mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-12-15 09:49:13 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
93b607dc72
opencv/modules/dnn/test
History
Yuantao Feng 23b244d3a3
Merge pull request #25881 from fengyuentau:dnn/cpu/optimize_activations_with_v_exp 
dnn: optimize activations with v_exp #25881

Merge with https://github.com/opencv/opencv_extra/pull/1191.

This PR optimizes the following activations:

- [x] Swish
- [x] Mish
- [x] Elu
- [x] Celu
- [x] Selu
- [x] HardSwish

### Performance (Updated on 2024-07-18)

#### AmLogic A311D2 (ARM Cortex A73 + A53)

```
Geometric mean (ms)

            Name of Test              activations activations.patch activations.patch
                                                                              vs
                                                                         activations
                                                                          (x-factor)
Celu::Layer_Elementwise::OCV/CPU        115.859          27.930              4.15
Elu::Layer_Elementwise::OCV/CPU          27.846          27.003              1.03
Gelu::Layer_Elementwise::OCV/CPU         0.657           0.602               1.09
HardSwish::Layer_Elementwise::OCV/CPU    31.885          6.781               4.70
Mish::Layer_Elementwise::OCV/CPU         35.729          32.089              1.11
Selu::Layer_Elementwise::OCV/CPU         61.955          27.850              2.22
Swish::Layer_Elementwise::OCV/CPU        30.819          26.688              1.15
```

#### Apple M1

```
Geometric mean (ms)

               Name of Test                activations activations.patch activations.patch
                                                                                   vs
                                                                              activations
                                                                               (x-factor)
Celu::Layer_Elementwise::OCV/CPU              16.184          2.118               7.64
Celu::Layer_Elementwise::OCV/CPU_FP16         16.280          2.123               7.67
Elu::Layer_Elementwise::OCV/CPU               9.123           1.878               4.86
Elu::Layer_Elementwise::OCV/CPU_FP16          9.085           1.897               4.79
Gelu::Layer_Elementwise::OCV/CPU              0.089           0.081               1.11
Gelu::Layer_Elementwise::OCV/CPU_FP16         0.086           0.074               1.17
HardSwish::Layer_Elementwise::OCV/CPU         1.560           1.555               1.00
HardSwish::Layer_Elementwise::OCV/CPU_FP16    1.536           1.523               1.01
Mish::Layer_Elementwise::OCV/CPU              6.077           2.476               2.45
Mish::Layer_Elementwise::OCV/CPU_FP16         5.990           2.496               2.40
Selu::Layer_Elementwise::OCV/CPU              11.351          1.976               5.74
Selu::Layer_Elementwise::OCV/CPU_FP16         11.533          1.985               5.81
Swish::Layer_Elementwise::OCV/CPU             4.687           1.890               2.48
Swish::Layer_Elementwise::OCV/CPU_FP16        4.715           1.873               2.52
```

#### Intel i7-12700K

```
Geometric mean (ms)

            Name of Test              activations activations.patch activations.patch
                                                                    vs
                                                               activations
                                                                (x-factor)
Celu::Layer_Elementwise::OCV/CPU        17.106       3.560         4.81
Elu::Layer_Elementwise::OCV/CPU          5.064       3.478         1.46
Gelu::Layer_Elementwise::OCV/CPU         0.036       0.035         1.04
HardSwish::Layer_Elementwise::OCV/CPU    2.914       2.893         1.01
Mish::Layer_Elementwise::OCV/CPU         3.820       3.529         1.08
Selu::Layer_Elementwise::OCV/CPU        10.799       3.593         3.01
Swish::Layer_Elementwise::OCV/CPU        3.651       3.473         1.05
```

