[Relax][Torch] AssertionError: Unsupported function types ['mean.default'] #18574
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ult'] - Summary: Happen when convert module from exported_program have torch.mean without dim. - Resolved: Add "mean.default" into create_convert_map in class ExportedProgramImporter.
Contributor
Summary of ChangesHello @locnd182644, 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 addresses a specific conversion issue within the Relax frontend for PyTorch's Highlights
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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request correctly addresses an AssertionError for the unsupported function type mean.default when importing a PyTorch exported_program. The issue occurs when torch.mean is used without a dim argument. The fix involves mapping mean.default to the existing _mean handler, which is appropriate as it already handles cases where the dimension is None. The addition of a new test case, MeanWithoutDim, in test_frontend_from_exported_program.py is excellent, as it ensures this scenario is covered and prevents future regressions. The changes are sound and well-tested. I have a few minor suggestions to improve code style by removing trailing whitespace.
| "any.dim": self._any, | ||
| "any.dims": self._any, | ||
| "mean.dim": self._mean, | ||
| "mean.default": self._mean, |
Contributor
There was a problem hiding this comment.
There is trailing whitespace on this line. Please remove it to adhere to PEP 8 style guidelines.
Suggested change
| "mean.default": self._mean, | |
| "mean.default": self._mean, |
| class MeanKeepDim(Module): | ||
| def forward(self, input: torch.Tensor): | ||
| return input.mean(-1, keepdim=True) | ||
|
|
Contributor
There was a problem hiding this comment.
This line contains only whitespace. Please remove it to improve code cleanliness and adhere to PEP 8.
| gv: R.Tuple(R.Tensor((256, 1), dtype="float32")) = (lv,) | ||
| R.output(gv) | ||
| return gv | ||
|
|
Contributor
There was a problem hiding this comment.
This line contains only whitespace. Please remove it to improve code cleanliness and adhere to PEP 8.
Member
|
@tvm-bot rerun |
Contributor
|
Failed to re-run CI in https://github.com/apache/tvm/actions/runs/20419842803 Detailswith response |
Contributor
|
Failed to re-run CI in https://github.com/apache/tvm/actions/runs/20419842803 Detailswith response |
Member
|
Hi @locnd182644 Sorry, the CI seems stuck and GitHub “Re-run all jobs” fails for me. Could you please push an empty commit to retrigger CI, or rerun the checks from your side? |
Contributor
Author
|
@tlopex Thank you. I will rerun the check now. |
…into relax/torch/mean
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Happen error when create module from exported_program have torch.mean without dim.
Reproduce
Resolve: