Hi,
I am confused while reading documentation of CrossEntropyLoss. Does n and nClasses are the same thing? If not, what is n?
“It is useful when training a classification problem with n classes”
…
“input has to be a 2D Tensor of size batch x n.
This criterion expects a class index (0 to nClasses-1) as the target for each value of a 1D tensor of size n”