Hao
Hao
In my experience, when d loss decrease to a small value (0.1 to 0.2) and g loss increase to a high value (2 to 3), it means the training finish...
Hi, could you show your result?
To rotate an image, you need to set the values in the transformation matrix, see https://en.wikipedia.org/wiki/Affine_transformation
I got the same problem, it seems this code is not useful ..
this project just does not work