I'm very new to AI and deep learning. So my question is going to be very basic.
I'm trying to understand which approach I would need to use to cross-breed set of images. Let's say I'm having dataset of cats and dataset of human faces and as output I want to get images that would look like cat-humans.
I tried to use DCGAN network, this in particular: https://github.com/pytorch/examples/tree/main/dcgan. But as output I'm getting an image that is baed only on one of the datasets (either human or cat, not anything that would look like cross-breed).
I suppose, I completely misunderstand the concept of DCGAN, or perhaps I just need to tweak the network to achieve desired results?
Anyway, I'm kinda lost here and just asking for directions. Perhaps there's better network architecture for this purpose or some specific set up needed.
