cv.dnn.readNet()

官方文档：
https://docs.opencv.org/3.4/d6/d0f/group__dnn.html#ga3b34fe7a29494a6a4295c169a7d32422

Python使用方法举例（Examples for Python）：

如使用Darknet的预训练模型：

weights = "yolov2.weights"
config_file = "yolov2.cfg"
# read pre-trained model and config file
net = cv2.dnn.readNet(weights, config_file)

如使用Caffe的预训练模型：

path_to_prototxt = "deploy.prototxt"
path_to_caffemodel = "hed_pretrained_bsds.caffemodel"
net = cv.dnn.readNet(path_to_prototxt, path_to_caffemodel)

C++使用方法举例（Examples for C++）：

samples/dnn/classification.cpp;
samples/dnn/object_detection.cpp;
samples/dnn/openpose.cpp;
samples/dnn/segmentation.cpp;
samples/dnn/text_detection.cpp.

可使用的模型（Available Model）：

Caffe, TensorFlow, Torch, Darknet, DLDT, ONNX

模型权重文件支持的文件格式：

• *.caffemodel (Caffe, http://caffe.berkeleyvision.org/)
• *.pb (TensorFlow, https://www.tensorflow.org/)
• *.t7 | *.net (Torch, http://torch.ch/)
• *.weights (Darknet, https://pjreddie.com/darknet/)
• *.bin (DLDT, https://software.intel.com/openvino-toolkit)
• *.onnx (ONNX, https://onnx.ai/)

模型配置文件支持的文件格式：

*.prototxt (Caffe, http://caffe.berkeleyvision.org/)
*.pbtxt (TensorFlow, https://www.tensorflow.org/)
*.cfg (Darknet, https://pjreddie.com/darknet/)
*.xml (DLDT, https://software.intel.com/openvino-toolkit)

可见不支持pytorch的*.pth和keras等的*.h5

cv.dnn 的其它加载模型的方法有：

• readNetFromCaffe()
• readNetFromDarknet()
• readNetFromModelOptimizer()
• readNetFromONNX()
• readNetFromTensorflow()
• readNetFromTorch()

支持的文件格式同readNet()中相应的模型