Open zhangshun97 opened 6 years ago
I was trying to train a DCGAN based model with WGAN and WGAN-GP improvements. However, when I print out the gradient penalty item, it seems that it will first decrease to zero and then increase to infinity. How could that happen ?
I was trying to train a DCGAN based model with WGAN and WGAN-GP improvements. However, when I print out the gradient penalty item, it seems that it will first decrease to zero and then increase to infinity. How could that happen ?