In the 4th jupyter file named Word Window Classification and Neural Networks, I found something wrong. Specifically, in the class WindowClassifier, you has used self.softmax = nn.LogSoftmax(dim=1)in the output layer, then you don't need use CrossEntropyLoss() loss, you must use torch.nn.NLLLoss loss
In the 4th jupyter file named
Word Window Classification and Neural Networks, I found something wrong. Specifically, in the classWindowClassifier, you has usedself.softmax = nn.LogSoftmax(dim=1)in the output layer, then you don't need useCrossEntropyLoss()loss, you must usetorch.nn.NLLLossloss