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
Fix issue #25077#25100
Fixes https://github.com/opencv/opencv/issues/25077
### 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
Fixes#24974 support HardSwishInt8 #24985
As given very clearly in the issue #24974 I made the required 2 changes to implement HardSwish Layer in INT8. Requesting comments.
resolves https://github.com/opencv/opencv/issues/24974
- [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
- [ ] 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
Co-authored-by: Dhanwanth1803 <dhanwanthvarala@gmail,com>
Vulkan backend for NaryEltwiseLayer in DNN module #24768
We improve Vulkan backend for ``NaryEltwiseLayer`` in DNN module by:
- add a basic framework for Vulkan backend in ``NaryEltwiseLayer``
- add a compute shader for binary forwarding (an imitation of what has been done in native OpenCV backend including broadcasting and eltwise-operation)
- typo fixed:
- Wrong info output in ``context.cpp``
Currently, our implementation (or all layers supporting Vulkan backend) runs pretty slow on discrete GPUs basically due to IO cost in function ``copyToHost``, and we are going to fix that by
- find out the best ``VkMemoryProperty`` for various discrete GPUs
- prevent ``copyToHost`` in middle layers during forwarding, (i.e keep data in GPU memory)
### 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
- [ ] There is a reference to the 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
Co-authored-by: IskXCr <IskXCr@outlook.com>
Handle warnings in loongson-related code #24925
See https://github.com/fengyuentau/opencv/actions/runs/7665377694/job/20891162958#step:14:16
Warnings needs to be handled before we add the loongson server to our CI.
### 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.
- [ ] The feature is well documented and sample code can be built with the project CMake
Removed all pre-C++11 code, workarounds, and branches #23736
This removes a bunch of pre-C++11 workrarounds that are no longer necessary as C++11 is now required.
It is a nice clean up and simplification.
* No longer unconditionally #include <array> in cvdef.h, include explicitly where needed
* Removed deprecated CV_NODISCARD, already unused in the codebase
* Removed some pre-C++11 workarounds, and simplified some backwards compat defines
* Removed CV_CXX_STD_ARRAY
* Removed CV_CXX_MOVE_SEMANTICS and CV_CXX_MOVE
* Removed all tests of CV_CXX11, now assume it's always true. This allowed removing a lot of dead code.
* Updated some documentation consequently.
* Removed all tests of CV_CXX11, now assume it's always true
* Fixed links.
---------
Co-authored-by: Maksim Shabunin <maksim.shabunin@gmail.com>
Co-authored-by: Alexander Smorkalov <alexander.smorkalov@xperience.ai>
python: accept path-like objects wherever file names are expected #24773
Merry Christmas, all 🎄
Implements #15731
Support is enabled for all arguments named `filename` or `filepath` (case-insensitive), or annotated with `CV_WRAP_FILE_PATH`.
Support is based on `PyOS_FSPath`, which is available in Python 3.6+. When running on older Python versions the arguments must have a `str` value as before.
### 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
- [ ] 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
dnn onnx: add group norm layer #24610
dnn onnx: add group norm layer
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
### 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
- [ ] 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
Co-authored-by: fengyuentau <yuantao.feng@opencv.org.cn>
Replace interactive batched Matrix Multiply. #24812
This PR replaces iterative batch matrix multiplication which `FastGemmBatch` in Einsum layer.
### 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
dnn: no layer norm fusion if axes.back() is not the axis of last dimension #24808
Merge with https://github.com/opencv/opencv_extra/pull/1137
Resolves https://github.com/opencv/opencv/issues/24797
### 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.
- [ ] The feature is well documented and sample code can be built with the project CMake
dnn onnx: add mod #24765
Resolves https://github.com/opencv/opencv/issues/23174
TODO:
- [x] enable some conformance tests
- [x] add backends
- [x] CANN
- [x] OpenVINO
- [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
dnn onnx: support constaint inputs in einsum importer #24753
Merge with https://github.com/opencv/opencv_extra/pull/1132.
Resolves https://github.com/opencv/opencv/issues/24697
Credits to @LaurentBerger.
---
This is a workaround. I suggest to get input shapes and calculate the output shapes in `getMemoryShapes` so as to keep the best compatibility. It is not always robust getting shapes during the importer stage and we should avoid that as much as possible.
