VITA-Group / TransGAN

[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

question about argumentation

siru-zhang opened this issue · comments

I am wondering why there is no parameter to control the probability of argumentation. Does this mean that the discriminator has not seen the real data (non-argumented image)?

The probability of augmentation is hard-coded. But discriminator still has a chance to see non-augmented data, even it is very low.