Two time-scale update rule for training GANs
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
czzyyy opened this issue 5 years ago · comments
Why is the FID score calculated using the CelebA real image 64*64 always around 27? It should be less than 5. . .The images I used are images cropped with list_bbox_celeba.txt for a total of 50,000.