Open Rubiel1 opened 4 years ago
Great. Does it help in your experiments? Maybe @zsyzzsoft can help create a PR or a branch for all the models. We are doing some experiments with conditional GANs and standard datasets, and considering adding them to arXiv v2.
I was missing one line, so I updated my original comment. I found that this helps to prevent the discriminator to overfit. But I was missing one line so I have to repeat the experiments.
There is a new paper on differentiable data augmentation for GANS: https://arxiv.org/pdf/2006.10738.pdf, it seems promising.
I have implemented it on pix2pix. For any one interested, I added:
the file to the folder utils.
parser.add_argument('--dif_data_augm', type=str, default='', help='differential data augmentation currenly only for pix2pix models. [color | translation | cutout | color,cutout|...|color,translation,cutout]')
here ,from util.DiffAugment_pytorch import DiffAugment
here`
specify the smooth data augmentation, default is none, options include translation, change on color and random cutout
here
`
smooth data aumentation policy
here
I replaced this by
` fake_AB = DiffAugment(fake_AB.detach(), policy=policy) # by default we don't modify the data
Also this by ` policy = self.dif_data_augm
and this by
`
real_AB = DiffAugment(real_AB, policy=policy)