In the paper, under the discriminator section, you write that "An up-sampling layer is added to the last convolution layer for re-scaling the output to the size of the input."
What is the purpose of this upscaling? How would this affect the loss? I can also see that this upscaling is commented out - did you find out that it was unnecessary?
Sorry for the confusion. We did try to upsample the final layer, but the results were not affected. In the final implementation as released here, there is no upsampling layer.
In the paper, under the discriminator section, you write that "An up-sampling layer is added to the last convolution layer for re-scaling the output to the size of the input."
What is the purpose of this upscaling? How would this affect the loss? I can also see that this upscaling is commented out - did you find out that it was unnecessary?