Open YunLord opened 5 years ago
loss_D_real = criterion_GAN(pred_real, torch.ones_like(pred_real));i think this should be loss_D_real = criterion_GAN(pred_real, torch.zeros_like(pred_real))
Not sure why you think that. At least that is the usual way to train GANs, check out https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html