After a GAN is trained, which parts of it are used to generate new outputs from data?
- Both Generator and Discriminator
Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.Sign up to join this community
I think so you are new to GANs.
As the name itself implies, the generator task is to generate new images to match the distribution of the model and the input data, hence it is the generator that contributes in the generation of the data, while the discriminator just tries to differentiate between the generated images by the generator and real data.