/relativistic-discriminator

A pytorch implementation of "The relativistic discriminator: a key element missing from standard GAN"

Primary LanguageJupyter NotebookMIT LicenseMIT

The Relativistic Discriminator: A Key Element Missing from Standard GAN

Alexia Jolicoeur-Martineau (Lady Davis Institute, Université de Montréal)

ICLR 2019



CAT 64x64

Images of cat faces generated by a RaLSGAN trained on the CAT dataset.



This folder provides a re-implementation of this paper in PyTorch, developed as part of the course METU CENG 796 - Deep Generative Models. The re-implementation is provided by:

Please see the jupyter notebook file main.ipynb for a summary of the paper, the implementation notes and our experimental results.

The viewer must use nbviewer when viewing the notebook as it will not load correctly otherwise.