### 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
Fixes#22747. Support [crop] configuration for DarkNet #24384
Request for comments. This is my first PR.
**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1112
resolves https://github.com/opencv/opencv/issues/22747
- [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
- [ ] 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
Try to enable Winograd by default in FP32 mode and disable it by default in FP16 mode #24709
Hopefully, it will resolve regressions since 4.8.1 (see also https://github.com/opencv/opencv/pull/24587)
### 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 another license that is incompatible with OpenCV
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the 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
dnn: add attention layer #24476Resolves#24609
Merge with: https://github.com/opencv/opencv_extra/pull/1128.
Attention operator spec from onnxruntime: https://github.com/microsoft/onnxruntime/blob/v1.16.1/docs/ContribOperators.md#com.microsoft.Attention.
TODO:
- [x] benchmark (before this PR vs. with this PR vs. ORT).
- [x] Layer fusion: Take care Slice with end=INT64_MAX.
- [x] Layer fusion: match more potential attention (VIT) patterns.
- [x] Single-head attention is supported.
- [x] Test AttentionSubgraph fusion.
- [x] Add acc tests for VIT_B_32 and VitTrack
- [x] Add perf tests for VIT_B_32 and VitTrack
## Benchmarks
Platform: Macbook Air M1.
### Attention Subgraph
Input scale: [1, 197, 768].
| | mean (ms) | median (ms) | min (ms) |
| ---------------------- | --------- | ----------- | -------- |
| w/ Attention (this PR) | 3.75 | 3.68 | 3.22 |
| w/o Attention | 9.06 | 9.01 | 8.24 |
| ORT (python) | 4.32 | 2.63 | 2.50 |
### ViTs
All data in millisecond (ms).
| ViTs | With Attention | Without Attention | ORT |
| -------- | -------------- | ----------------- | ------ |
| vit_b_16 | 302.77 | 365.35 | 109.70 |
| vit_b_32 | 89.92 | 116.22 | 30.36 |
| vit_l_16 | 1593.32 | 1730.74 | 419.92 |
| vit_l_32 | 468.11 | 577.41 | 134.12 |
| VitTrack | 3.80 | 3.87 | 2.25 |
### 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
Add blobrecttoimage #24539
### Pull Request Readiness Checklist
resolves https://github.com/opencv/opencv/issues/14659
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 #14659
- [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
dnn: refactor ONNX MatMul with fastGemm #24694
Done:
- [x] add backends
- [x] CUDA
- [x] OpenVINO
- [x] CANN
- [x] OpenCL
- [x] Vulkan
- [x] add perf tests
- [x] const B case
### Benchmark
Tests are done on M1. All data is in milliseconds (ms).
| Configuration | MatMul (Prepacked) | MatMul | InnerProduct |
| - | - | - | - |
| A=[12, 197, 197], B=[12, 197, 64], trans_a=0, trans_b=0 | **0.39** | 0.41 | 1.33 |
| A=[12, 197, 64], B=[12, 64, 197], trans_a=0, trans_b=0 | **0.42** | 0.42 | 1.17 |
| A=[12, 50, 64], B=[12, 64, 50], trans_a=0, trans_b=0 | **0.13** | 0.15 | 0.33 |
| A=[12, 50, 50], B=[12, 50, 64], trans_a=0, trans_b=0 | **0.11** | 0.13 | 0.22 |
| A=[16, 197, 197], B=[16, 197, 64], trans_a=0, trans_b=0 | **0.46** | 0.54 | 1.46 |
| A=[16, 197, 64], B=[16, 64, 197], trans_a=0, trans_b=0 | **0.46** | 0.95 | 1.74 |
| A=[16, 50, 64], B=[16, 64, 50], trans_a=0, trans_b=0 | **0.18** | 0.32 | 0.43 |
| A=[16, 50, 50], B=[16, 50, 64], trans_a=0, trans_b=0 | **0.15** | 0.25 | 0.25 |
### 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
Make default axis of softmax in onnx "-1" without opset option #24613
Try to solve problem: https://github.com/opencv/opencv/pull/24476#discussion_r1404821158
**ONNX**
`opset <= 11` use 1
`else` use -1
**TensorFlow**
`TF version = 2.x` use -1
`else` use 1
**Darknet, Caffe, Torch**
use 1 by definition
Classify and extend convolution and depthwise performance tests #24547
This PR aims to:
1. Extend the test cases from models: `YOLOv5`, `YOLOv8`, `EfficientNet`, `YOLOX`, `YuNet`, `SFace`, `MPPalm`, `MPHand`, `MPPose`, `ViTTrack`, `PPOCRv3`, `CRNN`, `PPHumanSeg`. (371 new test cases are added)
2. Classify the existing convolution performance test to below cases
- CONV_1x1
- CONV_3x3_S1_D1 (winograd)
- CONV
- DEPTHWISE
3. Reduce unnecessary test cases by follow 3 rules (366 test cases are pruned):
(i). For all tests, except for pad and bias related parameters, all other parameters are the same. Only one case can be reserved.
