Generative Adversarial Networks

  • Introduction to Generative Adversarial Networks, Section, Harvard University, 2019. Slides. Prepared by Vincent Casser.

Abstract
We describe a minimalistic implementation of Generative Adversarial Networks (GANs) in Keras. We train a simple GAN for the task of face synthesis on the CelebA dataset. The goal of this is to enhance understanding of the concepts, and to give an easy to understand hands-on example. It is recommended to take a look at the accompanying lecture slides.
Open in Full Screen