NotificationsYou must be signed in to change notification settings
Fork56.4k
Star85.3k

Support for`Unflatten` operation requred by`Attention` layer#25851

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Jump to bottom

Closed

Abdurrahheem wants to merge1 commit intoopencv:5.xfromAbdurrahheem:ash/torch-attention-export-fix

Closed

Support for`Unflatten` operation requred by`Attention` layer#25851

Abdurrahheem wants to merge1 commit intoopencv:5.xfromAbdurrahheem:ash/torch-attention-export-fix

Conversation

Copy link

Contributor

Abdurrahheem commentedJul 2, 2024

Pull Request Readiness Checklist

All test data and models for PR are located#1188

This PR fixes issue reised when importing batched vanillaAttention layer fromPyTorch via ONNX. Currently batched version ofAttention layer in PyTorchhas unflatten operation inside.unflatten operation causes issue inreshape layer (see the Reshape_2 in the graph below) due to incorrect output ofslice layer. This PR particularly fixesslice andconcat layers to handleunflatten operation.

See details athttps://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

I agree to contribute to the project under Apache 2 License.
To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
The PR is proposed to the proper branch
There is a reference to the original bug report and related work
There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
The feature is well documented and sample code can be built with the project CMake