Commit Graph

2261 Commits

Author SHA1 Message Date
Alexander Smorkalov
1c0ca41b6e
Merge pull request #24371 from hanliutong:clean-up
Clean up the obsolete API of Universal Intrinsic
2023-10-20 12:50:26 +03:00
andrewerf
b44cb33d2f
Merge pull request #21066 from andrewerf:21052-openvino-native-onnx
Native ONNX to Inference Engine backend #21066

Resolves #21052

### 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 other license that is incompatible with OpenCV
- [x] The PR is proposed to proper branch
- [x] 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
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-10-20 11:49:27 +03:00
fengyuentau
f2ef81a179 fp16 support for gather elements 2023-10-19 14:44:12 +08:00
Kumataro
6e4280ea81
Merge pull request #24372 from Kumataro:fix24369
Supporting protobuf v22 and later(with abseil-cpp/C++17) #24372

fix https://github.com/opencv/opencv/issues/24369
related https://github.com/opencv/opencv/issues/23791

1. This patch supports external protobuf v22 and later, it required abseil-cpp and c++17.
    Even if the built-in protobuf is upgraded to v22 or later, 
    the dependency on abseil-cpp and the requirement for C++17 will continue.
2. Some test for caffe required patched protobuf, so this patch disable them.

This patch is tested by following libraries.
-  Protobuf:                    /usr/local/lib/libprotobuf.so (4.24.4)
-  abseil-cpp:                YES (20230125)

### 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
2023-10-19 08:45:08 +03:00
Aser Atawya
240b245105
Merge pull request #24092 from Aser-Abdelfatah:GSoC_Support_GatherElements_ONNX
GSoC Add ONNX Support for GatherElements #24092

Merge with: https://github.com/opencv/opencv_extra/pull/1082
Adds support to the ONNX operator GatherElements [operator docs](https://github.com/onnx/onnx/blob/main/docs/Operators.md#GatherElements)
Added tests to opencv_extra at pull request https://github.com/opencv/opencv_extra/pull/1082

### 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
2023-10-18 10:41:47 +03:00
alexlyulkov
014e8485b5
Merge pull request #24367 from alexlyulkov:al/fixed-cumsum-inplace-flag
Fixed CumSum layer inplace flag #24367

When exclusive is false:
dst[i] = dst[i-1] + src[i]
When exclusive is true:
dst[i] = dst[i-1] + src[i-1]
So CumSum layer can be inplace only when exclusive flag is false.
2023-10-18 09:21:40 +03:00
Liutong HAN
a287605c3e Clean up the Universal Intrinsic API. 2023-10-13 19:23:30 +08:00
Yuantao Feng
0507043a55
Merge pull request #24386 from fengyuentau:fix_dtype_nary_eltwise
dnn: fix inconsistent input dtype for nary eltwise layers #24386

Resolves https://github.com/opencv/opencv/issues/24385
Merge with https://github.com/opencv/opencv_extra/pull/1107
Relates https://github.com/opencv/opencv/pull/24092#discussion_r1353964405

### 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
2023-10-13 11:56:18 +03:00
Alexander Smorkalov
58285e5468
Merge pull request #24359 from asmorkalov:as/FastNeuralStyle_eccv16_tuning
Tuned threshold for FastNeuralStyle_eccv16 test
2023-10-13 10:29:41 +03:00
Yuantao Feng
590f150d5e
dnn: hotfixes for fast gemm (#24315)
* remove Conformance from test names

* integrate neon optimization into default

* quick fix: define CV_NEON_AARCH64 0 for non NEON platforms

* remove var batch that leads to memory leak

* put neon code back to fast_gemm_kernels.simd

* reorganize code to reduce duplicate code
2023-10-07 21:48:44 +03:00
Sean McBride
5fb3869775
Merge pull request #23109 from seanm:misc-warnings
* Fixed clang -Wnewline-eof warnings
* Fixed all trivial clang -Wextra-semi and -Wc++98-compat-extra-semi warnings
* Removed trailing semi from various macros
* Fixed various -Wunused-macros warnings
* Fixed some trivial -Wdocumentation warnings
* Fixed some -Wdocumentation-deprecated-sync warnings
* Fixed incorrect indentation
* Suppressed some clang warnings in 3rd party code
* Fixed QRCodeEncoder::Params documentation.

---------

Co-authored-by: Alexander Smorkalov <alexander.smorkalov@xperience.ai>
2023-10-06 13:33:21 +03:00
HAN Liutong
07bf9cb013
Merge pull request #24325 from hanliutong:rewrite
Rewrite Universal Intrinsic code: float related part #24325

The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API.

The series of PRs is listed below:
#23885 First patch, an example
#23980 Core module
#24058 ImgProc module, part 1
#24132 ImgProc module, part 2
#24166 ImgProc module, part 3
#24301 Features2d and calib3d module
#24324 Gapi module

This patch (hopefully) is the last one in the series. 

This patch mainly involves 3 parts
1. Add some modifications related to float (CV_SIMD_64F)
2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`, 
    then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD`
3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments
    - Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....`
    - Some blocks can not be rewrited directly. (Not commented in the source code, just listed here)
      - ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct)
      - ./modules/imgproc/src/color_lab.cpp (Array of vector type)
      - ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type)
      - ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`)
      These algorithms will need to be redesigned to accommodate scalable backends.

### 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
2023-10-05 17:57:25 +03:00
Dmitry Kurtaev
2c92eb3175 Enable more tests for OpenVINO 2023.0 2023-10-05 12:51:55 +03:00
Alexander Smorkalov
33d64d0491 Tuned threshold for FastNeuralStyle_eccv16 test for systems without AVX2. 2023-10-04 16:19:13 +03:00
Wanli
62b5470b78
Merge pull request #24298 from WanliZhong:extend_perf_net_test
Extend performance test models #24298

**Merged With https://github.com/opencv/opencv_extra/pull/1095**

This PR aims to extend the performance tests. 

- **YOLOv5** for object detection
- **YOLOv8** for object detection
- **EfficientNet** for classification

Models from OpenCV Zoo:

- **YOLOX** for object detection
- **YuNet** for face detection
- **SFace** for face recognization
- **MPPalm** for palm detection
- **MPHand** for hand landmark
- **MPPose** for pose estimation
- **ViTTrack** for object tracking
- **PPOCRv3** for text detection
- **CRNN** for text recognization
- **PPHumanSeg** for human segmentation

If other models should be added, **please leave some comments**. Thanks!



Build opencv with script:
```shell
-DBUILD_opencv_python2=OFF
-DBUILD_opencv_python3=OFF
-DBUILD_opencv_gapi=OFF
-DINSTALL_PYTHON_EXAMPLES=OFF
-DINSTALL_C_EXAMPLES=OFF
-DBUILD_DOCS=OFF
-DBUILD_EXAMPLES=OFF
-DBUILD_ZLIB=OFF
-DWITH_FFMPEG=OFF
```



Performance Test on **Apple M2 CPU**
```shell
MacOS 14.0
8 threads
```

**1 thread:**
| Name of Test | 4.5.5-1th | 4.6.0-1th | 4.7.0-1th | 4.8.0-1th | 4.8.1-1th |
|--------------|:---------:|:---------:|:---------:|:---------:|:---------:|
| CRNN         |  76.244   |  76.611   |  62.534   |  57.678   |  57.238   |
| EfficientNet |    ---    |    ---    |  109.224  |  130.753  |  109.076  |
| MPHand       |    ---    |    ---    |  19.289   |  22.727   |  27.593   |
| MPPalm       |  47.150   |  47.061   |  41.064   |  65.598   |  40.109   |
| MPPose       |    ---    |    ---    |  26.592   |  32.022   |  26.956   |
| PPHumanSeg   |  41.672   |  41.790   |  27.819   |  27.212   |  30.461   |
| PPOCRv3      |    ---    |    ---    |  140.371  |  187.922  |  170.026  |
| SFace        |  43.830   |  43.834   |  27.575   |  30.653   |  26.387   |
| ViTTrack     |    ---    |    ---    |    ---    |  14.617   |  15.028   |
| YOLOX        | 1060.507  | 1061.361  |  495.816  |  533.309  |  549.713  |
| YOLOv5       |    ---    |    ---    |    ---    |  191.350  |  193.261  |
| YOLOv8       |    ---    |    ---    |  198.893  |  218.733  |  223.142  |
| YuNet        |  27.084   |  27.095   |  26.238   |  30.512   |  34.439   |
| MobileNet_SSD_Caffe         |  44.742   |  44.565   |  33.005   |  29.421   |  29.286   |
| MobileNet_SSD_v1_TensorFlow |  49.352   |  49.274   |  35.163   |  32.134   |  31.904   |
| MobileNet_SSD_v2_TensorFlow |  83.537   |  83.379   |  56.403   |  42.947   |  42.148   |
| ResNet_50                   |  148.872  |  148.817  |  77.331   |  67.682   |  67.760   |


**n threads:**
| Name of Test | 4.5.5-nth | 4.6.0-nth | 4.7.0-nth | 4.8.0-nth | 4.8.1-nth |
|--------------|:---------:|:---------:|:---------:|:---------:|:---------:|
| CRNN         |  44.262   |  44.408   |  41.540   |  40.731   |  41.151   |
| EfficientNet |    ---    |    ---    |  28.683   |  42.676   |  38.204   |
| MPHand       |    ---    |    ---    |   6.738   |  13.126   |   8.155   |
| MPPalm       |  16.613   |  16.588   |  12.477   |  31.370   |  17.048   |
| MPPose       |    ---    |    ---    |  12.985   |  19.700   |  16.537   |
| PPHumanSeg   |  14.993   |  15.133   |  13.438   |  15.269   |  15.252   |
| PPOCRv3      |    ---    |    ---    |  63.752   |  85.469   |  76.190   |
| SFace        |  10.685   |  10.822   |   8.127   |   8.318   |   7.934   |
| ViTTrack     |    ---    |    ---    |    ---    |  10.079   |   9.579   |
| YOLOX        |  417.358  |  422.977  |  230.036  |  234.662  |  228.555  |
| YOLOv5       |    ---    |    ---    |    ---    |  74.249   |  75.480   |
| YOLOv8       |    ---    |    ---    |  63.762   |  88.770   |  70.927   |
| YuNet        |   8.589   |   8.731   |  11.269   |  16.466   |  14.513   |
| MobileNet_SSD_Caffe         |  12.575   |  12.636   |  11.529   |  12.114   |  12.236   |
| MobileNet_SSD_v1_TensorFlow |  13.922   |  14.160   |  13.078   |  12.124   |  13.298   |
| MobileNet_SSD_v2_TensorFlow |  25.096   |  24.836   |  22.823   |  20.238   |  20.319   |
| ResNet_50                   |  41.561   |  41.296   |  29.092   |  30.412   |  29.339   |


