Skip to content

Add celu, hardsigmoid, selu, thresholdedrelu layers#21190

Merged
opencv-pushbot merged 1 commit intoopencv:4.xfrom
rogday:acts
Dec 18, 2021
Merged

Add celu, hardsigmoid, selu, thresholdedrelu layers#21190
opencv-pushbot merged 1 commit intoopencv:4.xfrom
rogday:acts

Conversation

@rogday
Copy link
Copy Markdown
Member

@rogday rogday commented Dec 3, 2021 •
edited by alalek
Loading

Tests are coming to 4.x with #21088

ONNX reference:
Celu, HardSigmoid, Selu, ThresholdedReLU

Note:
I removed initWebnnAPI blocks from layers, which already derive desired functionality from BaseDefaultFunctor. (intoduced in #20406)

Pull Request Readiness Checklist

See details at https://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 other license that is incompatible with OpenCV
  • The PR is proposed to proper branch
  • There is reference to 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
force_builders=Custom,Custom Win,Custom Mac

buildworker:Custom=linux-4,linux-6
Xbuild_image:Custom=ubuntu-cuda:16.04
build_image:Custom=ubuntu-cuda:18.04

Xbuild_image:Custom=ubuntu-openvino-2021.4.2:20.04
Xbuild_image:Custom=ubuntu-openvino-2021.3.0:20.04
Xbuild_image:Custom=ubuntu-openvino-2021.2.0:20.04
Xbuild_image:Custom=ubuntu-openvino-2020.3.0:16.04
build_image:Custom Win=openvino-2021.4.2
Xbuild_image:Custom Win=openvino-2021.3.0-vc16
build_image:Custom Mac=openvino-2021.4.0

test_modules:Custom=dnn,python2,python3,java
test_modules:Custom Win=dnn,python2,python3,java
test_modules:Custom Mac=dnn,python2,python3,java

Xbuildworker:Custom=linux-1
Xtest_opencl:Custom=ON
Xtest_bigdata:Custom=1
Xtest_filter:Custom=*

test_bigdata:Custom Win=1
buildworker:Custom Win=windows-3
test_opencl:Custom Win=ON
test_filter:Custom Win=*

YashasSamaga
YashasSamaga reviewed Dec 3, 2021
View reviewed changes
@rogday rogday marked this pull request as draft December 6, 2021 10:58
@rogday rogday marked this pull request as ready for review December 6, 2021 11:14
alalek
alalek approved these changes Dec 13, 2021
View reviewed changes
Copy link
Copy Markdown
Member

@alalek alalek left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you 👍

@alalek
Copy link
Copy Markdown
Member

alalek commented Dec 17, 2021

Need to rebase PR.

@opencv-pushbot opencv-pushbot merged commit 30df77f into opencv:4.x Dec 18, 2021
@rogday rogday deleted the acts branch December 18, 2021 14:41
@alalek alalek mentioned this pull request Dec 30, 2021
Merged
@alalek alalek mentioned this pull request Feb 22, 2022
Merged
@Noklm
Copy link
Copy Markdown

Noklm commented Mar 16, 2023

If I'm not wrong these layers are merged in opencv 4.7.0 ? Are they implemented only for CUDA backends ? or are they available on default CPU ? Because when I try to load my rtmdet.onnx not far away from a yolo I get the error below:

Can't create layer "/backbone/stage1/stage1.1/attention/act/HardSigmoid_output_0" of type "HardSigmoid" in function 'getLayerInstance'

Thank you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@alalek alalek alalek approved these changes

+1 more reviewer

@YashasSamaga YashasSamaga YashasSamaga left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

@alalek alalek

Labels

category: dnn feature

Projects

None yet

Milestone

4.5.5

Development

Successfully merging this pull request may close these issues.

5 participants

@rogday @alalek @Noklm @YashasSamaga @opencv-pushbot