Questions about your code

[gymoon10]

Hi, I'm Goo-Young Moon, a master's degree student at Korea University. I read your paper interestingly while investigating the research on synthetic data generation with GAN. But, I opened the issue as I had some questions while I was looking at the code you uploaded.

1. In the dcgan_ej.py and wgan-gp.py, unlike the contents of the paper, it seems that only general dcgan & wgan-gp losses are used without the process of style transfer. If style transfer is taking place, I would appreciate it if you could tell me which part of the code it is.

2. According to the 3.1 ch of paper, two types of images are mentioned: content & style. But in the 4.3 ch it seems like that only style images are given as input. Can you explain in detail what kind of images are used as input when the dataloader loads imgs.

Thank you for your research and hard work.