Performance Test 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)
```shell
Ubuntu 22.04.2 LTS
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
```


**1 thread:**
| Name of Test | 4.5.5-1th | 4.6.0-1th | 4.7.0-1th | 4.8.0-1th | 4.8.1-1th |
|--------------|:---------:|:---------:|:---------:|:---------:|:---------:|
| CRNN         |  16.752   |  16.851   |  16.840   |  16.625   |  16.663   |
| EfficientNet |    ---    |    ---    |  61.107   |  76.037   |  53.890   |
| MPHand       |    ---    |    ---    |   8.906   |   9.969   |   8.403   |
| MPPalm       |  24.243   |  24.638   |  18.104   |  35.140   |  18.387   |
| MPPose       |    ---    |    ---    |  12.322   |  16.515   |  12.355   |
| PPHumanSeg   |  15.249   |  15.303   |  10.203   |  10.298   |  10.353   |
| PPOCRv3      |    ---    |    ---    |  87.788   |  144.253  |  90.648   |
| SFace        |  15.583   |  15.884   |  13.957   |  13.298   |  13.284   |
| ViTTrack     |    ---    |    ---    |    ---    |  11.760   |  11.710   |
| YOLOX        |  324.927  |  325.173  |  235.986  |  253.653  |  254.472  |
| YOLOv5       |    ---    |    ---    |    ---    |  102.163  |  102.621  |
| YOLOv8       |    ---    |    ---    |  87.013   |  103.182  |  103.146  |
| YuNet        |  12.806   |  12.645   |  10.515   |  12.647   |  12.711   |
| MobileNet_SSD_Caffe         |  23.556   |  23.768   |  24.304   |  22.569   |  22.602   |
| MobileNet_SSD_v1_TensorFlow |  26.136   |  26.276   |  26.854   |  24.828   |  24.961   |
| MobileNet_SSD_v2_TensorFlow |  43.521   |  43.614   |  46.892   |  44.044   |  44.682   |
| ResNet_50                   |  73.588   |  73.501   |  75.191   |  66.893   |  65.144   |


**n thread:**
| Name of Test | 4.5.5-nth | 4.6.0-nth | 4.7.0-nth | 4.8.0-nth | 4.8.1-nth | 
|--------------|:---------:|:---------:|:---------:|:---------:|:---------:|
| CRNN         |   8.665   |   8.827   |  10.643   |   7.703   |   7.743   | 
| EfficientNet |    ---    |    ---    |  16.591   |  12.715   |   9.022   |   
| MPHand       |    ---    |    ---    |   2.678   |   2.785   |   1.680   |           
| MPPalm       |   5.309   |   5.319   |   3.822   |  10.568   |   4.467   |       
| MPPose       |    ---    |    ---    |   3.644   |   6.088   |   4.608   |        
| PPHumanSeg   |   4.756   |   4.865   |   5.084   |   5.179   |   5.148   |        
| PPOCRv3      |    ---    |    ---    |  32.023   |  50.591   |  32.414   |      
| SFace        |   3.838   |   3.980   |   4.629   |   3.145   |   3.155   |       
| ViTTrack     |    ---    |    ---    |    ---    |  10.335   |  10.357   |   
| YOLOX        |  68.314   |  68.081   |  82.801   |  74.219   |  73.970   |      
| YOLOv5       |    ---    |    ---    |    ---    |  47.150   |  47.523   |    
| YOLOv8       |    ---    |    ---    |  32.195   |  30.359   |  30.267   |    
| YuNet        |   2.604   |   2.644   |   2.622   |   3.278   |   3.349   |    
| MobileNet_SSD_Caffe         |  13.005   |   5.935   |   8.586   |   4.629   |   4.713   |
| MobileNet_SSD_v1_TensorFlow |   7.002   |   7.129   |   9.314   |   5.271   |   5.213   |
| MobileNet_SSD_v2_TensorFlow |  11.939   |  12.111   |  22.688   |  12.038   |  12.086   |
| ResNet_50                   |  18.227   |  18.600   |  26.150   |  15.584   |  15.706   |
2023-10-04 13:05:32 +03:00
alexlyulkov
9bd14d5417
Merge pull request #24353 from alexlyulkov:al/fixed-cumsum-layer
Fixed CumSum dnn layer #24353

Fixes #20110

The algorithm had several errors, so I rewrote it.
Also the layer didn't work with non constant axis tensor. Fixed it.
Enabled CumSum layer tests from ONNX conformance.
2023-10-03 13:58:25 +03:00
Alexander Smorkalov
5caee5cc64 Fixed OpenCL PF16 fallback in Einsum layer. 2023-09-29 15:52:23 +03:00
Dmitry Kurtaev
c7ec0d599a
Merge pull request #23987 from dkurt:openvino_int8_backend
OpenVINO backend for INT8 models #23987

### Pull Request Readiness Checklist

TODO:
- [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069)
- [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum)
- [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039)
- [x] Single layer tests (convolution)
- [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~


Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`:
| backend | performance (median time) |
|---|---|
| OpenCV | 77.42ms |
| OpenVINO 2023.0 | 10.90ms |

CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz`

Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef

---

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
2023-09-28 16:24:43 +03:00
Alexander Smorkalov
b8d4ac589d
Merge pull request #24334 from fengyuentau:fix_24319
dnn onnx: fix not-found constant indices for Gather if shared
2023-09-28 13:08:26 +03:00
fengyuentau
7fa0493ca0 init commit 2023-09-28 11:50:21 +08:00
Yuantao Feng
307324f4ac
Merge pull request #24283 from fengyuentau:halide_tests
dnn: merge tests from test_halide_layers to test_backends #24283

Context: https://github.com/opencv/opencv/pull/24231#pullrequestreview-1628649980

### 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
2023-09-27 14:09:47 +03:00
Dmitry Kurtaev
2b6d0f36f0
Merge pull request #24309 from dkurt:gemm_ov_hotfix
Update OpenVINO init of new GEMM layer #24309

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

CI validation:

- [x] 2022.1.0: https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100368
- [ ] 2021.4.2: https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100373

Checklist:
- [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
2023-09-27 10:25:45 +03:00
Yuantao Feng
bb171a0c05
dnn: expand refactor with cv::broadcast for onnx models (#24295)
* add expand impl with cv::broadcast

* remove expandMid

* deduce shape from -1

* add constant folding

* handle input constant; handle input constant 1d

* add expand conformance tests; add checks to disallow shape of neg values; add early copy for unchanged total elements

* fix ExpandSubgraph

* dummy commit to trigger build

* dummy commit to trigger build 1

* remove conformance from test names
2023-09-27 09:28:52 +03:00
Alexander Smorkalov
9942757bab
Merge pull request #24316 from alexlyulkov:al/fix-caffe-read-segfault
Fixed segfault when reading Caffe model
2023-09-25 17:53:54 +03:00
Alexander Lyulkov
72e7672a6c Fixed segfault when reading Caffe model 2023-09-25 12:55:11 +07:00
Abduragim Shtanchaev
865e7cacca
Merge pull request #24037 from Abdurrahheem:ash/dev_einsum
Add Support for Einsum Layer #24037

### This PR adding support for [Einsum Layer](https://pytorch.org/docs/stable/generated/torch.einsum.html) (in progress). 

This PR is currently not to be merged but only reviewed. Test cases are located in [#1090](https://github.com/opencv/opencv_extra/pull/1090)RP in OpenCV extra

**DONE**: 
 - [x] 2-5D GMM support added
 - [x] Matrix transpose support added
 - [x] Reduction type comupte  'ij->j'
 - [x] 2nd shape computation - during forward 

**Next PRs**:
- [ ] Broadcasting reduction "...ii ->...i"
- [ ] Add lazy shape deduction. "...ij, ...jk->...ik"
- [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik")
- [ ] Add support for CUDA backend 
- [ ] BatchWiseMultiply optimize

**Later in 5.x version (requires support for 1D matrices)**: 
- [ ] Add 1D vector multiplication support 
- [ ] Inter product "i, i" (problems with 1D shapes)

### 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
2023-09-22 11:25:02 +03:00
Alexander Smorkalov
799bb0cd18
Merge pull request #24291 from visitorckw:fix-memory-leak
Fix memory leak and handle realloc failure
2023-09-20 08:49:56 +03:00
Yuantao Feng
8a96e34e33
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897)
* first commit

* turned C from input to constant; force C constant in impl; better handling 0d/1d cases

