Hi,
When I use nn.BCELoss()
for the criterion, I have the assertion error:
anaconda3/lib/python3.6/site-packages/torch/nn/_functions/thnn/loss.py in forward(self, input, target)
20
21 def forward(self, input, target):
---> 22 assert input.nelement() == target.nelement()
23 self._resize_weight(target)
24 result = super(BCELoss, self).forward(input, target)
But when I change the loss into nn.CrossEntropy()
, it is OK to run.
What is the problem here?