(ii). When the only difference is the channel of input shape, and other parameters are the same. Only one case can be reserved in each range `[1, 3], [4, 7], [8, 15], [16, 31], [32, 63], [64, 127], [128, 255], [256, 511], [512, 1023], [1024, 2047], [2048, 4095]`
(iii). When the only difference is the width and height of input shape, and other parameters are the same. Only one case can be reserved in each range `[1, 31], [32, 63], [64, 95]... `
> **Reproduced**: 1. follow step in https://github.com/alalek/opencv/commit/dnn_dump_conv_kernels to dump all convolution cases from new models. (declared flops may not right, need to be checked manually) 2 and 3. Use the script from python code [classify conv.txt](https://github.com/opencv/opencv/files/13522228/classify.conv.txt)
**Performance test result on Apple M2**
**Test result details**: [M2.md](https://github.com/opencv/opencv/files/13379189/M2.md)
**Additional test result details with FP16**: [m2_results_with_fp16.zip](https://github.com/opencv/opencv/files/13491070/m2_results_with_fp16.zip)
**Brief summary for 4.8.1 vs 4.7.0 or 4.6.0**:
1. `CONV_1x1_S1_D1` dropped significant with small or large input shape.
2. `DEPTHWISE_5x5 ` dropped a little compared with 4.7.0.
---
**Performance test result on [Intel Core i7-12700K](https://www.intel.com/content/www/us/en/products/sku/134594/intel-core-i712700k-processor-25m-cache-up-to-5-00-ghz/specifications.html)**: 8 Performance-cores (3.60 GHz, turbo up to 4.90 GHz), 4 Efficient-cores (2.70 GHz, turbo up to 3.80 GHz), 20 threads.
**Test result details**: [INTEL.md](https://github.com/opencv/opencv/files/13374093/INTEL.md)
**Brief summary for 4.8.1 vs 4.5.5**:
1. `CONV_5x5_S1_D1` dropped significant.
2. `CONV_1x1_S1_D1`, `CONV_3x3_S1_D1`, `DEPTHWISE_3x3_S1_D1`, `DEPTHWISW_3x3_S2_D1` dropped with small input shape.
---
TODO:
- [x] Perform tests on arm with each opencv version
- [x] Perform tests on x86 with each opencv version
- [x] Split each test classification with single test config
- [x] test enable fp16
Add test for YoloX Yolo v6 and Yolo v8 #24611
This PR adds test for YOLOv6 model (which was absent before)
The onnx weights for the test are located in this PR [ #1126](https://github.com/opencv/opencv_extra/pull/1126)
### 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
- [ ] 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
dnn cuda: support Sub #24647
Related https://github.com/opencv/opencv/issues/24606#issuecomment-1837390257
### 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
dnn onnx graph simplifier: handle optional inputs of Slice #24655
Resolves https://github.com/opencv/opencv/issues/24609
### 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
CSBVision
Yuantao Feng
Laurent Berger
Dhanwanth1803
Alexander Smorkalov
fengyuentau
Haosonn
Alexander Alekhin
Sean McBride
Abduragim
Dhanwanth1803
Stefan Dragnev
jimmylaw21
Abduragim Shtanchaev
cudawarped
Alexander Alekhin
Dmitry Kurtaev
Vadim Pisarevsky
llh721113
Wanli