Why do the Generator not use the real images in train.py

[kinglon]

I looked through the train.py, and didn't find the Generator use the real image. I doubt if the Generator load a pre-train model that have learned from a lot of real images. Now, I want to use sofgan to generate an anime photo, can I achieve it after a model train only using the real anime pictures and its segmaps.

[apchenstu]

sorry, I could not catch the question, could you ask it in another way?

[kinglon]

I have learnt the answer from this article. The Discriminator learns features from real image, then tell the Generator those features. The Generator uses those features to generate fake images.