so most examples I've seen create two NN-s, train them, then they stack them, make the discriminator part untrainable and then train this stacked NN, why do we do this? So loss, that is calculated on the discriminator end, recalibrates the weights of a generator part? So after we train a discriminitor a little bit, we only pass the fake images generator generates? Premise was that they both train at the same time, wasn't it?

  • $\begingroup$ Could you expand your post? What is GAN (is it Generative adversarial network?, if so please include it) and split your sentences into shorter ones? The title should be more about your question not just general topic it touches. $\endgroup$ – Evil May 11 '19 at 12:42

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.