* integrate with gemm from ficus nn

* fix const inputs

* adjust threshold for int8 tryQuantize

* adjust threshold for int8 quantized 2

* support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet

* add gemm perf against innerproduct

* add perf tests for innerproduct with bias

* fix perf

* add memset

* renamings for next step

* add dedicated perf gemm

* add innerproduct in perf_gemm

* remove gemm and innerproduct perf tests from perf_layer

* add perf cases for vit sizes; prepack constants

* remove batched gemm; fix wrong trans; optimize KC

* remove prepacking for const A; several fixes for const B prepacking

* add todos and gemm expression

* add optimized branch for avx/avx2

* trigger build

* update macros and signature

* update signature

* fix macro

* fix bugs for neon aarch64 & x64

* add backends: cuda, cann, inf_ngraph and vkcom

* fix cuda backend

* test commit for cuda

* test cuda backend

* remove debug message from cuda backend

* use cpu dispatcher

* fix neon macro undef in dispatcher

* fix dispatcher

* fix inner kernel for neon aarch64

* fix compiling issue on armv7; try fixing accuracy issue on other platforms

* broadcast C with beta multiplied; improve func namings

* fix bug for avx and avx2

* put all platform-specific kernels in dispatcher

* fix typos

* attempt to fix compile issues on x64

* run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon

* fix typo

* quick fix: add macros for pack4

* quick fix: use vmlaq_f32 for armv7

* quick fix for missing macro of fast gemm pack f32 4

* disable conformance tests when optimized branches are not supported

* disable perf tests when optimized branches are not supported

* decouple cv_try_neon and cv_neon_aarch64

* drop googlenet_2023; add fastGemmBatched

* fix step in fastGemmBatched

* cpu: fix initialization ofb; gpu: support batch

* quick followup fix for cuda

* add default kernels

* quick followup fix to avoid macro redef

* optmized kernels for lasx

* resolve mis-alignment; remove comments

* tune performance for x64 platform

* tune performance for neon aarch64

* tune for armv7

* comment time consuming tests

* quick follow-up fix
2023-09-20 00:53:34 +03:00
Kuan-Wei Chiu
e16ca08b33 Fix memory leak and handle realloc failure
In the previous code, there was a memory leak issue where the
previously allocated memory was not freed upon a failed realloc
operation. This commit addresses the problem by releasing the old
memory before setting the pointer to NULL in case of a realloc failure.
This ensures that memory is properly managed and avoids potential
memory leaks.
2023-09-18 22:43:44 +08:00
Alexander Smorkalov
157b0e7760
Merge pull request #24275 from alexlyulkov:al/fix-tf-graph-simplifier
Fixed removePhaseSwitches in tf_graph_simplifier
2023-09-18 11:02:44 +03:00
Alexander Lyulkov
d4cb564ce2 Fixed removePhaseSwitches in tf_graph_simplifier 2023-09-15 14:22:21 +07:00
Dmitry Kurtaev
c5edd20354 Higher threshold for FasterRCNN_vgg16 2023-09-14 13:11:53 +03:00
alexlyulkov
1e54e56579
Merge pull request #24266 from alexlyulkov:al/tf-argmax-default-dim
Added default dimension value to tensorflow ArgMax and ArgMin layers #24266

Added default dimension value to tensorflow ArgMax and ArgMin layers.
Added exception when accessing layer's input with out of range index.
Fixes https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=48452
2023-09-14 10:25:24 +03:00
Alexander Smorkalov
62c0556c58
Merge pull request #24252 from opencv-pushbot:gitee/alalek/refactor_24218
cmake: revise OPENCV_DNN_BACKEND_DEFAULT integration
2023-09-11 08:55:19 +03:00
Alexander Alekhin
02525abd9f cmake: revise OPENCV_DNN_BACKEND_DEFAULT integration
- disable message on default value
2023-09-10 13:11:36 +00:00
Dmitry Kurtaev
5dc5b27858 Enable build with OpenVINO in Debug 2023-09-09 20:38:59 +03:00
Alexander Smorkalov
e60825e75b
Merge pull request #24218 from CSBVision:patch-5
Added CMake configuration OPENCV_DNN_BACKEND_DEFAULT
2023-09-08 14:21:39 +03:00
Alexander Smorkalov
5350fba319
Merge pull request #24128 from CSBVision:CSBVision-patch-1
Fix bug at blobFromImagesWithParams
2023-09-06 16:20:37 +03:00
CSBVision
674c618471 Update dnn_utils.cpp 2023-09-06 10:01:07 +03:00
Dmitry Kurtaev
178fdbbda8
Merge pull request #24196 from dkurt:ov_backend_cleanups
Use ngraph::Output in OpenVINO backend wrapper #24196

### Pull Request Readiness Checklist

resolves https://github.com/opencv/opencv/issues/24102

* Use `ngraph::Output<ngraph::Node>>` insead of `std::shared_ptr<ngraph::Node>` as a backend wrapper. It lets access to multi-output nodes: 588ddf1b18/modules/dnn/src/net_openvino.cpp (L501-L504)
* All layers can be customizable with OpenVINO >= 2022.1. nGraph reference code used for default layer implementation does not required CPU plugin also (might be tested by commenting CPU plugin at `/opt/intel/openvino/runtime/lib/intel64/plugins.xml`).
* Correct inference if only intermediate blobs requested.


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
2023-09-05 18:08:28 +03:00
Björn Böken
639836ebf0 Added CMake configuration OPENCV_DNN_BACKEND_DEFAULT 2023-09-05 10:05:12 +02:00
Wanli
84f32bbb24 increase Fast Math threshold 2023-09-05 14:03:54 +08:00
Sam James
c20febdbb0
Fix compilation on arm64 with FP16 when disabled
If building with -mcpu=native or any other setting which implies the current
CPU has FP16 but with intrinsics disabled, we mistakenly try to use it even
though convolution.hpp conditionally defines it correctly based on whether
we should *use it*. convolution.cpp on the other hand was mismatched and
trying to use it if the CPU supported it, even if not enabled in the build
system.

Make the guards match.

Bug: https://bugs.gentoo.org/913031
Signed-off-by: Sam James <sam@gentoo.org>
2023-08-29 03:05:49 +01:00
Dmitry Kurtaev
a0debc3a9a Enable OpenVINO max pooling with indices since 2022.1 2023-08-23 10:39:38 +03:00
Dmitry Kurtaev
d88ad46978 Remove explitit transB attribute from MatMul perf test 2023-08-18 15:10:14 +03:00
autoantwort
f5a14532c2
Merge pull request #24167 from autoantwort:missing-include
* add missing include

* Apply CR
2023-08-17 09:34:19 +00:00
Dmitry Kurtaev
8ad5eb521a
Merge pull request #24120 from dkurt:actualize_dnn_links
OCL_FP16 MatMul with large batch

* Workaround FP16 MatMul with large batch

* Fix OCL reinitialization

* Higher thresholds for INT8 quantization

* Try fix gemm_buffer_NT for half (columns)

* Fix GEMM by rows

* Add batch dimension to InnerProduct layer test

* Fix Test_ONNX_conformance.Layer_Test/test_basic_conv_with_padding

* Batch 16

* Replace all vload4

* Version suffix for MobileNetSSD_deploy Caffe model
2023-08-16 15:46:11 +03:00
MuZihao
16681d1080 fix the issue in layer fused 2023-08-16 09:34:59 +08:00
Yuantao Feng
ba70ec99b3
Merge pull request #24122 from fengyuentau:remove_tengine
dnn: cleanup of tengine backend #24122

🚀 Cleanup for OpenCV 5.0. Tengine backend is added for convolution layer speedup on ARM CPUs, but it is not maintained and the convolution layer on our default backend has reached similar performance to that of Tengine.

Tengine backend related PRs:
- https://github.com/opencv/opencv/pull/16724
- https://github.com/opencv/opencv/pull/18323

### 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
2023-08-09 09:26:02 +03:00
unknown
87b7ce4415 Solved issue 24044 2023-08-04 21:57:22 +02:00
Laurent Berger
2ff16d4c45
Merge pull request #24101 from LaurentBerger:I24076
Invalid memory access fix for ONNX split layer parser #24076 #24101

### 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 https://github.com/opencv/opencv/issues/24076
- [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
2023-08-04 12:18:49 +03:00
Alexander Smorkalov
5466fd2606
Merge pull request #24104 from cudawarped:cuda_fix_cuda_toolkit_12_2
`cuda`: fix for compatibility with CUDA Toolkit >= 12.2.0
2023-08-04 12:11:15 +03:00
Dmitry Kurtaev
4b8aeb1129
Merge pull request #24039 from dkurt:tflite_test_backends
TFLite models on different backends (tests and improvements) #24039

### Pull Request Readiness Checklist

* MaxUnpooling with OpenVINO
* Fully connected with transposed inputs/weights with OpenVINO
* Enable backends tests for TFLite (related to https://github.com/opencv/opencv/issues/23992#issuecomment-1640691722)
* Increase existing tests thresholds

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
2023-08-04 11:28:51 +03:00
Dmitry Kurtaev
96f23e3da1
Merge pull request #24080 from dkurt:dnn_cuda_layers
Resolve uncovered CUDA dnn layer #24080

### Pull Request Readiness Checklist

* Gelu activation layer on CUDA
* Try to relax GEMM from ONNX

resolves https://github.com/opencv/opencv/issues/24064

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
2023-08-03 09:13:42 +03:00
Dmitry Kurtaev
0245c0cd10
Merge pull request #24072 from dkurt:openvino_cpu_tests
Remove legacy nGraph logic #24072

### Pull Request Readiness Checklist

TODO:
- [x] Test with OpenVINO 2021.4 (tested locally)

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
2023-08-02 14:39:11 +03:00
Dmitry Kurtaev
195aad8e6a
Merge pull request #24069 from dkurt:openvino_detection_layer
DetectionOutput layer on OpenVINO without limitations #24069

### Pull Request Readiness Checklist

required for https://github.com/opencv/opencv/pull/23987

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
2023-08-02 14:28:47 +03:00
cudawarped
ab8cb6f8a9 cuda: fix for compatibility with CUDA Toolkit >= 12.2.0 2023-08-01 13:02:42 +03:00
Dmitry Kurtaev
677a28fd2a
Merge pull request #24056 from dkurt:eltwise_prelu
PReLU with element-wise scales #24056

### Pull Request Readiness Checklist

resolves https://github.com/opencv/opencv/issues/24051

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
2023-07-27 16:36:40 +03:00
SaltFish-T
ab6bffc6f8
Merge pull request #23936 from SaltFish-T:4.x
Update opencv dnn to support cann version >=6.3 #23936

1.modify the search path of "libopsproto.so" in OpenCVFindCANN.cmake
2.add the search path of "libgraph_base.so" in OpenCVFindCANN.cmake
3.automatic check Ascend socVersion,and test on Ascend310/Ascend310B/Ascend910B well
2023-07-27 14:21:30 +03:00
Alexander Smorkalov
e5e1a3bfde
Merge pull request #24043 from zixianweei:use-vaddq_f32-on-arm64
fix compilation error on Windows ARM, use vaddq_f32 instead of +=
2023-07-25 11:41:09 +03:00
zixgo
ec7689421d fix compilation error on Windows ARM, use vaddq_f32 instead of += 2023-07-21 19:54:43 +08:00
Alexander Smorkalov
d96ff496b4 Increase eps for Test_Torch_nets.FastNeuralStyle_accuracy to prevent sporadic test failres with CUDA. 2023-07-21 13:51:03 +03:00
Dmitry Kurtaev
e41ba90f17
Merge pull request #24004 from dkurt:tflite_new_layers
[TFLite] Pack layer and other fixes for SSD from Keras #24004

