Surya comments

Repositories
Issues
Comments

Results 1 comments of


                                            Surya

L1 loss problem with GAN if some data has ground-truth and some not

Hi @HymEric Maybe you could try using an external function such that g(ground-truth) --> generated, before using L1 loss, as mentioned in https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/293#issuecomment-397740979