Softmax == Softmax2D in current Pytorch version?


(Ywu36) #1

Just curious whether the softmax in a Fully Convolutional Network equals to Softmax2D ? As in the source code it seems to be true. But the current version of Pytorch document does not mention anything about 2D softmax.

http://pytorch.org/docs/master/_modules/torch/nn/modules/activation.html#Softmax


#2

i think it is just missing in documentation.


(Ywu36) #3

Agreed. Adding this to the document will reduce ambiguities.


#4

added in now. sorry for the delay.