### Pull Request Readiness Checklist

resolves https://github.com/opencv/opencv/issues/23992

**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1076

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
2023-07-21 09:13:37 +03:00
Alexander Smorkalov
23f27d8dbe Use OpenCV logging instead of std::cerr. 2023-07-19 10:49:54 +03:00
Zihao Mu
1920993525
Merge pull request #23952 from zihaomu:fix_depth_conv_5x5
DNN: optimize the speed of general Depth-wise #23952

Try to solve the issue: https://github.com/opencv/opencv/issues/23941

### 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
2023-07-14 17:34:39 +03:00
Alexander Smorkalov
bf06bc92aa Merge branch '3.4' into merge-3.4 2023-06-23 20:12:58 +03:00
Yuantao Feng
aff420329c
Merge pull request #23853 from fengyuentau:disable_fp16_warning
dnn: disable warning when loading a fp16 model #23853

### 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
2023-06-23 19:52:04 +03:00
Alexander Smorkalov
d9a5603fa3
Merge pull request #23860 from fengyuentau:fix_overflow_sigmoid_v3.4
dnn: fix overflow in sigmoid layer for 3.4
2023-06-23 19:47:42 +03:00
fengyuentau
29388f80a5 fix overflow 2023-06-23 21:22:21 +08:00
Alexander Smorkalov
51702ffd92 pre: OpenCV 4.8.0 (version++) 2023-06-20 15:52:57 +03:00
Dmitry Kurtaev
433c364456
Merge pull request #23724 from dkurt:java_without_ant
Build Java without ANT #23724

### Pull Request Readiness Checklist

Enables a path of building Java bindings without ANT

* Able to build OpenCV JAR and Docs without ANT
  ```
  --   Java:
  --     ant:                         NO
  --     JNI:                         /usr/lib/jvm/default-java/include /usr/lib/jvm/default-java/include/linux /usr/lib/jvm/default-java/include
  --     Java wrappers:               YES
  --     Java tests:                  NO
  ```
* Possible to build OpenCV JAR without ANT but tests still require ANT

**Merge with**: https://github.com/opencv/opencv_contrib/pull/3502

Notes:
- Use `OPENCV_JAVA_IGNORE_ANT=1` to force "Java" flow for building Java bindings
- Java tests still require Apache ANT
- JAR doesn't include `.java` source code files.


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
2023-06-16 19:58:20 +03:00
Alexander Smorkalov
3c0b71bcec
Merge pull request #23795 from dkurt:tf_half_pixel_for_nn
Consider half pixel mode in ONNX resize
2023-06-16 10:21:20 +03:00
Dmitry Kurtaev
924c01dbec
Replace CV_Assert_N 2023-06-15 17:30:33 +03:00
Wang Kai
fc2d933224 removing unreachable code and fixing a typo 2023-06-15 01:09:02 +08:00
Dmitry Kurtaev
6909fffde1 Consider half pixel mode in ONNX resize 2023-06-14 14:21:28 +03:00
Dmitry Kurtaev
f9d7f47e28 Change Scalar assignment in Python from single value 2023-06-13 10:45:03 +03:00
Wang Kai
4622f1e89b fixing typo of a variable name in dnn::runFastConv 2023-06-11 01:54:03 +08:00
Zihao Mu
eec8a20c33
Merge pull request #23763 from zihaomu:add_runtime_check
DNN: fix bug for X86 Winograd #23763

Address https://github.com/opencv/opencv/issues/23760
The patch aims to add a runtime check for X86 platform without AVX(2).

### 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
2023-06-09 09:18:12 +03:00
Alexander Smorkalov
6d2cbc4055
Merge pull request #23761 from LaurentBerger:typeblobfromimages
checktype in blobFromImages and blobFromImagesWithParams
2023-06-08 09:59:01 +03:00
unknown
5f8e43da85 checktype in blobFromImages and blobFromImagesWithParams 2023-06-07 16:15:58 +02:00
Abduragim Shtanchaev
6b53fe8f7b
Merge pull request #23746 from Abdurrahheem:ash/graph_simplifier
Assertion Fix in Split Layer #23746

### Pull Request Readiness Checklist

This PR fixes issue mentioned in [#23663](https://github.com/opencv/opencv/issues/23663)
Merge with https://github.com/opencv/opencv_extra/pull/1067

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
2023-06-07 16:01:42 +03:00
Olivier Hotel
0442c6fa81 Addition of normalize_axis to ONNXImporter::parseSqueeze to support negative values for the axes attribut.
Negative values are part of the ONNX optset>=11.

Signed-off-by: Olivier Hotel <olivier.hotel@orange.com>
2023-05-30 10:21:27 +02:00
Abduragim Shtanchaev
ecd2e8ff47 added index that check all inputs of nodes that
match
2023-05-29 14:48:42 +03:00
Alexander Smorkalov
cf0ba039c3
Merge pull request #23625 from zihaomu:improve_conv
DNN: Remove unnecessary flags for convolution
2023-05-26 12:59:36 +03:00
Alexander Smorkalov
26a7b332cb
Merge pull request #23671 from zihaomu:fix_potential_bug
DNN: fix potential bug, stride should not be set as 0.
2023-05-25 13:36:37 +03:00
Yuantao Feng
f07b01cc34
Merge pull request #23655 from fengyuentau:qlinearsoftmax
Support ONNX operator QLinearSoftmax in dnn #23655

Resolves https://github.com/opencv/opencv/issues/23636.
Merge with https://github.com/opencv/opencv_extra/pull/1064.

This PR maps the QLinearSoftmax (from com.microsoft domain) to SoftmaxInt8 in dnn along with some speed optimization.

Todo:
- [x] support QLinearSoftmax with opset = 13
- [x] add model and test data for QLinearSoftmax with opset = 13
- [x] ensure all models have dims >= 3.
- [x] add the script to generate model and test data 

### 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
2023-05-25 13:35:58 +03:00
zihaomu
4384e77bd1 when stride ==0, it should be bug 2023-05-24 21:57:59 +08:00
Alexander Smorkalov
4a559bc2ab
Merge pull request #23656 from peters:patch-2
Build fix for AVX 256
2023-05-23 09:20:34 +03:00
Alexander Smorkalov
b122a4b436
Merge pull request #23646 from dkurt:dnn_ie_region_fix
Fix Region layer with OpenVINO in case of different width/height
2023-05-22 16:22:50 +03:00
Peter Rekdal Khan-Sunde
04970490ec
Build fix
/build/build_cuda/3p/opencv/linux-x64/ubuntu22.04/Debug/modules/dnn/src/layers/cpu_kernels/convolution.cpp: In function 'void cv::dnn::packData8(char*&, float*&, int&, int&, int&, const int*, int, int, int)':
/build/build_cuda/3p/opencv/linux-x64/ubuntu22.04/Debug/modules/dnn/src/layers/cpu_kernels/convolution.cpp:448:43: error: 'CONV_NR' was not declared in this scope; did you mean 'CONV_3D'?
  448 |                 vx_store(inpbufC_FP32 + k*CONV_NR, vx_load(inptrInC + k1));
      |                                           ^~~~~~~
      |                                           CONV_3D
2023-05-22 11:25:04 +02:00
Alexander Smorkalov
f2311d1bfd
Merge pull request #23645 from Abdurrahheem:ash/tf_init_input_check
Add assert to check if layer input size is not empty
2023-05-19 13:28:24 +03:00
Zihao Mu
5025f29378
speed up vulkan dnn, and support ios and apple m1 chip. (#23349) 2023-05-18 20:02:27 +03:00
Dmitry Kurtaev
af14780526 Fix Region layer with OpenVINO in case of different width/height 2023-05-18 17:45:30 +03:00
Abduragim Shtanchaev
2b9d2c726a add assert to check if layer input size is not empty 2023-05-18 16:17:57 +03:00
Abduragim Shtanchaev
d2143bcd44
Merge pull request #23614 from Abdurrahheem:lstm_layout_attribute
LSTM ONNX Layout Attribute Support #23614 

### Explanation

This PR contains necessary changes to support `layout` attribute. This attributes is present in [ONNX](https://github.com/onnx/onnx/blob/main/docs/Operators.md#lstm) and [Torch](https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html#lstm) (in touch it is name as `batch_first=True`) libraries. When `layout = 1` input to LSTM layer is expected to have batch dimension first -> `[batch_size, sequence_length, features]` vs `layout = 0` - default `[sequence_length, batch_size, features]`

### Test Data

Test data and data generator for PR located here [#1063](https://github.com/opencv/opencv_extra/pull/1063)

### 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
2023-05-17 22:46:56 +03:00
Yuantao Feng
eefee8574a
dnn: refactor reduce (#23613)
* initial impl

* remove reduce in8; fix reduce importer

* fix bugs and add log sum exp

* remove unnecessary header and fix indentation
2023-05-17 10:03:45 +03:00
Zihao Mu
5229312ad2
Merge pull request #22275 from zihaomu:fp16_support_conv
DNN: FP16 support on Convolution 2D #22275 

## FP16 support on ARM platform
This PR proposes to support FP16 backend in Convolution.
For now, we only support FP16 at ARM aarch64.

In addition to adding fp16, I also added `seperateIm2col` optimization in this patch.

