Skip to content

Conversation

@PES2UG23CS205
Copy link

This PR documents the current limitation of keras.ops.correlate with complex
dtypes on the TensorFlow and PyTorch backends, where complex inputs are cast to
floating-point types and imaginary components are dropped.

This clarification aligns with the discussion in issue #21617.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @PES2UG23CS205, 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 primarily intends to improve the clarity of the keras.ops.correlate function's behavior by documenting its current limitation with complex data types on TensorFlow and PyTorch backends. This documentation will inform users that complex inputs will have their imaginary components discarded. This clarification directly addresses discussions from issue #21617. Additionally, a minor adjustment was made to the OpenVINO backend's test exclusion list, removing NumPyTestRot90.

Highlights

  • Documentation Intent: This pull request aims to document a known limitation within keras.ops.correlate regarding complex data types. Specifically, it clarifies that when complex inputs are used with TensorFlow and PyTorch backends, they are cast to floating-point types, and their imaginary components are dropped.
  • Test Configuration Update: The NumPyTestRot90 test has been removed from the list of tests excluded for the OpenVINO backend, suggesting it is now expected to pass or its exclusion is no longer necessary.

🧠 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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request appears to combine two unrelated changes. The main purpose, as described, is to document a limitation in keras.ops.correlate. However, the provided file changes only show the removal of NumPyTestRot90 from the excluded tests for the OpenVINO backend, which seems related to enabling rot90 tests. It is generally recommended to keep pull requests focused on a single logical change. I am unable to review the documentation change for correlate as the relevant file is not included in the provided patch. My review is therefore limited to the changes in keras/src/backend/openvino/excluded_concrete_tests.txt. In that file, I've noted that a blank line has been added at the beginning, which should be removed.

NNOpsDynamicShapeTest::test_glu
NNOpsBehaviorTest::test_invalid_strategy_ctc_decode
NNOpsBehaviorTest::test_logit_recovery_binary_crossentropy
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This change introduces a blank line at the beginning of the file. While this might not cause issues, it's generally better to avoid leading blank lines in configuration files like this to prevent potential parsing errors. Please remove the blank line.

Copy link
Collaborator

@hertschuh hertschuh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This change appears to change all carriage returns from Unix style to Windows style, thus showing every line changed:
https://github.com/keras-team/keras/pull/21984/changes

Can you revert the carriage returns?

@@ -1,264 +1,271 @@
NumPyTestRot90
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Undo this file

@PES2UG23CS205
Copy link
Author

Thanks for the review!

You’re right , the previous version of this PR unintentionally included OpenVINO files due to CRLF line endings.
I’ve reverted those entirely, and the PR now only contains the intended documentation update for keras.ops.correlate.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants