opencv/modules/dnn/test
Yuantao Feng 347d673a87
Merge pull request #23279 from fengyuentau:add_topk
dnn: add ONNX TopK #23279

Merge with https://github.com/opencv/opencv_extra/pull/1200

Partially fixes #22890 and #20258

To-do:

- [x] TopK forward impl
- [x] add tests
- [x] support Opset 1 & 10 if possible
- [ ] ~Support other backends~ (TopK has two outputs, which is not supported by other backends, such as openvino)


Perf:

M1 (time in millisecond)

| input shape     | axis | dnn  | ort  |
| --------------- | ---- | ---- | ---- |
| (1000, 100)     | 0    | 1.68 | 4.07 |
| (1000, 100) K5  | 0    | 1.13 | 0.12 |
| (1000, 100)     | 1    | 0.96 | 0.77 |
| (100, 100, 100) | 0    | 10.00 | 31.13 |
| (100, 100, 100) | 1    | 7.33 | 9.17 |
| (100, 100, 100) | 2    | 7.52 | 9.48 |

M2 (time in milisecond)

| input shape     | axis | dnn  | ort  |
| --------------- | ---- | ---- | ---- |
| (1000, 100)     | 0    | 0.76 | 2.44 |
| (1000, 100) K5 | 0 | 0.68 | 0.07 |
| (1000, 100)     | 1    | 0.41 | 0.50 |
| (100, 100, 100) | 0    | 4.83 | 17.52|
| (100, 100, 100) | 1    | 3.60 | 5.08 |
| (100, 100, 100) | 2    | 3.73 | 5.10 |

ONNXRuntime performance testing script: https://gist.github.com/fengyuentau/a119f94fd16721ec9974b8c7b0a45d4c

### 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
2024-08-21 17:03:24 +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 #25644 from DaniAffCH:blockwise-quantization 2024-07-30 14:16:08 +03:00
test_onnx_conformance_layer_filter__vulkan_denylist.inl.hpp Merge pull request #25644 from DaniAffCH:blockwise-quantization 2024-07-30 14:16:08 +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 #25644 from DaniAffCH:blockwise-quantization 2024-07-30 14:16:08 +03:00
test_onnx_conformance_layer_filter_opencv_ocl_fp32_denylist.inl.hpp Merge pull request #25644 from DaniAffCH:blockwise-quantization 2024-07-30 14:16:08 +03:00
test_onnx_conformance_layer_parser_denylist.inl.hpp Merge pull request #25644 from DaniAffCH:blockwise-quantization 2024-07-30 14:16:08 +03:00
test_onnx_conformance.cpp Merge pull request #25644 from DaniAffCH:blockwise-quantization 2024-07-30 14:16:08 +03:00
test_onnx_importer.cpp Merge pull request #23279 from fengyuentau:add_topk 2024-08-21 17:03:24 +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