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
dnn: add openvino, opencl and cuda backends for layer normalization layer #24552
Conversation
Oh, wait a minute, why we need continue development of LayerNorm layer while there is a new InstanceNorm layer #24378? I expected that LayerNorm should be removed completely. |
We agreed previously in the meeting that we keep two classes, and they share similar kernels for CPU. |
Let's see the final state. As far as I remember the only difference between them is scalar or vector scale/bias values, |
Indexing is also different as well. For Instance Normalization, its indexing is like |
8ab8f52
to
9f0ce10
Compare
dnn: add openvino, opencl and cuda backends for layer normalization layer opencv#24552 Merge after opencv#24544. Todo: - [x] openvino - [x] opencl - [x] cuda ### 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
Merge after #24544.
Todo:
Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
Patch to opencv_extra has the same branch name.