How the dim parameter of the Softmax() is reflected in CrossEntropyLoss()

1

Hello,

I am new to PyTorch, and I encountered a quesiton about Softmax() and CrossEntropyLoss().

In a multi-classification task, I set dim=1 in Softmax(). I wanna know if I need to set the similar parameter in CrossEntropyLoss(). However, I did not find the similar parameter as dim in softmax(). And how the dim parameter of the Softmax() is reflected in CrossEntropyLoss()?

Thanks!

2

One of my guesses is that “dim” is set to a default value. For example, the default value is 1.

3

nn.CrossEntropyLoss expects the class dimension in dim1 as explained here.