Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I'm just starting out in ML and I am interested in a model that can swap similar things in images, like doors or items on a desk. Is it possible to take a library like https://github.com/deepfakes/faceswap which is meant to swap faces and train it to swap other things?
When I search for 'swapping' models, face-swapping is pretty much all I get, which isn't what I want.
The technology behind faceswaps using two autoencoders should also work for things instead of persons. The logic behind it stays the same, would just need enough training data.
