Open ir1979 opened 5 years ago
The normalize-operation in the transform expects 3 channels. For a gray-scale image with 1 channel change
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
to
transforms.Normalize((0.5,), (0.5,))
Lol,the Conv_autoencoder python code is way too too simply and way toto crude
Your file produces Error: RuntimeError: output with shape [1, 28, 28] doesn't match the broadcast shape [3, 28, 28]
It probably due to the gray-scale image downloaded automatically.