Configuration for colored dataset

I have a dataset that has both trainA and trainB images as RGB i.e. 3 channels but I get this error whenever I try to train.

    return torch.cat([x, self.model(x)], 1)
RuntimeError: Sizes of tensors must match except in dimension 2. Got 2 and 3 (The offending index is 0)

Please guide me on how to configure the train options for training for such a dataset. Thank you.
