DCGAN-tensorflow
DCGAN-tensorflow copied to clipboard
Training good till epoch 20 then goes horribly bad...
I had these settings CelebA 265 input 128 output 25 epochs --crop --train and everything was going fine till epoch 20 then things got very badly? Anybody an idea what's happening and if I can redo it from epoch 19?? Waste of amazon EC2 GPU time and money otherwise?
What are the epochs for each of these pictures? The 3rd one looks like a very early epoch.
I believe that the mode collapse may be caused by updating the generator twice for every one update of the discriminator. Reverting to 1 to 1 training can solve this from my experience.