vae-gan-tf2

Tensorflow 2 implementation of VEA-GAN

Objective:

Implementation of: Autoencoding beyond pixels using a learned similarity metric by Anders Boesen Lindbo Larsen and Søren Kaae Sønderby and Hugo Larochelle and Ole Winther https://arxiv.org/abs/1512.09300

Status

• Vae-gan implementation is working for 64 * 64 images from celeba dataset.

Futur objectives:

Use the GAN loss of: Wasserstein GAN by Martin Arjovsky and Soumith Chintala and Léon Bottou https://arxiv.org/abs/1701.07875