Updated yunet model usage and added .gitattributes

.gitattributes

@@ -0,0 +1,26 @@
+
+# Caffe
+*.caffemodel filter=lfs diff=lfs merge=lfs -text
+
+# Tensorflow
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pbtxt filter=lfs diff=lfs merge=lfs -text
+
+# Torch
+*.t7 filter=lfs diff=lfs merge=lfs -text
+*.net filter=lfs diff=lfs merge=lfs -text
+
+# Darknet
+*.weights filter=lfs diff=lfs merge=lfs -text
+
+# ONNX
+*.onnx filter=lfs diff=lfs merge=lfs -text
+
+# NPY
+*.npy filter=lfs diff=lfs merge=lfs -text
+
+# Images
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,9 @@
+*.pyc
+**/__pycache__
+**/__pycache__/**
+
+.vscode
+
+build/
+**/build
+**/build/**

demo.py

@@ -1,19 +1,20 @@
 # This file is part of OpenCV Zoo project.
 # It is subject to the license terms in the LICENSE file found in the same directory.
 
-
-import sys
 import argparse
 
 import numpy as np
 import cv2 as cv
+from huggingface_hub import hf_hub_download
+
+# Download ONNX model from Hugging Face
+model_d = hf_hub_download(repo_id="opencv/face_detection_yunet", filename="face_detection_yunet_2023mar.onnx")
 
 # Check OpenCV version
 opencv_python_version = lambda str_version: tuple(map(int, (str_version.split("."))))
 assert opencv_python_version(cv.__version__) >= opencv_python_version("4.10.0"), \
        "Please install latest opencv-python for benchmark: python3 -m pip install --upgrade opencv-python"
 
-sys.path.append('../face_detection_yunet')
 from yunet import YuNet
 
 from ediffiqa import eDifFIQA
@@ -52,8 +53,6 @@ ediffiqa_parser.add_argument('--model_q', '-mq', type=str, default='ediffiqa_tin
                     help="Usage: Set model type, defaults to 'ediffiqa_tiny_jun2024.onnx'.")
 
 yunet_parser = parser.add_argument_group("YuNet", " Parameters of YuNet - For face detection ")
-yunet_parser.add_argument('--model_d', '-md', type=str, default='../face_detection_yunet/face_detection_yunet_2023mar.onnx',
-                    help="Usage: Set model type, defaults to '../face_detection_yunet/face_detection_yunet_2023mar.onnx'.")
 yunet_parser.add_argument('--conf_threshold', type=float, default=0.9,
                     help='Usage: Set the minimum needed confidence for the model to identify a face, defauts to 0.9. Smaller values may result in faster detection, but will limit accuracy. Filter out faces of confidence < conf_threshold.')
 yunet_parser.add_argument('--nms_threshold', type=float, default=0.3,
@@ -104,7 +103,6 @@ def align_image(image, detection_data):
 
 
 if __name__ == '__main__':
-
     backend_id = backend_target_pairs[args.backend_target][0]
     target_id = backend_target_pairs[args.backend_target][1]
 
@@ -120,7 +118,7 @@ if __name__ == '__main__':
 
     # Instantiate YuNet (face detection)
     model_detect = YuNet(
-        modelPath=args.model_d,
+        modelPath=model_d,
         inputSize=[320, 320],
         confThreshold=args.conf_threshold,
         nmsThreshold=args.nms_threshold,
@@ -152,4 +150,3 @@ if __name__ == '__main__':
 
     print(f" Saving visualization to results.jpg. ")
     cv.imwrite('results.jpg', viz_image)
-

yunet.py

@@ -0,0 +1,55 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+from itertools import product
+
+import numpy as np
+import cv2 as cv
+
+class YuNet:
+    def __init__(self, modelPath, inputSize=[320, 320], confThreshold=0.6, nmsThreshold=0.3, topK=5000, backendId=0, targetId=0):
+        self._modelPath = modelPath
+        self._inputSize = tuple(inputSize) # [w, h]
+        self._confThreshold = confThreshold
+        self._nmsThreshold = nmsThreshold
+        self._topK = topK
+        self._backendId = backendId
+        self._targetId = targetId
+
+        self._model = cv.FaceDetectorYN.create(
+            model=self._modelPath,
+            config="",
+            input_size=self._inputSize,
+            score_threshold=self._confThreshold,
+            nms_threshold=self._nmsThreshold,
+            top_k=self._topK,
+            backend_id=self._backendId,
+            target_id=self._targetId)
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackendAndTarget(self, backendId, targetId):
+        self._backendId = backendId
+        self._targetId = targetId
+        self._model = cv.FaceDetectorYN.create(
+            model=self._modelPath,
+            config="",
+            input_size=self._inputSize,
+            score_threshold=self._confThreshold,
+            nms_threshold=self._nmsThreshold,
+            top_k=self._topK,
+            backend_id=self._backendId,
+            target_id=self._targetId)
+
+    def setInputSize(self, input_size):
+        self._model.setInputSize(tuple(input_size))
+
+    def infer(self, image):
+        # Forward
+        faces = self._model.detect(image)
+        return np.empty(shape=(0, 5)) if faces[1] is None else faces[1]