5,323
edits
No edit summary |
|||
Line 16: | Line 16: | ||
[https://arxiv.org/pdf/1704.00028.pdf Paper]<br> | [https://arxiv.org/pdf/1704.00028.pdf Paper]<br> | ||
[https://medium.com/@jonathan_hui/gan-wasserstein-gan-wgan-gp-6a1a2aa1b490 Medium post]<br> | [https://medium.com/@jonathan_hui/gan-wasserstein-gan-wgan-gp-6a1a2aa1b490 Medium post]<br> | ||
This new WGAN-GP loss function improves the stability of training. | This new WGAN-GP loss function improves the stability of training.<br> | ||
Normally, the discriminator is trained with a cross-entropy with sigmoid loss function.<br> | |||
The WGAN proposes using Wasserstein distance which is implemented by removing the cross-entropy+sigmoid | |||
and clipping (clamp) the weights on the discriminator to a range <math>[-c, c]</math>.<br> | |||
However, weight clipping leads to other issues which limit the critic.<br> | |||
Instead of clipping, WGAN-GP proposes gradient penalty to enforce 1-Lipschitz . | |||
==Applications== | ==Applications== |