Query: WGAN-GP FID SCORE (PyTorch)

[KomputerMaster64]

Thank you for sharing the implementations of the GAN based models on popular datasets like CelebA.
I have implemented the WGAN-GP model (in PyTorch), the samples are looking closer the reported work (please refer to the attached image). When I try to evaluate the Fréchet inception distance (FID score), I am not able to comprehend the high values of 100+ (best value 113.4). Others have reported lower FID Scores. Authors in the Quality Aware Generative Adversarial Networks compared the vairous FID scores for various GAN models and there Ishaan Gulrajani's official implementation of WGAN-GP got FID score of 12.89.

I request you to guide me.
Regards
Prabhav

I have used the following repositories for reference while implementing the WGAN-GP model and evaluating the FID scores:
LynnHo/DCGAN-LSGAN-WGAN-GP-DRAGAN-Pytorch
CharlesNord/WGAN-GP-DRAGAN-Celeba-Pytorch
eriklindernoren/PyTorch-GAN
hukkelas/pytorch-frechet-inception-distance
mseitzer/pytorch-fid

[APushingBoy]

Hello, I'm using the code here to train WGAN-GP on cifar10, but I keep getting blurry images. Since you have tried to train the model on CelebA, which is also a more complex dataset than MNIST, have you ever tried on cifar10? Sorry that my comment is not helping you with your problem, but can you share your hyperparameters with me when you do experiments on CelebA?

[baicaiPCX]

您好，您的邮件小皮已经收到啦！！！