Re:Pokemon GAN
by flor1s on Monday February 14, 2022 @06:29PM
(#30340029)
Traditional GANs typically have a different problem called mode collapse, in which the generator learns one (or a few) outputs that the discriminator likes. Conditional GANs are given a condition as input and have more chance of overfitting, as the loss function is a combination of the GAN output and a supervised loss based on the condition.
[ Parent
| on HN ]
There are no comments on this comment yet.