Re: [PR] [Relax] Fix HardSigmoid returns 1.0 for NaN input [tvm]
cchung100m commented on PR #18631: URL: https://github.com/apache/tvm/pull/18631#issuecomment-3846203848 Hi @mshr-h Thanks for the reply. Could we keep the issue/PR open and mark it as known question for now? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] - To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
Re: [PR] [Relax] Fix HardSigmoid returns 1.0 for NaN input [tvm]
mshr-h commented on PR #18631: URL: https://github.com/apache/tvm/pull/18631#issuecomment-3805653711 Since the behavior for NaN inputs is not well defined, both tvm and onnxruntime are correct according to the specification. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] - To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
Re: [PR] [Relax] Fix HardSigmoid returns 1.0 for NaN input [tvm]
cchung100m commented on PR #18631: URL: https://github.com/apache/tvm/pull/18631#issuecomment-3802662075 Hi @tlopex @mshr-h Any suggestions would be appreciated if you are available. 😄 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] - To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
Re: [PR] [Relax] Fix HardSigmoid returns 1.0 for NaN input [tvm]
gemini-code-assist[bot] commented on code in PR #18631:
URL: https://github.com/apache/tvm/pull/18631#discussion_r2657711678
##
python/tvm/relax/frontend/onnx/onnx_frontend.py:
##
@@ -3254,7 +3254,11 @@ def _impl_v1(cls, bb, inputs, attr, params):
alpha = relax.const(alpha, dtype=dtype)
beta = float(attr.get("beta", 0.5))
beta = relax.const(beta, dtype=dtype)
-return relax.op.clip(relax.op.add(relax.op.multiply(alpha, x), beta),
0, 1)
+clipped = relax.op.clip(relax.op.add(relax.op.multiply(alpha, x),
beta), 0, 1)
+# Preserve NaN values: where x is NaN, return NaN instead of clipped
value
+is_nan = relax.op.isnan(x)
+nan_val = relax.op.divide(relax.const(0.0, dtype=dtype),
relax.const(0.0, dtype=dtype))
Review Comment:
For creating a NaN scalar constant, it's more direct and readable to use
`relax.const(float('nan'), dtype=dtype)` instead of dividing zero by zero. This
also avoids creating intermediate `Constant` and `divide` operator nodes in the
graph, making the graph construction slightly more efficient.
```suggestion
nan_val = relax.const(float("nan"), dtype=dtype)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
-
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
Re: [PR] [Relax] Fix HardSigmoid returns 1.0 for NaN input [tvm]
gemini-code-assist[bot] commented on PR #18631: URL: https://github.com/apache/tvm/pull/18631#issuecomment-3705311450 ## Summary of Changes Hello @cchung100m, I'm Gemini Code Assist[^1]! 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 critical bug in the `Relax` framework's `HardSigmoid` operator where NaN inputs were not handled correctly, leading to an erroneous output of 1.0. The changes ensure that `HardSigmoid` now propagates NaN values as expected, improving the numerical stability and correctness of computations involving undefined or unrepresentable floating-point numbers. The fix is accompanied by a dedicated test case to validate the new behavior. ### Highlights * **HardSigmoid NaN Handling**: The `HardSigmoid` operator in `relax.frontend.onnx` has been updated to correctly propagate NaN (Not a Number) values. Previously, NaN inputs would incorrectly result in an output of 1.0. * **Implementation Details**: The fix involves computing the standard clipped result, then explicitly checking for NaN inputs using `relax.op.isnan`. If an input is NaN, `relax.op.where` is used to return a NaN value (generated by `0.0 / 0.0`) at that position, otherwise the clipped value is returned. * **New Test Case**: A new test, `test_hardsigmoid_nan`, has been added to `tests/python/relax/test_frontend_onnx.py` to verify that `HardSigmoid` correctly preserves NaN values in its output when given NaN inputs. 🧠**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](https://codeassist.google/code-review/login) 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](https://developers.google.com/gemini-code-assist/docs/review-github-code), here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either `/gemini ` or `@gemini-code-assist `. 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](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). 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 :thumbsup: and :thumbsdown: 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](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG). 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](https://cloud.google.com/products/gemini/code-assist). [^1]: Review the [Privacy Notices](https://policies.google.com/privacy), [Generative AI Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of Service](https://policies.google.com/terms), and learn how to configure Gemini Code Assist in GitHub [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). Gemini can make mistakes, so double check it and [use code with caution](https://support.google.com/legal/answer/13505487). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] - To unsubscribe, e-mail: discuss-archive-unsu
