Hi Ralmohsen,
When i run train_AAE.py, without change original source code, there have a isse like this:

Running on GeForce RTX 2080 Ti Train set size: 33800 /home/jason/.local/lib/python3.6/site-packages/torch/nn/functional.py:1386: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead. warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.") /home/jason/.local/lib/python3.6/site-packages/torch/nn/modules/loss.py:512: UserWarning: Using a target size (torch.Size([128])) that is different to the input size (torch.Size([98])) is deprecated. Please ensure they have the same size. return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction) Traceback (most recent call last): File "train_AAE.py", line 324, in <module> main(0, 0) File "train_AAE.py", line 211, in main D_real_loss = BCE_loss(D_result, y_real_) File "/home/jason/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__ result = self.forward(*input, **kwargs) File "/home/jason/.local/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 512, in forward return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction) File "/home/jason/.local/lib/python3.6/site-packages/torch/nn/functional.py", line 2106, in binary_cross_entropy "!= input nelement ({})".format(target.numel(), input.numel())) ValueError: Target and input must have the same number of elements. target nelement (128) != input nelement (98)
How i can fix it?

hi all and @podgorskiy @Ralmohsen

While using the Cifar 10 or Cifar100 dataset, are there any changes to be made in the arguments or in any other parts of the code?