Open theotheo opened 2 years ago
I think it should be doable. But you may need to carefully tune different parameters to stabilize the GAN training . If the dataset has complex background (like IMGUR5K) then you may require some other form of supervision to handle the forground and background seperately. In any case, I think you can possibly extend HWT to generate color images.
Hello!
I need to generate color images for my project. I want to try changing your architecture accordingly. I guess this should be easy to do. It is enough to change the number of channels at input and output, right? I'm wondering what you think of this possibility. Any thoughts welcome!