cycleGAN-PyTorch icon indicating copy to clipboard operation
cycleGAN-PyTorch copied to clipboard
verified publisher icon arnab39

About setting grad to false in train iteration.

Open Michi-123 opened this issue 5 years ago • 0 comments

In training, discriminator gradient is set to false while generator is updating. But I tried with no discriminator lock, and it it seems the result was same. I wonder the lock code needs in PyTorch?

Michi-123 avatar Jul 07 '20 23:07 Michi-123