DualGAN
DualGAN copied to clipboard
convergence of training process
In the DualGAN paper shows Algorithm 1 DualGAN training procedure. It says stop training until convergence. Do you have any idea what exactly it means? Does it means A_d_loss and B_d_loss update to 0.5 Simultaneously?Many thanks.
No, convergence means the image quality reaches satisfactory. Practically, you need to specify the args.epoch manually by observing the image quality.