News for hackers. Stuff that matters.
Re:Progressive Growing of GANs for Improved Quality, Stabili... by argonaut on Saturday October 28, 2017 @07:34PM (#15577243)
The critic idea seems interesting but doesn't really get to the question of whether/to what degree the GAN is just interpolating the training data. It seems more of a useful tool for diagnosing GANs.
Re:Progressive Growing of GANs for Improved Quality, Stabili... by ericjang on Sunday October 29, 2017 @12:59AM (#15578018)
If it were memorizing training data, it would due poorly on a Wasserstein critic trained on a validation set drawn from the same data distribution.