The input image is normalized between 0-1, so the output should be a nn.Sigmoid() layer instead of nn.Tanh(). Note that nn.Tanh() may also work, but using nn.Sigmoid() is more appropriate and will make the learning easier since the network can now only output values between 0-1 every pixel.
The input image is normalized between 0-1, so the output should be a nn.Sigmoid() layer instead of nn.Tanh(). Note that nn.Tanh() may also work, but using nn.Sigmoid() is more appropriate and will make the learning easier since the network can now only output values between 0-1 every pixel.