-
Notifications
You must be signed in to change notification settings - Fork 19.7k
Document complex dtype limitation in ops.correlate #21984
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Document complex dtype limitation in ops.correlate #21984
Conversation
Summary of ChangesHello @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 Highlights
🧠 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 AssistThe 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
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 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
|
There was a problem hiding this 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 | ||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
hertschuh
left a comment
There was a problem hiding this 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 | |||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Undo this file
|
Thanks for the review! You’re right , the previous version of this PR unintentionally included OpenVINO files due to CRLF line endings. |
This PR documents the current limitation of
keras.ops.correlatewith complexdtypes 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.