## How to use FP16 to speed up convolution?
```
Net net = readNet(modelPath);
net.setPreferableTarget(DNN_TARGET_CPU_FP16);
net.setInput(blob);
Mat output = net.forward();
```

### TODO List
| Task | Status | Remarks |
|:-------:|:--------:|:------------:|
| Convolution 2D FP16 | ✔️ | Done |
| Winograd FP16 | Because the current modification has reached 2k lines, winograd fp16 will be completed in the next PR. |  |
| Accuracy Test | ✔️ | Done |
| Performance Test | ✔️ | Done |
| Compiler bug | ✔️ | Done |

### Speed Test for FP 16.

**Test on M1 chip, 4 threads.**

| Model Name | FP32 (Conv+Wino) | Conv(FP16) + Wino(FP 32) |
|:-------:|:--------:|:------------:|
| ReseNet 50 | 26.0 ms | **18.05 ms** (25% speed up)|
| MobileNet V2 | 4.17 ms | **3.09 ms (29% speed up)** |

### Speed Test for `seperateIm2col` trick on X86.
**Test on AMD 5600x, 12 threads.**
| Model Name | 4.x | Patch |
|:-------:|:--------:|:------------:|
| MobileNet V2 | 5.6 ms | **3.0 ms (46% speed up)** |

### Performance Test

#### Performance Test of X86 platform: AMD 5600X, with `-perf_threas=1`
|Name of Test|4.x|patch|patch vs 4.x (x-factor)|
|---|:-:|:-:|:-:|
|Name of Test|4.x 0|fp16pr final|fp16pr final vs 4.x 0 (x-factor)|
|---|:-:|:-:|:-:|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 19}, OCN=2, G=2, S=2, P=(1, 1), BIAS, OCV/CPU)|0.001|0.001|1.00|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 25}, OCN=2, G=2, P=(2, 2), PM=SAME, OCV/CPU)|0.001|0.001|1.03|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 6, 10}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.001|0.001|0.92|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.002|0.003|0.95|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.006|0.006|1.00|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.045|0.033|1.39|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)|0.011|0.009|1.17|
|conv3d::Conv3D::(GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)|0.109|0.078|1.39|
|conv3d::Conv3D::(GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)|0.040|0.042|0.94|
|conv3d::Conv3D::(GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.326|0.342|0.95|
|conv3d::Conv3D::(GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.580|0.589|0.99|
|conv3d::Conv3D::(GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)|1.293|1.382|0.94|
|conv3d::Conv3D::(GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)|3.590|3.710|0.97|
|conv3d::Conv3D::(GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)|1.120|1.191|0.94|
|conv3d::Conv3D::(GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)|2.576|2.872|0.90|
|conv3d::Conv3D::(GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)|4.599|4.670|0.98|
|conv3d::Conv3D::(GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)|9.230|9.582|0.96|
|conv3d::Conv3D::(GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)|65.946|69.381|0.95|
|conv3d::Conv3D::(GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)|18.915|19.289|0.98|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU)|1.404|1.457|0.96|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU)|2.060|1.501|1.37|
|conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU)|1.409|1.464|0.96|
|conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)|1.793|1.838|0.98|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)|1.207|1.199|1.01|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)|1.277|1.275|1.00|
|conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|2.319|2.370|0.98|
|conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU)|1.351|1.346|1.00|
|conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU)|3.520|3.612|0.97|
|conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.876|1.880|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU)|1.981|1.995|0.99|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU)|2.620|2.627|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU)|4.202|4.123|1.02|
|conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|2.429|2.445|0.99|
|conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|2.591|2.576|1.01|
|conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)|3.005|2.998|1.00|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU)|3.515|3.532|1.00|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU)|3.115|3.134|0.99|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|3.937|3.899|1.01|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU)|5.533|5.471|1.01|
|conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|3.472|3.464|1.00|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)|4.302|4.322|1.00|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)|6.100|6.035|1.01|
|conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)|6.580|6.484|1.01|
|conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|9.741|9.634|1.01|
|conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|10.131|10.156|1.00|
|conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|12.391|12.350|1.00|
|conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU)|91.074|87.893|1.04|
|conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|5.903|5.903|1.00|
|conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU)|6.890|6.794|1.01|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)|5.160|5.131|1.01|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|4.970|5.036|0.99|
|conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|5.045|5.015|1.01|
|conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)|11.583|11.343|1.02|
|conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)|5.348|5.320|1.01|
|conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU)|5.357|5.396|0.99|
|conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU)|6.050|6.006|1.01|
|conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU)|5.952|5.953|1.00|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU)|8.014|8.014|1.00|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU)|12.472|12.577|0.99|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU)|10.803|10.655|1.01|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU)|18.429|13.405|1.37|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU)|6.659|6.647|1.00|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU)|14.192|13.819|1.03|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU)|6.045|6.068|1.00|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)|12.742|12.828|0.99|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU)|8.046|7.773|1.04|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.440|17.192|1.01|
|conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)|15.418|14.972|1.03|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)|0.430|0.430|1.00|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)|6.692|6.663|1.00|
|conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU)|6.350|6.347|1.00|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)|0.267|0.265|1.01|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)|7.755|7.558|1.03|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)|0.203|0.202|1.00|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|10.663|10.576|1.01|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)|10.827|10.614|1.02|
|conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU)|7.049|6.947|1.01|
|conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU)|6.900|6.901|1.00|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)|0.165|0.165|1.00|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)|17.953|17.251|1.04|
|conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU)|7.430|7.320|1.01|
|conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU)|22.187|21.705|1.02|
|conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU)|8.349|8.126|1.03|
|conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)|8.273|8.297|1.00|
|conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU)|8.169|8.094|1.01|
|conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)|13.602|13.359|1.02|
|conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU)|8.633|8.584|1.01|
|conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)|29.339|28.897|1.02|
|conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|13.000|12.920|1.01|
|conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|14.262|13.319|1.07|
|conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|27.453|27.253|1.01|
|conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU)|32.052|27.269|1.18|
|conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|15.363|15.208|1.01|
|conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|18.543|18.434|1.01|
|conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)|39.114|37.954|1.03|
|conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|36.271|36.972|0.98|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|19.262|19.427|0.99|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|19.298|19.349|1.00|
|conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|20.261|19.847|1.02|
|conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|21.867|21.525|1.02|
|conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU)|51.756|49.979|1.04|
|conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|28.133|27.060|1.04|
|conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU)|25.035|24.980|1.00|
|conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|25.858|25.821|1.00|
|conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|27.313|27.149|1.01|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)|28.219|28.111|1.00|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|46.025|46.674|0.99|
|conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|30.220|29.446|1.03|
|conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|49.410|48.708|1.01|
|conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|38.203|38.001|1.01|
|conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|39.961|39.021|1.02|
|conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|48.685|47.075|1.03|
|conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|75.114|72.586|1.03|
|conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)|41.222|41.144|1.00|
|conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU)|46.220|46.353|1.00|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU)|98.201|98.771|0.99|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|100.106|96.971|1.03|
|conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|146.977|140.445|1.05|
|conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU)|198.618|194.665|1.02|


#### Performance Test of ARM platform: apple M1, with `-perf_threas=1`

Min (ms)

