Fix WebGPU Conv auto_pad=SAME_UPPER padding calculation#27249
Merged
fs-eire merged 2 commits intomicrosoft:mainfrom Feb 11, 2026
Merged
Fix WebGPU Conv auto_pad=SAME_UPPER padding calculation#27249fs-eire merged 2 commits intomicrosoft:mainfrom
fs-eire merged 2 commits intomicrosoft:mainfrom
Conversation
The WebGPU Conv and ConvTranspose operators were producing incorrect results when using auto_pad=SAME_UPPER with strides > 1. Root cause: The head padding values were being unnecessarily recalculated after InferPadsAndOutputShape() had already computed the correct values. The recalculation formula could produce incorrect results. Fix: Simply use pads[0] and pads[1] directly, which already contain the correct head padding values computed upstream. This matches the behavior of the TypeScript implementation. Fixes microsoft#26734
Contributor
|
/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 4 pipeline(s). |
Contributor
|
The change itself looks good to me. Could you please add a test case in onnxruntime\test\providers\cpu\nn\conv_op_test.cc ? |
Add test case Conv2D_AutoPad_SAME_UPPER_Stride2 that verifies correct asymmetric padding calculation when auto_pad=SAME_UPPER and stride>1. This catches the off-by-one padding bug fixed in this PR.
Contributor
Author
|
@fs-eire Added regression test |
Contributor
|
/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 4 pipeline(s). |
fs-eire
approved these changes
Feb 10, 2026
Contributor
Author
|
Thanks for the review and guidance on adding the test! |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
The WebGPU Conv and ConvTranspose operators were producing incorrect results when using auto_pad=SAME_UPPER with strides > 1.
Root cause: The head padding values were being unnecessarily recalculated after InferPadsAndOutputShape() had already computed the correct values. The recalculation formula could produce incorrect results.
Fix: Simply use pads[0] and pads[1] directly, which already contain the correct head padding values computed upstream. This matches the behavior of the TypeScript implementation.
Fixes #26734