Hangyan Zhu

> There are some differences between the cleaned code and the original code indeed. But I do think that it would be better rather than worse. > Sorry for that...

> @HyZhu39 Hello, how you get the FID between images generated by 5 style codes and the real images? > The generated images for 5 style codes should be put...

> You're welcomed. Since there are same identities in one folder, the FID (which uses the variance of the image features) would definitely become bigger. Sorry for bothering again. I...

> Actually, you need to randomly sample the reference images for each source image. If you sample only one reference image to translate all the source images into 'with_bangs', the...

Sorry for mistakes I made and my misunderstanding of your experiment settings, I think I understand your experiment settings actually now. I randomly sample the reference images for each source...

Many thanks for your help. I have packed some qualitative experiment results and the images of my quantitative experiment (if you needed) in the following Baidu Yun link. Thank you...

> The qualitative results seem to be promising. > I calculate FID using StarGANv2's script. > I check the difference between [StarGANv2's](https://github.com/clovaai/stargan-v2/blob/master/metrics/fid.py) and [pytorch-FID](https://github.com/mseitzer/pytorch-fid/blob/master/src/pytorch_fid/fid_score.py) and find that these is a...

Thank you for your help again. It's your selfless help that I can successfully reproduce your experiment results. We communicate in English here for the convenience of other people’s references....