mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-11-27 20:50:25 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
Open Source Computer Vision Library
33,930 Commits 6 Branches 126 Tags 3 GiB
C++ 87%
C 3.4%
Python 2.8%
CMake 2.1%
Java 1.6%
Other 2.9%
5aa5c39210
Go to file
Yuantao Feng 5aa5c39210
Merge pull request #25076 from fengyuentau:improve_attention 
dnn: try improving performance of Attention layer #25076

Checklist:

- [x] Use `Mat` over `Mat::zeros` for temporary buffer in forward
- [x] Use layer internal buffer over temporary Mat buffer
- [x] Try a single fastGemmBatch on the Q/K/V calculation

Performance:

Performance test case is `Layer_Attention.VisionTransformer/0`, which has input of shape {1, 197, 768}, weight of shape {768, 2304} and bias {2304}.

Data is in millisecond.

| | macOS 14.2.1, Apple M1 | Ubuntu 22.04.2, Intel i7 12700K |
| - | - | - |
| Current | 10.96 | 1.58 |
| w/ Mat | 6.27 | 1.41 |
| w/ Internals | 5.87 | 1.38 |
| w/ fastGemmBatch | 6.12 | 2.14 |


### Pull Request Readiness Checklist

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
2024-02-28 16:47:08 +03:00
.github Added job to test with real hardware. 2024-01-31 15:05:19 +03:00
3rdparty Fixed lcense and readme filenames after TBB update 2024-02-27 12:06:55 +03:00
apps Add missing <sstream> includes 2023-09-05 22:04:26 +03:00
cmake Disable fp16 instructions detection on Windows ARM64 because of build issues #25052. 2024-02-22 12:52:26 +03:00
data Merge pull request #22727 from su77ungr:patch-1 2022-11-17 06:54:25 +00:00
doc Merge pull request #23018 from stopmosk:move-aruco-tutorial 2024-02-26 14:57:46 +03:00
include exclude opencv_contrib modules 2020-02-26 15:12:45 +03:00
modules Merge pull request #25076 from fengyuentau:improve_attention 2024-02-28 16:47:08 +03:00
platforms Merge pull request #25084 from EDVTAZ:emscripten-3.1.54-compat 2024-02-26 10:30:56 +03:00
samples Merge pull request #25095 from cabelo:yolov8x 2024-02-27 15:34:15 +03:00
.editorconfig add .editorconfig 2018-10-11 17:57:51 +00:00
.gitattributes cmake: generate and install ffmpeg-download.ps1 2018-06-09 13:19:48 +03:00
.gitignore Merge pull request #17165 from komakai:objc-binding 2020-06-08 18:32:53 +00:00
CMakeLists.txt Merge pull request #24934 from GengGode:fix 2024-02-02 15:48:42 +03:00
CONTRIBUTING.md migration: github.com/opencv/opencv 2016-07-12 12:51:12 +03:00
COPYRIGHT copyright: 2023 (update) 2023-01-09 09:49:22 +00:00
LICENSE Merge pull request #18073 from vpisarev:apache2_license 2020-08-17 11:49:11 +00:00
README.md Update README.md - remove IndieGoGo, add Support OpenCV page 2024-01-10 10:18:52 -08:00
SECURITY.md Updated PGP key for security reports 2023-04-19 19:16:55 +03:00

README.md

OpenCV: Open Source Computer Vision Library

Resources

Contributing

Please read the contribution guidelines before starting work on a pull request.

Summary of the guidelines:

  • One pull request per issue;
  • Choose the right base branch;
  • Include tests and documentation;
  • Clean up "oops" commits before submitting;
  • Follow the coding style guide.

Additional Resources