[Relax][Onnx] Pass output_padding param in ConvTranspose

[locnd182644]

Summary

Inconsistent shapes of results produced by TVM and ONNX View due to the ConvTranspose operator

Steps to Reproduce

• ONNX View: Output Shape = (1, 6, 56, 56)

• TVM: Output Shape = (1, 6, 55, 55) (due to output_padding=[0, 0])

class Module:
    def main(input: R.Tensor((1, 3, 28, 28), dtype="float32"), weight: R.Tensor((3, 6, 3, 3), dtype="float32"), bias: R.Tensor((6,), dtype="float32")) -> R.Tensor((1, 6, 55, 55), dtype="float32"):
        R.func_attr({"num_input": 1, "params": [metadata["ffi.Tensor"][0], metadata["ffi.Tensor"][1]]})
        with R.dataflow():
            lv: R.Tensor((1, 6, 55, 55), dtype="float32") = R.nn.conv2d_transpose(input, weight, strides=[2, 2], padding=[1, 1, 1, 1], output_padding=[0, 0], dilation=[1, 1], groups=1, data_layout="NCHW", kernel_layout="IOHW", out_layout="NCHW", out_dtype="void")
            lv1: R.Tensor((1, 6, 1, 1), dtype="float32") = R.reshape(bias, R.shape([1, 6, 1, 1]))
            gv: R.Tensor((1, 6, 55, 55), dtype="float32") = R.add(lv, lv1)
            R.output(gv)
        return gv

Expected

• output_padding = [1, 1]

class Module:
    def main(input: R.Tensor((1, 3, 28, 28), dtype="float32"), weight: R.Tensor((3, 6, 3, 3), dtype="float32"), bias: R.Tensor((6,), dtype="float32")) -> R.Tensor((1, 6, 56, 56), dtype="float32"):
        R.func_attr({"num_input": 1, "params": [metadata["ffi.Tensor"][0], metadata["ffi.Tensor"][1]]})
        with R.dataflow():
            lv: R.Tensor((1, 6, 56, 56), dtype="float32") = R.nn.conv2d_transpose(input, weight, strides=[2, 2], padding=[1, 1, 1, 1], output_padding=[1, 1], dilation=[1, 1], groups=1, data_layout="NCHW", kernel_layout="IOHW", out_layout="NCHW", out_dtype="void")
            lv1: R.Tensor((1, 6, 1, 1), dtype="float32") = R.reshape(bias, R.shape([1, 6, 1, 1]))
            gv: R.Tensor((1, 6, 56, 56), dtype="float32") = R.add(lv, lv1)
            R.output(gv)
        return gv

Resolve

• When implement converts an onnx ConvTranspose node into an equivalent Relax expression, get and pass output_padding param into op.
• Fixed: [Bug] inconsistent shapes of results produced by TVM and ONNXRuntime due to the ConvTranspose operator #18601

[gemini-code-assist]

Summary of Changes

Hello @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 critical issue where the ConvTranspose operator produced inconsistent output shapes between TVM and ONNX due to the output_padding parameter not being properly handled during the ONNX to Relax conversion. The changes ensure that this parameter is correctly propagated and validated, leading to accurate and consistent results for transposed convolutions across both frameworks. This resolves issue #18601.

Highlights

• ONNX ConvTranspose output_padding: The output_padding parameter from ONNX ConvTranspose nodes is now correctly extracted and passed to the Relax conv2d_transpose operator, resolving inconsistencies in output shapes between TVM and ONNX.
• Relax ConvTranspose validation fix: A bug in the conv2d_transpose operator's validation logic was fixed, correcting the expected size of output_padding from 4 to 2.
• Enhanced testing: New test cases have been added to test_frontend_onnx.py to specifically verify the correct behavior of ConvTranspose with varying output_padding values.

🧠 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. ↩

[gemini-code-assist]

Code Review

This pull request correctly adds the output_padding parameter to the ConvTranspose operator in the ONNX frontend, which resolves an output shape inconsistency. The changes to the frontend implementation and the related error message fix are both accurate. I've noticed a couple of issues in the accompanying test file: the output shape calculation within the test is incorrect, and tests for ConvTranspose1D have been commented out. I have provided suggestions to fix the test logic and to add a TODO to track the disabled tests.

[tlopex]

LGTM! Thank you!