查询: WGAN-GP FID 分数 (PyTorch)

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), and the samples look closer to 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 understand the high values of 100+ (the best value is 113.4). Others have reported lower FID Scores. The authors in Quality Aware Generative Adversarial Networks compared the various FID scores for various GAN models, and Ishaan Gulrajani's official implementation of WGAN-GP got a FID score of 12.89.