RuntimeError: expected scalar type Long but found Float. - test

[Matias_Vasquez]

Maybe this old question can help you. It seems you have a similar problem, due to CrossEntropyLoss

RuntimeError: multi-target not supported (newbie)

CrossEntropyLoss does not expect a one-hot encoded vector as the target, but class indices: The input is expected to contain scores for each class. input has to be a 2D Tensor of size (minibatch, C). This criterion expects a class index (0 to C-1) as the target for each value of a 1D tensor of size minibatch