Training on custom data does not balance out

[mehdiosa]

Hello,

thanks for this repo and all of the implementations. I have been trying to get the Implementation to work on some custom data, however, the loss curves always indicate that something is going wrong. The data I am training on is 256 x 256 and when training on it the discriminator keeps going to values very close to 0 and eventually either goes to zero or comes back for a few training steps and then repeats the same procedure.

Do you have any tips or suggestions on which parameters to change so the training runs more stable with a custom dataset?

Thanks

[mingukkang]

Some useful tips for GAN training:

1. apply weight decay (1e-5)
2. use differentiable augmentations
3. remove attention layers
4. use smaller batch size for training.

Luck luck:)