CycleGAN-TensorFlow
CycleGAN-TensorFlow copied to clipboard
identity mapping loss
Hi, thank you for sharing this implementation. do you plan on adding support for the identity mapping loss as described in the original paper? thanks
Yes, I will add identity mapping loss soon. But before that, I have to fix #18. Anyway, pull requests are always welcome! 😉
Have you added the identity mapping loss yet? Besides, I found the training is slow. Do you have any idea to facilitate the training? What do you think of using WGAN-GP instead of LSGAN?
@vanhuyz Good luck
@lizhuorong CycleWGAN should be a more robust method
i want to change the loss function by pixel wise loss , how i can do that please