Merge pull request #25463 from WanliZhong:ocvface2YuNet

Change opencv_face_detector related tests and samples from caffe to onnx #25463

Part of https://github.com/opencv/opencv/issues/25314

This PR aims to change the tests related to opencv_face_detector from caffe framework to onnx. Tests in `test_int8_layer.cpp` and `test_caffe_importer.cpp` will be removed in https://github.com/opencv/opencv/pull/25323

### 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

modules/dnn/misc/python/test/test_dnn.py

@@ -286,41 +286,42 @@ class dnn_test(NewOpenCVTests):
 
 
     def test_face_detection(self):
-        proto = self.find_dnn_file('dnn/opencv_face_detector.prototxt')
-        model = self.find_dnn_file('dnn/opencv_face_detector.caffemodel', required=False)
-        if proto is None or model is None:
-            raise unittest.SkipTest("Missing DNN test files (dnn/opencv_face_detector.{prototxt/caffemodel}). Verify OPENCV_DNN_TEST_DATA_PATH configuration parameter.")
-
+        model = self.find_dnn_file('dnn/onnx/models/yunet-202303.onnx', required=False)
         img = self.get_sample('gpu/lbpcascade/er.png')
-        blob = cv.dnn.blobFromImage(img, mean=(104, 177, 123), swapRB=False, crop=False)
 
-        ref = [[0, 1, 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631],
-               [0, 1, 0.9934696,  0.2831718,  0.50738752, 0.345781,   0.5985168],
-               [0, 1, 0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290],
-               [0, 1, 0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477],
-               [0, 1, 0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494],
-               [0, 1, 0.95097077, 0.51901293, 0.45863652, 0.5777427,  0.5347801]]
+        ref = [[1, 339.62445, 35.32416, 30.754604, 40.202126, 0.9302596],
+               [1, 140.63962, 255.55545, 32.832615, 41.767395, 0.916015],
+               [1, 68.39314, 126.74046, 30.29324, 39.14823, 0.90639645],
+               [1, 119.57139, 48.482178, 30.600697, 40.485996, 0.906021],
+               [1, 259.0921, 229.30713, 31.088186, 39.74022, 0.90490955],
+               [1, 405.69778, 87.28158, 33.393406, 42.96226, 0.8996978]]
 
         print('\n')
         for backend, target in self.dnnBackendsAndTargets:
             printParams(backend, target)
 
-            net = cv.dnn.readNet(proto, model)
-            net.setPreferableBackend(backend)
-            net.setPreferableTarget(target)
-            net.setInput(blob)
-            out = net.forward().reshape(-1, 7)
+            net = cv.FaceDetectorYN.create(
+                model=model,
+                config="",
+                input_size=img.shape[:2],
+                score_threshold=0.3,
+                nms_threshold=0.45,
+                top_k=5000,
+                backend_id=backend,
+                target_id=target
+            )
 
-            scoresDiff = 4e-3 if target in [cv.dnn.DNN_TARGET_OPENCL_FP16, cv.dnn.DNN_TARGET_MYRIAD] else 1e-5
-            iouDiff = 2e-2 if target in [cv.dnn.DNN_TARGET_OPENCL_FP16, cv.dnn.DNN_TARGET_MYRIAD] else 1e-4
+            out = net.detect(img)
+            out = out[1]
+            out = out.reshape(-1, 15)
 
             ref = np.array(ref, np.float32)
-            refClassIds, testClassIds = ref[:, 1], out[:, 1]
-            refScores, testScores = ref[:, 2], out[:, 2]
-            refBoxes, testBoxes = ref[:, 3:], out[:, 3:]
+            refClassIds, testClassIds = ref[:, 0], np.ones(out.shape[0], np.float32)
+            refScores, testScores = ref[:, -1], out[:, -1]
+            refBoxes, testBoxes = ref[:, 1:5], out[:, 0:4]
 
             normAssertDetections(self, refClassIds, refScores, refBoxes, testClassIds,
-                                 testScores, testBoxes, 0.5, scoresDiff, iouDiff)
+                                 testScores, testBoxes, 0.5)
 
     def test_async(self):
         timeout = 10*1000*10**6  # in nanoseconds (10 sec)