### 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
2024-07-19 16:03:19 +03:00
..
cityscapes_semsegm_test_enet.py Misc. modules/ typos 2018-02-12 07:09:43 -05:00
imagenet_cls_test_alexnet.py change fcn8s-heavy-pascal tests from caffe to onnx 2024-05-03 00:15:09 +08:00
imagenet_cls_test_googlenet.py Misc. modules/ typos 2018-02-12 07:09:43 -05:00
imagenet_cls_test_inception.py fix 4.x links 2021-12-22 13:24:30 +00:00
npy_blob.cpp dnn: fix precomp.hpp usage 2018-02-28 17:06:26 +03:00
npy_blob.hpp dnn: fix precomp.hpp usage 2018-02-28 17:06:26 +03:00
pascal_semsegm_test_fcn.py change fcn8s-heavy-pascal tests from caffe to onnx 2024-05-03 00:15:09 +08:00
test_backends.cpp Merge pull request #24834 from fengyuentau:cuda_naryeltwise_broadcast 2024-01-11 10:04:46 +03:00
test_caffe_importer.cpp dnn(test): skip very long debug tests, reduce test time 2023-12-25 08:44:06 +00:00
test_common.cpp cmake: fix build of dnn tests with shared common code 2019-03-31 08:52:25 +00:00
test_common.hpp Merge pull request #25880 from Jamim:fix/cuda-no-fp16 2024-07-10 12:39:30 +03:00
test_common.impl.hpp Merge pull request #25181 from dkurt:release_conv_weights 2024-03-25 09:03:28 +03:00
test_darknet_importer.cpp dnn(test): skip very long debug tests, reduce test time 2023-12-25 08:44:06 +00:00
test_googlenet.cpp Merge pull request #22275 from zihaomu:fp16_support_conv 2023-05-17 09:38:33 +03:00
test_graph_simplifier.cpp Merge pull request #25271 from fengyuentau:matmul_bias 2024-03-29 17:35:23 +03:00
test_ie_models.cpp Fix for OpenVINO 2024.0 2024-03-18 15:05:50 +04:00
test_int8_layers.cpp Merge pull request #25779 from fengyuentau:dnn/fix_onnx_depthtospace 2024-06-21 19:28:22 +03:00
test_layers.cpp Skip Test_Caffe_layers.Concat with Vulkan due to sporadic failures. 2024-05-17 11:54:25 +03:00
test_main.cpp Merge pull request #23109 from seanm:misc-warnings 2023-10-06 13:33:21 +03:00
test_misc.cpp Merge pull request #23736 from seanm:c++11-simplifications 2024-01-19 16:53:08 +03:00
test_model.cpp Made fcn-resnet50-12.onnx model optional. 2024-05-03 16:14:22 +03:00
test_nms.cpp batched nms impl 2022-11-29 15:32:34 +08:00
test_onnx_conformance_layer_filter__cuda_denylist.inl.hpp Merge pull request #25630 from fengyuentau:nary-multi-thread 2024-07-03 10:09:05 +03:00
test_onnx_conformance_layer_filter__cuda_fp16_denylist.inl.hpp Merge pull request #25630 from fengyuentau:nary-multi-thread 2024-07-03 10:09:05 +03:00
test_onnx_conformance_layer_filter__halide_denylist.inl.hpp Merge pull request #24353 from alexlyulkov:al/fixed-cumsum-layer 2023-10-03 13:58:25 +03:00
test_onnx_conformance_layer_filter__openvino.inl.hpp Merge pull request #25881 from fengyuentau:dnn/cpu/optimize_activations_with_v_exp 2024-07-19 16:03:19 +03:00
test_onnx_conformance_layer_filter__vulkan_denylist.inl.hpp Merge pull request #25630 from fengyuentau:nary-multi-thread 2024-07-03 10:09:05 +03:00
test_onnx_conformance_layer_filter_opencv_all_denylist.inl.hpp Merge pull request #25630 from fengyuentau:nary-multi-thread 2024-07-03 10:09:05 +03:00
test_onnx_conformance_layer_filter_opencv_cpu_denylist.inl.hpp Merge pull request #21865 from rogday:nary_eltwise_layers 2022-07-19 06:14:05 +03:00
test_onnx_conformance_layer_filter_opencv_denylist.inl.hpp move global skip out of if loop, and add opencv_deny_list 2023-03-13 22:16:51 +08:00
test_onnx_conformance_layer_filter_opencv_ocl_fp16_denylist.inl.hpp Merge pull request #25630 from fengyuentau:nary-multi-thread 2024-07-03 10:09:05 +03:00
test_onnx_conformance_layer_filter_opencv_ocl_fp32_denylist.inl.hpp implementation of scatter and scatternd with conformance tests enabled 2022-10-17 11:30:32 +08:00
test_onnx_conformance_layer_parser_denylist.inl.hpp Merge pull request #25881 from fengyuentau:dnn/cpu/optimize_activations_with_v_exp 2024-07-19 16:03:19 +03:00
test_onnx_conformance.cpp Merge pull request #25881 from fengyuentau:dnn/cpu/optimize_activations_with_v_exp 2024-07-19 16:03:19 +03:00
test_onnx_importer.cpp Merge pull request #25147 from fengyuentau:dnn/elementwise_layers/speedup 2024-07-08 14:24:36 +03:00
test_precomp.hpp dnn: reduce set of ignored warnings 2018-11-15 13:15:59 +03:00
test_tf_importer.cpp dnn(test): skip very long debug tests, reduce test time 2023-12-25 08:44:06 +00:00
test_tflite_importer.cpp Merge pull request #25613 from CNOCycle:tflite/ops 2024-05-31 19:31:21 +03:00
test_torch_importer.cpp DNN: add the Winograd fp16 support (#23654) 2023-11-20 13:45:37 +03:00