|Name of Test|4.x|patch|4.x vs patch (x-factor)|
|---|:-:|:-:|:-:|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 19}, OCN=2, G=2, S=2, P=(1, 1), BIAS, OCV/CPU)|0.001|0.001|1.07|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 25}, OCN=2, G=2, P=(2, 2), PM=SAME, OCV/CPU)|0.001|0.001|1.10|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 6, 10}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.002|0.002|0.97|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.003|0.003|0.84|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.009|0.009|1.00|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.027|0.030|0.90|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)|0.008|0.007|1.07|
|conv3d::Conv3D::(GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)|0.066|0.072|0.91|
|conv3d::Conv3D::(GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)|0.090|0.054|1.68|
|conv3d::Conv3D::(GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.328|0.409|0.80|
|conv3d::Conv3D::(GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.659|0.697|0.95|
|conv3d::Conv3D::(GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)|1.266|1.403|0.90|
|conv3d::Conv3D::(GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)|3.550|4.145|0.86|
|conv3d::Conv3D::(GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)|1.188|1.375|0.86|
|conv3d::Conv3D::(GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)|2.683|3.236|0.83|
|conv3d::Conv3D::(GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)|4.491|5.501|0.82|
|conv3d::Conv3D::(GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)|8.916|10.181|0.88|
|conv3d::Conv3D::(GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)|69.995|72.296|0.97|
|conv3d::Conv3D::(GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)|22.531|23.139|0.97|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU)|2.239|1.933|1.16|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU_FP16)|-|1.010|-|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU)|3.134|2.068|1.52|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU_FP16)|-|1.062|-|
|conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU)|1.918|1.920|1.00|
|conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU_FP16)|-|1.014|-|
|conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)|2.340|2.352|0.99|
|conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.247|-|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)|1.116|1.111|1.00|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU_FP16)|-|1.114|-|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)|1.116|1.112|1.00|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|1.113|-|
|conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|3.067|3.085|0.99|
|conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.622|-|
|conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU)|1.153|1.187|0.97|
|conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU_FP16)|-|1.150|-|
|conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU)|4.804|4.849|0.99|
|conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU_FP16)|-|2.922|-|
|conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.463|1.469|1.00|
|conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.459|-|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU)|1.577|1.580|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU_FP16)|-|1.580|-|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU)|1.826|1.818|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU_FP16)|-|1.817|-|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU)|6.541|5.081|1.29|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU_FP16)|-|2.809|-|
|conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.912|1.919|1.00|
|conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.919|-|
|conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|1.961|1.971|0.99|
|conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|1.961|-|
|conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)|2.317|2.329|0.99|
|conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU_FP16)|-|2.322|-|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU)|2.920|2.947|0.99|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU_FP16)|-|2.924|-|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU)|2.467|2.466|1.00|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU_FP16)|-|2.496|-|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|3.028|2.997|1.01|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|2.986|-|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU)|4.353|4.355|1.00|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU_FP16)|-|4.355|-|
|conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|2.762|2.793|0.99|
|conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU_FP16)|-|2.797|-|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)|3.428|3.226|1.06|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU_FP16)|-|3.223|-|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)|3.967|3.957|1.00|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU_FP16)|-|3.960|-|
|conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)|4.806|4.387|1.10|
|conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU_FP16)|-|4.366|-|
|conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|14.509|11.756|1.23|
|conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|6.510|-|
|conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|13.718|13.287|1.03|
|conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU_FP16)|-|7.190|-|
|conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|15.133|14.853|1.02|
|conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU_FP16)|-|8.671|-|
|conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU)|41.928|43.328|0.97|
|conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU_FP16)|-|38.072|-|
|conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|4.409|4.428|1.00|
|conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|4.427|-|
|conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU)|6.144|5.363|1.15|
|conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU_FP16)|-|5.368|-|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)|3.926|3.932|1.00|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU_FP16)|-|3.938|-|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|3.920|3.915|1.00|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU_FP16)|-|3.950|-|
|conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|3.767|3.764|1.00|
|conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|3.762|-|
|conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)|19.959|13.875|1.44|
|conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU_FP16)|-|7.781|-|
|conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)|3.951|3.955|1.00|
|conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU_FP16)|-|3.969|-|
|conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU)|4.050|4.034|1.00|
|conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.093|-|
|conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU)|4.923|4.506|1.09|
|conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.509|-|
|conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU)|4.759|4.476|1.06|
|conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.447|-|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU)|6.079|5.628|1.08|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU_FP16)|-|5.625|-|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU)|19.843|17.523|1.13|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|8.917|-|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU)|8.334|8.247|1.01|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU_FP16)|-|8.246|-|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU)|23.164|18.199|1.27|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|9.305|-|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU)|5.184|5.178|1.00|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU_FP16)|-|5.149|-|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.990|18.103|0.99|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|9.777|-|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU)|4.831|4.522|1.07|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|4.523|-|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.328|17.319|1.00|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|8.948|-|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU)|5.944|5.961|1.00|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU_FP16)|-|5.936|-|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU)|19.811|20.064|0.99|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|11.705|-|
|conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)|22.398|17.686|1.27|
|conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU_FP16)|-|9.859|-|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)|0.416|0.416|1.00|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.417|-|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)|5.356|5.110|1.05|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU_FP16)|-|5.114|-|
|conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU)|5.092|4.748|1.07|
|conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.754|-|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)|0.260|0.229|1.13|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.229|-|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)|5.872|5.460|1.08|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU_FP16)|-|5.460|-|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)|0.161|0.161|1.00|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.161|-|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|7.176|7.175|1.00|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|7.162|-|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)|7.174|7.185|1.00|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU_FP16)|-|7.157|-|
|conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU)|5.400|5.180|1.04|
|conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU_FP16)|-|5.201|-|
|conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU)|5.330|5.188|1.03|
|conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU_FP16)|-|5.177|-|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)|0.115|0.115|1.00|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.115|-|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)|26.156|20.222|1.29|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU_FP16)|-|11.203|-|
|conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU)|5.627|5.543|1.02|
|conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU_FP16)|-|5.506|-|
|conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU)|27.925|27.741|1.01|
|conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU_FP16)|-|17.217|-|
|conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU)|6.359|6.062|1.05|
|conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU_FP16)|-|6.048|-|
|conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)|6.559|6.322|1.04|
|conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU_FP16)|-|6.280|-|
|conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU)|6.412|6.200|1.03|
|conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU_FP16)|-|6.197|-|
|conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)|9.167|8.624|1.06|
|conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU_FP16)|-|8.626|-|
|conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU)|6.755|6.491|1.04|
|conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU_FP16)|-|6.520|-|
|conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)|35.664|34.752|1.03|
|conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU_FP16)|-|20.260|-|
|conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|9.514|9.414|1.01|
|conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|9.462|-|
|conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|10.631|9.963|1.07|
|conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|9.935|-|
|conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|37.465|36.798|1.02|
|conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU_FP16)|-|19.569|-|
|conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU)|38.157|36.157|1.06|
|conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU_FP16)|-|18.902|-|
|conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|10.356|10.401|1.00|
|conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|10.360|-|
|conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|12.641|12.150|1.04|
|conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU_FP16)|-|12.162|-|
|conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)|50.545|50.505|1.00|
|conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU_FP16)|-|27.950|-|
|conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|54.233|49.603|1.09|
|conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU_FP16)|-|26.515|-|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|13.779|12.968|1.06|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|12.984|-|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|15.809|15.329|1.03|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|15.433|-|
|conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|14.563|14.527|1.00|
|conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|14.480|-|
|conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|16.714|16.484|1.01|
|conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|16.362|-|
|conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU)|77.832|65.729|1.18|
|conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU_FP16)|-|32.065|-|
|conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|21.903|20.386|1.07|
|conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU_FP16)|-|20.416|-|
|conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU)|20.405|18.148|1.12|
|conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU_FP16)|-|18.128|-|
|conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|20.334|18.521|1.10|
|conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|18.495|-|
|conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|21.527|19.584|1.10|
|conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|19.630|-|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)|22.715|20.057|1.13|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU_FP16)|-|20.068|-|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|26.228|24.992|1.05|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|24.957|-|
|conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|21.524|21.581|1.00|
|conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|21.782|-|
|conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|34.094|31.964|1.07|
|conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|31.925|-|
|conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|28.677|27.813|1.03|
|conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|27.808|-|
|conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|31.274|27.892|1.12|
|conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|27.910|-|
|conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|30.533|30.007|1.02|
|conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|30.089|-|
|conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|39.837|38.312|1.04|
|conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|38.477|-|
|conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)|32.480|29.237|1.11|
|conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU_FP16)|-|29.452|-|
|conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU)|33.544|32.832|1.02|
|conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|32.784|-|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU)|134.481|130.678|1.03|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU_FP16)|-|70.134|-|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|127.930|126.530|1.01|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU_FP16)|-|65.261|-|
|conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|201.346|187.007|1.08|
|conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU_FP16)|-|91.525|-|
|conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU)|252.038|245.587|1.03|
|conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU_FP16)|-|125.477|-|

### 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
2023-05-17 09:38:33 +03:00
Alexander Smorkalov
59ca444b26
Merge pull request #23560 from WanliZhong:eltwise_cuda_bug
DNN/CUDA: Solve the bug of same shape broadcast with CUDA
2023-05-16 14:16:37 +03:00
zihaomu
91b6c8507a remove flag of convolution 2023-05-16 15:29:20 +08:00
Dmitry Kurtaev
a8d3d1f6f9
Merge pull request #23604 from dkurt:dnn_no_protobuf
Build DNN without Protobuf

DNN module can be built without Protobuf for Darknet, TFLite, OpenVINO, Torch (not PyTorch) models.

```
cmake \
    -DCMAKE_BUILD_TYPE=Release \
    -DBUILD_LIST=dnn \
    -DWITH_PROTOBUF=OFF \
    -DWITH_OPENCL=OFF

7.1M    lib/libopencv_dnn.so.4.7.0
```


```
cmake \
    -DCMAKE_BUILD_TYPE=Release \
    -DBUILD_LIST=dnn \
    -DWITH_OPENCL=OFF

3.9M    lib/libopencv_dnn.so.4.7.0
```

### 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
2023-05-15 12:23:18 +03:00
wanli
46991bcd62 Solve the bug of same shape broadcast with CUDA 2023-05-15 13:55:38 +08:00
Alexander Smorkalov
85b04f0b4d
Merge pull request #23557 from WanliZhong:eltwise_cpu_bug
fix nary elementwise bug in cpu
2023-05-11 15:56:46 +03:00
Dmitry Kurtaev
676afdc494 Update FlatBuffers source code to 23.5.9 2023-05-10 14:39:36 +03:00
wanli
85cc4086c8 fix nary elementwise bug in cpu 2023-05-10 14:29:33 +08:00
Alexander Smorkalov
25c28c5da4
Merge pull request #23485 from zihaomu:add_onnx_where
DNN: add ONNX where node support
2023-05-05 09:21:07 +03:00
zihaomu
0513741a85 add broadcast where node 2023-05-05 11:16:19 +08:00
Alexander Smorkalov
351589e5fb
Merge pull request #23491 from fengyuentau:patch_for_segment_anything
Fixes for Segment Anything
2023-05-04 21:07:58 +03:00
Alexander Alekhin
3c76b33532 Merge pull request #22614 from zihaomu:add_std2DB_API 2023-05-01 19:37:23 +00:00
zihaomu
8be93a6de7 add scale factor to DB demo. 2023-04-30 22:03:21 +08:00
Abduragim Shtanchaev
3b1ee0549b added test for lstm without hidden
states initialization
2023-04-25 16:01:13 +03:00
Alexander Smorkalov
e3e1f704a4
Merge pull request #23528 from WanliZhong:issue23278
DNN/CUDA: make 'abcd op 1b11' broadcast eltwise operator support cuda
2023-04-24 19:31:55 +03:00
Dmitry Kurtaev
aa57833ad5
Merge pull request #23409 from dkurt:dnn_tflite_quant
Import and inference INT8 quantized TFLite model #23409

### Pull Request Readiness Checklist

* Support quantized TFLite models
* Enable fused activations (FP32, INT8)

**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1048

![res](https://user-images.githubusercontent.com/25801568/231433201-566b4bd6-ccff-462c-9e74-adbdcdf3648b.png)

on the image, green boxes are from TFLite and red boxes from OpenCV

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
2023-04-24 13:44:10 +03:00
Abduragim Shtanchaev
e4e774d42b
Merge pull request #23475 from Abdurrahheem:lstm_fix_initialization
Fix ONNX parser for single-layer LSTM hidden and cell states #23475

### Fix ONNX parser for single-layer LSTM hidden and cell states

### 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


This PR addresses #21118 [issue](https://github.com/opencv/opencv/issues/21118). The problem is that the ONNX parser is unable to read the hidden state and cell state for single-layer LSTMs. This PR fixes the issue by updating the parser to correctly read hidden and cell states.
2023-04-24 13:39:41 +03:00
wanli
e4360294c5 make 'abcd op 1b11' broadcast support cuda 2023-04-23 17:46:50 +08:00
Alexander Alekhin
9ab0ff6cf2 Merge pull request #23511 from zihaomu:issue_23465 2023-04-22 04:01:26 +00:00
Zihao Mu
601778e0e6
Merge pull request #22750 from zihaomu:improve_blobFromImage
DNN: Add New API blobFromImageParam #22750

The purpose of this PR:

1. Add new API `blobFromImageParam` to extend `blobFromImage` API. It can support the different data layout (NCHW or NHWC), and letter_box.
2. ~~`blobFromImage` can output `CV_16F`~~

### 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
2023-04-21 19:10:17 +03:00
zihaomu
54e1a8709d fix the bug, disable the fast1x1 when padding is not 0. 2023-04-21 10:55:07 +08:00
Yuantao Feng
3c1fcd5deb
Merge pull request #23401 from fengyuentau:fix_cann_layer_support
dnn: Support more operators in CANN backend #23401

This PR adds the support of following layers:

- [x] Sub
- [x] PRelu
- [x] DeConv
- [x] Also warn users if backend is switched back to default if some of the layers are not supported.
- [ ] [Dropped] LSTM: some hacks (adding layers) were introduced which makes it even harder to build the graph for CANN backend.

