-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[js/webgpu] Fix max pool shape end with 0 #21559
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If I understand correctly, the error is caused by the 2d shapes of kernelShape
/strides
/dilations
while the 1d shapes are expected since it's pool1d instead of pool2d.
Based on that, I think the right fixing should be passing the right shape to attributes in c++ side instead of modifying it in js. See code here https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/providers/js/operators/pool.h#L29-L32, it will always generate a 2d array to attributes.dilations
/attributes.kernel_shape
/attributes.strides
. To get the right attribute shapes, you can refer to conv's implementation here https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/providers/js/operators/conv.h#L30-L45 which supports any expected shapes.
Thanks @qjia7, updated. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks!
@guschmue @fs-eire @satyajandhyala Please take a look, thanks.
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline |
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Linux Android Emulator QNN CI Pipeline |
/azp run Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline |
Azure Pipelines successfully started running 1 pipeline(s). |
2 similar comments
Azure Pipelines successfully started running 1 pipeline(s). |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline |
No pipelines are associated with this pull request. |
/azp run Windows GPU CUDA CI Pipeline, Windows GPU DML CI Pipeline, Windows GPU Doc Gen CI Pipeline |
No pipelines are associated with this pull request. |
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline |
/azp run Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Big Models,Linux Android Emulator QNN CI Pipeline,Android CI Pipeline,iOS CI Pipeline |
/azp run ONNX Runtime React Native CI Pipeline |
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
1 similar comment
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline |
/azp run Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline |
/azp run Big Models,Linux Android Emulator QNN CI Pipeline,Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline |
Azure Pipelines successfully started running 1 pipeline(s). |
1 similar comment
Azure Pipelines successfully started running 1 pipeline(s). |
Azure Pipelines successfully started running 1 pipeline(s). |
This PR is replaced by #21698 because the build pipeline failed to trigger. |
Bug: #21386
Description
Motivation and Context