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

modules/dnn/perf/perf_layer.cpp

@@ -1043,4 +1043,67 @@ INSTANTIATE_TEST_CASE_P(/**/, Layer_Elementwise,
                                               /* withWebnn= */           false,
                                               /* withCann= */            false));
 
+struct Layer_TopK : public TestBaseWithParam<tuple<Backend, Target>> {
+    void test_layer(const std::vector<int> &input_shape, const int K, const int axis) {
+        int backend_id = get<0>(GetParam());
+        int target_id = get<1>(GetParam());
+
+        Mat input_data(input_shape, CV_32F);
+        randn(input_data, -1.f, 1.f);
+
+        Net net;
+        LayerParams lp;
+        lp.type = "TopK";
+        lp.name = "testLayer";
+        lp.set("k", K);
+        lp.set("axis", axis);
+        net.addLayerToPrev(lp.name, lp.type, lp);
+
+        // Warmup
+        {
+            net.setInput(input_data);
+            net.setPreferableBackend(backend_id);
+            net.setPreferableTarget(target_id);
+            net.forward();
+        }
+
+        TEST_CYCLE() {
+            net.forward();
+        }
+
+        SANITY_CHECK_NOTHING();
+    }
+
+    std::vector<int> input_shape_2d{1000, 100};
+    std::vector<int> input_shape_3d{100, 100, 100};
+};
+
+PERF_TEST_P_(Layer_TopK, TopK_2D_Axis0) {
+    test_layer(input_shape_2d, input_shape_2d[0] / 2, 0);
+}
+PERF_TEST_P_(Layer_TopK, TopK_2D_Axis0_K5) {
+    test_layer(input_shape_2d, 5, 0);
+}
+PERF_TEST_P_(Layer_TopK, TopK_2D_Axis1) {
+    test_layer(input_shape_2d, input_shape_2d[1] / 2, 1);
+}
+PERF_TEST_P_(Layer_TopK, TopK_3D_Axis0) {
+    test_layer(input_shape_3d, input_shape_3d[0] / 2, 0);
+}
+PERF_TEST_P_(Layer_TopK, TopK_3D_Axis1) {
+    test_layer(input_shape_3d, input_shape_3d[1] / 2, 1);
+}
+PERF_TEST_P_(Layer_TopK, TopK_3D_Axis2) {
+    test_layer(input_shape_3d, input_shape_3d[2] / 2, 2);
+}
+INSTANTIATE_TEST_CASE_P(/**/, Layer_TopK,
+                        dnnBackendsAndTargets(/* withInferenceEngine= */ false,
+                                              /* withHalide= */          false,
+                                              /* withCpuOCV= */          true,
+                                              /* withVkCom= */           false,
+                                              /* withCUDA= */            false,
+                                              /* withNgraph= */          false,
+                                              /* withWebnn= */           false,
+                                              /* withCann= */            false));
+
 } // namespace