, addressing a critical dependency for the CoreML backend. The new operator flattens all dimensions of a tensor except the batch dimension, which was previously a missing feature preventing full CoreML integration. The changes encompass the entire lifecycle of the operator, from its low-level C++ definition and Python bindings to its shape inference, legalization, and thorough unit testing, ensuring its correct and robust operation within the system.

Highlights

• New batch_flatten Operator: Introduced relax.nn.batch_flatten to flatten all dimensions except the batch dimension, crucial for neural network architectures.
• CoreML Backend Support Enabled: The absence of batch_flatten previously caused CoreML patterns and converters to be commented out; this PR enables them.
• Comprehensive Implementation: The operator includes a C++ definition, Python wrapper, struct info inference, and legalization via topi.reshape.
• Extensive Unit Testing: New unit tests cover operator correctness, struct info inference (including symbolic shapes), and legalization, ensuring robust functionality.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 introduces the relax.nn.batch_flatten operator, which is a great addition for CoreML backend support. The implementation is clean and follows the existing structure for Relax operators well. You've included comprehensive changes across the C++ implementation, Python bindings, legalization, and enabled it for the CoreML backend. The unit tests are thorough, covering correctness, struct info inference with various static and symbolic shapes, and legalization.

I found one potential issue in the legalization logic that could lead to a crash when dealing with inputs of unknown shape. I've left a specific comment with a suggested fix. Other than that, the changes look excellent.

[guan404ming]

cc @tlopex @mshr-h