DNN/CUDA: make 'abcd op 1b11' broadcast eltwise operator support cuda #23528
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@WanliZhong In case if you get the results with OpenCV perf tests then you can use |
|
Hi @asmorkalov, thanks for your reminder. I will tell Wanli how to do this performance test. |
|
Thanks, @asmorkalov . I have updated the summary results run this script to generate result .\bin\opencv_perf_dnn.exe '--gtest_filter=CUDA/Layer_NaryEltwise.*/*:CUDA/Layer_NaryEltwise/*.*' --gtest_output=xml:../tmp/1th.xml --perf_threads=1use this script to generate summary python ../modules/ts/misc/summary.py -m min 1th.xml 0th.xml -o markdownresult
|
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR will fix #23278
Current implement is a temp impl. I will try to make more eltwise broadcast cases support CUDA.
The inference time of model is from 26.7651 ms to 17.8416 ms.
perf_test result
run this script to generate result
use this script to generate summary
result
Layer by layer data:
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.