search

junyanz / pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch
Other
23.12k stars 6.32k forks source link

Hint for network flexibility #793

Open shinigami1992 opened 5 years ago

shinigami1992 commented 5 years ago

Hi, thanks for your great work.

I'm trying to apply cyclegan on my own custom anime dataset to learn facial expression transfer. My dataset includes 2000 sad and 2000 happy images.

I run the training process for about 100k iterations.

The problem is that I only see some small changes specially in mouth part. Do you have any suggestion? How can I make network more flexible for changing different parts of faces?

Some sample results

392-images 385-images 365-images

junyanz commented 5 years ago

I recommend that you use a smaller lambda for cycle consistency loss, remove identity loss, or increase the receptive field of the discriminator. You can also experiment with a bigger generator.