### 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
2023-04-20 10:18:35 +03:00
Abduragim Shtanchaev
b3a2444bcf
Merge pull request #23501 from Abdurrahheem:additional_lstm_tests
Added LSTM and GRU tests for various batch and input length sizes #23501

Added tests with various sequence length and batch sizes
Test data: https://github.com/opencv/opencv_extra/pull/1057

### 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
2023-04-20 10:11:33 +03:00
Alexander Smorkalov
aa17f881b1
Merge pull request #23482 from zihaomu:onnx_opset13_split
DNN: support the split node of onnx opset >= 13
2023-04-14 11:59:57 +03:00
fengyuentau
4f99e5ab37 allow null constant_value in Pad and ignore it when loading 2023-04-14 16:50:16 +08:00
fengyuentau
88cacd35c5 support broadcast on axis > 1 for Expand 2023-04-14 15:52:27 +08:00
Alexander Smorkalov
136121f6ee
Merge pull request #22660 from zhouzq-thu:4.x
Fix objectness is not assigned in dnn::region_layer
2023-04-12 09:34:58 +03:00
Alexander Smorkalov
3f02c9d5b9
Merge pull request #23310 from hanliutong:fix_hal_compatibility
Fix HAL compatibility layer
2023-04-11 12:43:54 +03:00
zihaomu
51281f8d69 support the split node of onnx opset >= 13 2023-04-11 16:18:50 +08:00
Yuantao Feng
3a83a35ab0
Merge pull request #23296 from fengyuentau:fix_identifying_constant
Fix identifying initializers in ONNX graph simplification #23296

Fixes https://github.com/opencv/opencv/issues/23295

### 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
2023-04-06 15:35:31 +03:00
Dmitry Kurtaev
5e1d33329b Several fixes for ONNX importer: Expand, Gather 2023-03-27 22:15:26 +03:00
HAN Liutong
a809ae4e88 Fix HAL compatibility layer and modify use cases. 2023-03-27 21:30:47 +08:00
Dmitry Kurtaev
5df6b4a756
Merge pull request #23325 from dkurt:dnn_input_info
Propagate inputs info for ONNX and TFLite models

### Pull Request Readiness Checklist

Needed for generic applications such as benchmarking pipelines. So OpenCV can tell about the default input shapes specified in the models.

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
2023-03-21 14:50:53 +03:00
Alexander Smorkalov
924a65413a
Merge pull request #23357 from zihaomu:fix_winograd_error_32bit
DNN : fix bug in 32 bit cpu
2023-03-15 11:24:54 +03:00
zihaomu
6bac5453d1 fix bug in 32 bit cpu 2023-03-15 08:24:55 +08:00
Alexander Smorkalov
ccbc784195
Merge pull request #23354 from zihaomu:issue_23351
DNN : fix bug in layer fusion
2023-03-14 17:23:25 +03:00
zihaomu
386be97ce2 fix bug in layer fusion 2023-03-14 19:06:06 +08:00
tingbo.liao
7d032de7e8 Fix bugs of test case failure
4 failed tests in open_test_dnn listed below:
* Test_Caffe_layers.Conv_Elu/0, where GetParam() = OCV/CPU
* Test_ONNX_layers.ConvResizePool1d/0, where GetParam() = OCV/CPU
* Test_TensorFlow_layers.tf_reshape_nhwc/0, where GetParam() = OCV/CPU
* Test_Torch_layers.net_inception_block/0, where GetParam() = OCV/CPU

In winofunc_AtXA_8x8_f32 and winofunc_BtXB_8x8_f32
implementation, incorrect input parameters cause tests failure.

Add four new different variables for the last four input parameters of
v_transpose4x4 to fix bugs, and update related comments.

Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
2023-03-14 17:05:19 +08:00
Alexander Smorkalov
22a52766dc
Merge pull request #23343 from zihaomu:fix_test_onnx_conf
DNN Test ONNX: Fix the logic of the test case
2023-03-13 21:48:41 +03:00
Yuantao Feng
b94e13c8ae
Merge pull request #23319 from fengyuentau:fix_zoo_issue_136
Related issue: https://github.com/opencv/opencv_zoo/issues/136

Features added:

- Support operators with multiple output: ONNX Split.
- Support Slice without steps.

Bugs fixed:

- Wrong settings in ClipByValue (Relu6).
- Wrong calculation of pads in convolution layer (It is wrong generally but only fixed specifically for CANN for now).

### 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
2023-03-13 21:46:33 +03:00
zihaomu
ee3740af00 move global skip out of if loop, and add opencv_deny_list 2023-03-13 22:16:51 +08:00
Zihao Mu
e03e2e7f94
Merge pull request #23192 from zihaomu:clean_up_SIMD_code
### Purpose of this PR:
- Move all dispatch and SIMD code of `convolution layer` into `simd.hpp` file.
- Support Winograd at AVX-only machine.
- Re-name the folder from `fast_conv` to `cpu_kernels`. In the future, we can put other layers of CPU optimization into it, like `GEMM` or `MatMul`.

## Performance Test
Since this patch just focuses on the code style, the performance is expected as the same as before.
Test with the following script: 
`./bin/opencv_perf_dnn '--gtest_filter=*conv*' --gtest_output="xml:../1-0th.xml" --perf_threads=1`

### Test on X86 platform
Min (ms)
|Name of Test|4.x | patch | 4.x vs patch (x-factor)|
|---|:-:|:-:|:-:|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 19}, OCN=2, G=2, S=2, P=(1, 1), BIAS, OCV/CPU)|0.001|0.001|0.98|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 25}, OCN=2, G=2, P=(2, 2), PM=SAME, OCV/CPU)|0.001|0.001|0.95|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 6, 10}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.001|0.001|0.97|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.002|0.002|1.04|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.002|0.002|0.94|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.040|0.044|0.93|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)|0.010|0.010|1.00|
|conv3d::Conv3D::(GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)|0.106|0.103|1.03|
|conv3d::Conv3D::(GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)|0.041|0.040|1.03|
|conv3d::Conv3D::(GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.340|0.329|1.03|
|conv3d::Conv3D::(GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.590|0.567|1.04|
|conv3d::Conv3D::(GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)|1.374|1.314|1.05|
|conv3d::Conv3D::(GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)|3.715|3.528|1.05|
|conv3d::Conv3D::(GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)|1.181|1.166|1.01|
|conv3d::Conv3D::(GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)|2.689|2.587|1.04|
|conv3d::Conv3D::(GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)|4.754|4.500|1.06|
|conv3d::Conv3D::(GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)|9.612|9.112|1.05|
|conv3d::Conv3D::(GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)|69.000|64.676|1.07|
|conv3d::Conv3D::(GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)|20.248|18.451|1.10|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU)|1.395|1.392|1.00|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU)|1.990|1.984|1.00|
|conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU)|1.393|1.360|1.02|
|conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)|1.813|1.744|1.04|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)|1.190|1.191|1.00|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)|1.286|1.284|1.00|
|conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|2.295|2.279|1.01|
|conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU)|1.322|1.331|0.99|
|conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU)|3.784|3.533|1.07|
|conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.838|1.844|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU)|1.957|1.959|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU)|2.596|2.573|1.01|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU)|4.183|4.083|1.02|
|conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|2.413|2.406|1.00|
|conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|2.538|2.546|1.00|
|conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)|2.972|2.980|1.00|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU)|3.452|3.464|1.00|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU)|3.082|3.105|0.99|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|4.043|3.919|1.03|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU)|5.538|5.531|1.00|
|conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|3.393|3.418|0.99|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)|4.325|4.234|1.02|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)|6.009|5.908|1.02|
|conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)|6.557|6.376|1.03|
|conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|10.114|9.472|1.07|
|conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|10.373|9.879|1.05|
|conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|12.782|11.624|1.10|
|conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU)|90.931|90.552|1.00|
|conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|6.091|5.818|1.05|
|conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU)|7.083|6.643|1.07|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)|5.054|5.059|1.00|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|5.005|4.931|1.02|
|conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|4.951|5.065|0.98|
|conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)|11.957|11.293|1.06|
|conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)|5.328|5.250|1.01|
|conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU)|5.544|5.292|1.05|
|conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU)|6.186|5.893|1.05|
|conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU)|6.153|5.834|1.05|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU)|8.154|8.107|1.01|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU)|12.699|12.256|1.04|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU)|11.355|11.217|1.01|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU)|19.062|17.814|1.07|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU)|6.820|6.531|1.04|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU)|14.502|13.483|1.08|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU)|6.270|6.123|1.02|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)|13.173|12.451|1.06|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU)|8.326|7.652|1.09|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.605|16.465|1.07|
|conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)|15.675|14.771|1.06|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)|0.420|0.423|0.99|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)|6.788|6.491|1.05|
|conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU)|6.456|6.168|1.05|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)|0.263|0.261|1.01|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)|7.690|7.398|1.04|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)|0.200|0.202|0.99|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|10.542|10.464|1.01|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)|10.876|10.728|1.01|
|conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU)|7.194|6.768|1.06|
|conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU)|7.099|6.731|1.05|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)|0.147|0.162|0.91|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)|18.558|17.141|1.08|
|conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU)|7.641|7.219|1.06|
|conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU)|22.666|20.999|1.08|
|conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU)|8.523|7.921|1.08|
|conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)|8.514|8.109|1.05|
|conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU)|8.300|7.878|1.05|
|conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)|13.403|13.131|1.02|
|conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU)|8.920|8.357|1.07|
|conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)|28.827|27.616|1.04|
|conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|12.895|12.670|1.02|
|conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|14.120|13.078|1.08|
|conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|27.541|27.582|1.00|
|conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU)|32.367|31.140|1.04|
|conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|14.934|14.910|1.00|
|conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|18.289|18.491|0.99|
|conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)|37.857|36.845|1.03|
|conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|37.402|36.566|1.02|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|19.031|19.164|0.99|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|19.019|19.135|0.99|
|conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|20.077|19.400|1.03|
|conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|21.883|21.302|1.03|
|conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU)|51.288|49.851|1.03|
|conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|27.349|28.359|0.96|
|conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU)|24.915|25.130|0.99|
|conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|25.488|25.899|0.98|
|conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|27.346|27.390|1.00|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)|28.033|28.301|0.99|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|50.216|49.970|1.00|
|conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|29.670|29.513|1.01|
|conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|50.565|49.634|1.02|
|conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|37.900|37.814|1.00|
|conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|41.367|39.742|1.04|
|conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|49.128|50.350|0.98|
|conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|79.643|80.645|0.99|
|conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)|41.439|40.895|1.01|
|conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU)|46.504|46.220|1.01|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU)|98.086|96.842|1.01|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|102.447|97.299|1.05|
|conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|145.047|144.996|1.00|
|conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU)|206.104|195.543|1.05|


