Why don't Generator rescale the generated output before sending it into the Discriminator in DCGAN tutorial?

12 Views Asked by At

I have a question about the DCGAN tutorial

I was wondering why the Generator do not rescale the generated output to range [0,1] before sending it into the Discriminator during the training process?

I thought that if the Generator model did not rescale the generated output, the Discriminator can easily learn the input images that did not include the value in range [0,1] as the fake image.

0

There are 0 best solutions below