opencv/modules/dnn
Abduragim Shtanchaev efbc9f0b66
Merge pull request #25861 from Abdurrahheem:ash/torch-attention-export-fix-4x
Merge pull request #25861 from Abdurrahheem:ash/torch-attention-export-fix-4x

Support for Unflatten operation requred by Attention layer - 4.x #25861

### Pull Request Readiness Checklist

All test data and models for PR are located [#1190](https://github.com/opencv/opencv_extra/pull/1190)

This PR fixes issue reised when importing batched  vanilla `Attention` layer from `PyTorch` via ONNX. Currently batched version of `Attention` layer in PyTorch [has unflatten operation inside](e3b3431c42/torch/nn/functional.py (L5500C17-L5500C31)). `unflatten` operation causes issue in `reshape` layer (see the Reshape_2 in the graph below) due to incorrect output of `slice` layer. This PR particularly fixes `slice` and `concat` layers to handle `unflatten` operation. 


<img width="673" alt="image" src="https://github.com/opencv/opencv/assets/44877829/5b612b31-657a-47f1-83a4-0ac35a950abd">


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

- [x] I agree to contribute to the project under Apache 2 License.
- [x] 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
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-07-04 16:25:31 +03:00
..
cmake Add Definition "_USE_MATH_DEFINES" for dnn plugin on Win32 build 2024-04-07 21:08:09 +09:00
include/opencv2 Merge pull request #25810 from fengyuentau:python/fix_parsing_3d_mat_in_dnn 2024-07-04 08:33:20 +03:00
misc Merge pull request #25810 from fengyuentau:python/fix_parsing_3d_mat_in_dnn 2024-07-04 08:33:20 +03:00
perf Fix proto and weights mess in dnn performance tests. 2024-02-07 09:16:09 +03:00
src Merge pull request #25861 from Abdurrahheem:ash/torch-attention-export-fix-4x 2024-07-04 16:25:31 +03:00
test Merge pull request #25861 from Abdurrahheem:ash/torch-attention-export-fix-4x 2024-07-04 16:25:31 +03:00
CMakeLists.txt Merge pull request #25230 from hanliutong/rvv-conv 2024-03-31 16:47:06 +03:00