/Fake-Anime-using-DCGAN-Pytorch

Implementing DCGAN for generating anime faces. The goal is to train a very simple model architectures, which produces highly realistic results. My generator is extremely simple, yet is actually able to produce surprisingly good results when trained enough. With image interpolation, this is clearly visible that the generator is not cheating/memorising the faces from the dataset.

Primary LanguageJupyter Notebook

Stargazers