### Test on M1(ARM) platform
|Name of Test|4.x|patch|4.x vs patch (x-factor)|
|---|:-:|:-:|:-:|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 19}, OCN=2, G=2, S=2, P=(1, 1), BIAS, OCV/CPU)|0.001|0.001|0.97|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 25}, OCN=2, G=2, P=(2, 2), PM=SAME, OCV/CPU)|0.001|0.001|0.94|
|conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 6, 10}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.002|0.002|0.92|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.003|0.003|1.00|
|conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.003|0.003|1.00|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.031|0.031|1.00|
|conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)|0.009|0.009|1.00|
|conv3d::Conv3D::(GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)|0.066|0.066|1.01|
|conv3d::Conv3D::(GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)|0.102|0.102|1.00|
|conv3d::Conv3D::(GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.328|0.328|1.00|
|conv3d::Conv3D::(GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.693|0.747|0.93|
|conv3d::Conv3D::(GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)|1.268|1.266|1.00|
|conv3d::Conv3D::(GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)|3.530|3.581|0.99|
|conv3d::Conv3D::(GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)|1.186|1.188|1.00|
|conv3d::Conv3D::(GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)|2.682|2.683|1.00|
|conv3d::Conv3D::(GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)|4.490|4.501|1.00|
|conv3d::Conv3D::(GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)|8.914|8.938|1.00|
|conv3d::Conv3D::(GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)|69.819|69.876|1.00|
|conv3d::Conv3D::(GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)|24.058|22.420|1.07|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU)|2.240|2.236|1.00|
|conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU)|3.132|3.136|1.00|
|conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU)|1.920|1.919|1.00|
|conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)|2.343|2.346|1.00|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)|1.234|1.116|1.11|
|conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)|1.109|1.121|0.99|
|conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|3.197|3.084|1.04|
|conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU)|1.123|1.148|0.98|
|conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU)|4.836|5.061|0.96|
|conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.535|1.463|1.05|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU)|1.756|1.584|1.11|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU)|1.821|1.820|1.00|
|conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU)|7.049|6.672|1.06|
|conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.967|1.922|1.02|
|conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|1.943|1.977|0.98|
|conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)|2.464|2.310|1.07|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU)|2.860|2.904|0.98|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU)|2.428|2.483|0.98|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|2.955|2.983|0.99|
|conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU)|4.328|4.484|0.97|
|conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|2.712|2.778|0.98|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)|3.205|3.331|0.96|
|conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)|4.193|4.412|0.95|
|conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)|5.026|4.565|1.10|
|conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|14.490|14.213|1.02|
|conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|14.886|14.003|1.06|
|conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|15.923|15.184|1.05|
|conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU)|45.136|41.696|1.08|
|conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|4.995|4.631|1.08|
|conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU)|6.402|6.261|1.02|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)|4.478|3.965|1.13|
|conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|3.908|3.978|0.98|
|conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|4.176|4.206|0.99|
|conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)|21.509|21.136|1.02|
|conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)|4.426|4.082|1.08|
|conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU)|4.098|4.289|0.96|
|conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU)|4.646|5.105|0.91|
|conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU)|4.746|4.724|1.00|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU)|5.614|5.779|0.97|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU)|21.909|20.718|1.06|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU)|8.256|8.290|1.00|
|conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU)|25.196|23.267|1.08|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU)|5.721|5.172|1.11|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU)|20.066|18.322|1.10|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU)|4.448|4.542|0.98|
|conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)|19.193|19.013|1.01|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU)|6.009|5.964|1.01|
|conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU)|20.169|20.009|1.01|
|conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)|22.584|23.423|0.96|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)|0.372|0.504|0.74|
|conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)|5.426|5.456|0.99|
|conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU)|4.945|5.221|0.95|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)|0.210|0.261|0.81|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)|5.720|5.997|0.95|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)|0.149|0.161|0.93|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|7.154|7.225|0.99|
|conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)|7.184|7.223|0.99|
|conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU)|5.324|5.343|1.00|
|conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU)|5.114|5.238|0.98|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)|0.111|0.121|0.92|
|conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)|25.907|26.804|0.97|
|conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU)|5.695|5.654|1.01|
|conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU)|27.435|27.566|1.00|
|conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU)|6.944|6.164|1.13|
|conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)|7.180|6.717|1.07|
|conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU)|6.817|6.050|1.13|
|conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)|9.225|8.660|1.07|
|conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU)|7.496|6.625|1.13|
|conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)|35.520|36.056|0.99|
|conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|9.990|9.702|1.03|
|conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|10.517|10.746|0.98|
|conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|36.702|36.731|1.00|
|conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU)|41.035|38.280|1.07|
|conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|10.981|10.573|1.04|
|conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|12.863|12.384|1.04|
|conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)|50.437|54.088|0.93|
|conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|50.650|50.635|1.00|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|14.696|14.606|1.01|
|conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|16.201|15.426|1.05|
|conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|16.061|14.292|1.12|
|conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|17.743|18.250|0.97|
|conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU)|77.909|78.165|1.00|
|conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|21.579|21.879|0.99|
|conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU)|20.424|19.589|1.04|
|conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|19.389|19.461|1.00|
|conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|21.319|20.358|1.05|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)|22.609|21.826|1.04|
|conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|25.497|25.789|0.99|
|conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|21.966|22.108|0.99|
|conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|35.883|33.470|1.07|
|conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|31.041|29.314|1.06|
|conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|29.922|28.145|1.06|
|conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|31.624|31.148|1.02|
|conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|38.564|39.164|0.98|
|conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)|31.502|30.269|1.04|
|conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU)|34.248|34.589|0.99|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU)|130.211|134.120|0.97|
|conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|127.490|132.874|0.96|
|conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|199.834|200.081|1.00|
|conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU)|247.346|247.523|1.00|


### 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


```
force_builders=Linux AVX2,Custom Win
build_image:Custom Win=msvs2019
CPU_BASELINE:Custom Win=AVX512_SKX
```
2023-03-10 11:59:49 +03:00
Alexander Alekhin
9eb5e39ff3 dnn(tflite): fix wrong axis normalization 2023-02-21 21:20:37 +00:00
Alexander Alekhin
bdff0949bb dnn(tflite): add 3rdparty flatbuffers with pre-generated schema 2023-02-21 16:06:19 +00:00
Zihao Mu
20dac7ea48
Merge pull request #23255 from zihaomu:fused_cuda_naryeltwise
DNN: fuse conv+naryEletwise on CUDA backend.
2023-02-17 10:18:13 +00:00
Alexander Alekhin
58d8a2702a Merge pull request #23243 from WanliZhong:accelerate_palm_det 2023-02-14 16:25:02 +00:00
Dmitry Kurtaev
76350cd30f
Merge pull request #23161 from dkurt:dnn_tflite
TFLite models importer

* initial commit

* Refactor TFLiteImporter

* Better FlatBuffers detection

* Add permute before 4D->3D reshape

* Track layers layout

* TFLite Convolution2DTransposeBias layer

* Skip TFLite tests without FlatBuffers

* Fix check of FlatBuffers in tests. Add readNetFromTFLite from buffer

* TFLite Max Unpooling test

* Add skip for TFLite unpooling test

* Revert DW convolution workaround

* Fix ObjC bindings

* Better errors handling

* Regenerate TFLite schema using flatc

* dnn(tflite): more checks, better logging

* Checks for unimplemented fusion. Fix tests
2023-02-13 14:00:20 +00:00
Yuantao Feng
c2b7c1f13b
Merge pull request #23219 from fengyuentau:add_gelu
Add GELU layer for vision transformers

* add gelu and gelu approximation

* drop setKernelParams
2023-02-10 18:03:29 +00:00
wanli
c8f5e228fc release MUL and ADD operator on CUDA 2023-02-10 19:33:59 +08:00
Alexander Alekhin
96a45e842e
Merge pull request #23061 from WanliZhong:gemm_cuda
DNN: make GEMM can be supported with transA and transB in CUDA
2023-02-09 00:06:32 +03:00
wanli
4718a4bf81 make GEMM can be supported with transA and transB in CUDA 2023-01-31 15:14:17 +08:00
Alexander Alekhin
cd44aa0bb1 Merge pull request #23162 from zihaomu:issue_23151 2023-01-28 13:00:43 +00:00
zihaomu
f45a12439a fix depth wise issue. 2023-01-28 11:41:00 +08:00
Yuantao Feng
4d918ba40b
Merge pull request #23047 from fengyuentau:layer_norm
dnn: add layer normalization for vision transformers

* add layer norm onnx parser, impl and tests

* add onnx graph simplifier for layer norm expanded

* handle the case when constants are of type Initializer

* add test case for layer norm expanded with initializers

* use CV_Assert & CV_CheckType in place of CV_Assert_N; use forward_fallback for OCL_FP16

* use const ref / ref in parameters of invoker::run; extract inner const if from nested loop; use size_t in place of ull

* template hasBias

* remove trailing whitespace

* use pointer parameter with null check; move normSize division & mean_square division outside of loop; use std::max to ensure positive value before std::sqrt

* refactor implementation, optimize parallel_for

* disable layer norm expanded

* remove the removal of layer norm optional outputs
2023-01-27 16:35:59 +03:00