Open 0xtristan opened 4 years ago
In the styleGAN 2 paper they state using a "non-saturating logistic loss", is there any particular reason you opted for hinge loss in this implementation?
For reference I believe the original loss functions for config-f are G_logistic_ns_pathreg for the generator and D_logistic_r1 for the discriminator (https://github.com/NVlabs/stylegan2/blob/master/training/loss.py).
G_logistic_ns_pathreg
D_logistic_r1
In the styleGAN 2 paper they state using a "non-saturating logistic loss", is there any particular reason you opted for hinge loss in this implementation?
For reference I believe the original loss functions for config-f are
G_logistic_ns_pathregfor the generator andD_logistic_r1for the discriminator (https://github.com/NVlabs/stylegan2/blob/master/training/loss.py).