The code to use the pre-trained model is as follows:
# Load pre-trained models resNet50 = models.resnet50(pretrained=True) ResNet50 = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=2) # Read the parameters pretrained_dict = resNet50.state_dict() model_dict = ResNet50.state_dict() # Strike out keys in pretained_dict that don't belong in model_dict pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict} # Update existing model_dict model_dict.update(pretrained_dict) # Load the state_dict that's really needed ResNet50.load_state_dict(model_dict)
This PyTorch loading pre-trained model example (pretrained) above is all I have to share with you, I hope it can give you a reference, and I hope you can support me more.