![]() What am I doing wrong? How can I fix this? Any help on this will be helpful. RuntimeError: Error(s) in loading state_dict for DataParallel: > 1224 self._class_._name_, "\n\t".join(error_msgs)))ġ225 return _IncompatibleKeys(missing_keys, unexpected_keys) Optimizer = (model.parameters(), lr=learning_rate) In_channels=3, # model input channels (1 for gray-scale images, 3 for RGB, etc.)Ĭlasses=2, # model output channels (number of classes in your dataset) ![]() mobilenet_v2 or efficientnet-b7Įncoder_weights='imagenet', # use `imagenet` pre-trained weights for encoder initialization But I notice that if I stop it I have to start over from the beginning again. To achieve this I've written a script like belowĮncoder_name="resnet152", # choose encoder, e.g. I'm trying to save checkpoint weights of the trained model after a certain number of epochs and continue to train from that last checkpoint to another number of epochs using PyTorch
0 Comments
Leave a Reply. |