dnn cann backend: add hardswish, layernorm and instasnce norm for cann and bug fix #24462
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
|
Will finalize this PR after the merge of #24409. |
12 tasks
asmorkalov
pushed a commit
that referenced
this pull request
Nov 7, 2023
dnn onnx: add instance norm layer #24378 Resolves #24377 Relates #24092 (comment) | Perf | multi-thread | single-thread | | - | - | - | | x: [2, 64, 180, 240] | 3.95ms | 11.12ms | Todo: - [x] speed up by multi-threading - [x] add perf - [x] add backend: OpenVINO - [x] add backend: CUDA - [x] add backend: OpenCL (no fp16) - [ ] add backend: CANN (will be done via #24462) ### 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 ``` force_builders=Linux OpenCL,Win64 OpenCL,Custom buildworker:Custom=linux-4 build_image:Custom=ubuntu:18.04 modules_filter:Custom=none disable_ipp:Custom=ON ```
01a16b5 to
07559e8
Compare
|
Will test this PR next week. |
|
Tests on Hardswish and LayerNormalization are passed with threshold 1e-3. However, due to the 1D mat shape problem, LayerNormalization with axis=-1 on CANN backend produces incorrect results, and InstanceNormalization on CANN backend leads to incorrect shape inference when building graph. So they are turned off for CANN backend for now. I think this PR can be merged and we leave the 1d mat shape problem to the future. |
vpisarev
approved these changes
Nov 15, 2023
11 tasks
12 tasks
IskXCr
pushed a commit
to Haosonn/opencv
that referenced
this pull request
Dec 20, 2023
dnn onnx: add instance norm layer opencv#24378 Resolves opencv#24377 Relates opencv#24092 (comment) | Perf | multi-thread | single-thread | | - | - | - | | x: [2, 64, 180, 240] | 3.95ms | 11.12ms | Todo: - [x] speed up by multi-threading - [x] add perf - [x] add backend: OpenVINO - [x] add backend: CUDA - [x] add backend: OpenCL (no fp16) - [ ] add backend: CANN (will be done via opencv#24462) ### 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 ``` force_builders=Linux OpenCL,Win64 OpenCL,Custom buildworker:Custom=linux-4 build_image:Custom=ubuntu:18.04 modules_filter:Custom=none disable_ipp:Custom=ON ```
IskXCr
pushed a commit
to Haosonn/opencv
that referenced
this pull request
Dec 20, 2023
…n and bug fix (opencv#24462) * add hardswish for cann * gemm cann bug fix * fix indentation * cann: add layer norm * cann: add instance norm * add supportBackend * cann: layer norm does not support axis=-1 due to 1d mat issue * disable instance norm for now * fix doc * remove tensor desc initialization for 1D tensor
thewoz
pushed a commit
to thewoz/opencv
that referenced
this pull request
Jan 4, 2024
dnn onnx: add instance norm layer opencv#24378 Resolves opencv#24377 Relates opencv#24092 (comment) | Perf | multi-thread | single-thread | | - | - | - | | x: [2, 64, 180, 240] | 3.95ms | 11.12ms | Todo: - [x] speed up by multi-threading - [x] add perf - [x] add backend: OpenVINO - [x] add backend: CUDA - [x] add backend: OpenCL (no fp16) - [ ] add backend: CANN (will be done via opencv#24462) ### 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 ``` force_builders=Linux OpenCL,Win64 OpenCL,Custom buildworker:Custom=linux-4 build_image:Custom=ubuntu:18.04 modules_filter:Custom=none disable_ipp:Custom=ON ```
thewoz
pushed a commit
to thewoz/opencv
that referenced
this pull request
Jan 4, 2024
…n and bug fix (opencv#24462) * add hardswish for cann * gemm cann bug fix * fix indentation * cann: add layer norm * cann: add instance norm * add supportBackend * cann: layer norm does not support axis=-1 due to 1d mat issue * disable instance norm for now * fix doc * remove tensor desc initialization for 1D tensor
Merged
thewoz
pushed a commit
to thewoz/opencv
that referenced
this pull request
May 29, 2024
dnn onnx: add instance norm layer opencv#24378 Resolves opencv#24377 Relates opencv#24092 (comment) | Perf | multi-thread | single-thread | | - | - | - | | x: [2, 64, 180, 240] | 3.95ms | 11.12ms | Todo: - [x] speed up by multi-threading - [x] add perf - [x] add backend: OpenVINO - [x] add backend: CUDA - [x] add backend: OpenCL (no fp16) - [ ] add backend: CANN (will be done via opencv#24462) ### 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 ``` force_builders=Linux OpenCL,Win64 OpenCL,Custom buildworker:Custom=linux-4 build_image:Custom=ubuntu:18.04 modules_filter:Custom=none disable_ipp:Custom=ON ```
thewoz
pushed a commit
to thewoz/opencv
that referenced
this pull request
May 29, 2024
…n and bug fix (opencv#24462) * add hardswish for cann * gemm cann bug fix * fix indentation * cann: add layer norm * cann: add instance norm * add supportBackend * cann: layer norm does not support axis=-1 due to 1d mat issue * disable instance norm for now * fix doc * remove tensor desc initialization for 1D tensor
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Resolves #24154
Resolves opencv/ci-gha-workflow#120 (comment)
New CANN operator added in this PR:
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.