docs: Keras 3 evaluate() and compiled metrics clarification #21506
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @sonali-kumari1, 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 focuses on enhancing the clarity of Keras 3's evaluate() method documentation. The primary goal is to resolve confusion regarding the output of evaluate() when used with compiled metrics, particularly how it relates to the model.metrics_names attribute, ensuring users can correctly interpret the results.
Highlights
- Documentation Improvement: I've updated the docstring for the
evaluate()method in Keras 3 to provide clearer guidance on its return values, especially when compiled metrics are involved. - Metrics Clarification: The documentation now explicitly addresses the potential mismatch between the number of values returned by
evaluate()and the entries inmodel.metrics_nameswhen submetrics are present. It clarifies thatmodel.metrics_namesoften lists only top-level names, whileevaluate()can return multiple submetric values, and explains that the order ofevaluate()output corresponds to the order of metrics specified duringmodel.compile().
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 or fill out our survey to provide feedback.
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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request improves the documentation for evaluate() to clarify the relationship between its return values and model.metrics_names. The change is helpful. I've suggested a small wording improvement to make the order of the returned values (loss and metrics) even clearer.
keras/src/trainers/trainer.py
Outdated
| length mismatch. The order of the `evaluate()` output corresponds | ||
| to the order of metrics specified during `model.compile()`. You can |
There was a problem hiding this comment.
This is a great clarification! To make it even more precise, could we also mention that the loss is the first value in the returned list? The current wording (...corresponds to the order of metrics...) could be interpreted as if only metrics are returned, which might be confusing.
| length mismatch. The order of the `evaluate()` output corresponds | |
| to the order of metrics specified during `model.compile()`. You can | |
| length mismatch. The returned values are ordered as: first the loss, then the metrics from `model.compile()` in order. You can |
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #21506 +/- ##
==========================================
- Coverage 82.84% 82.72% -0.13%
==========================================
Files 565 567 +2
Lines 55656 56214 +558
Branches 8685 8786 +101
==========================================
+ Hits 46108 46501 +393
- Misses 7433 7556 +123
- Partials 2115 2157 +42
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This commit improves the documentation for
evaluate()when used with compiled metrics in Keras 3. The existing documentation can be imprecise becausemodel.metrics_namesdoes not always provide a complete list of the values returned byevaluate().colab gist
Fixes : #21487