Number of classes of domain classifier
ilteralp opened this issue · 3 comments
ilteralp commented
Hi all, I have a question. Why does the output layer of domain classifier have 2 output features (this line) ? Since the domain labels are either 0
or 1
in the paper, I think it should be a binary classifier as below,
self.domain_classifier.add_module('d_fc2', nn.Linear(100, 1))
msseibel commented
Agree. But weirdly I saw this also in many other implementations.
GZK66666 commented
The target label is a binary one-hot vector, so there are two outputs, and finally through softmax?