I am training a GAN in which I am optimizing or reducing the loss of the generator and the discriminator simultaneously. However, the images generated are very noisy. What could be the hidden reason? Why the simultaneous optimization of the loss functions does not ensure good images in GAN?

  • $\begingroup$ This question does not appear to be about theoretical computer science. You should consider asking this question in a forum focused on machine learning (or even GANs particularly). $\endgroup$
    – SamM
    Oct 9 at 3:07


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.