Overview / Usage

Generative adversarial networks (GANs) are a class of artificial intelligence algorithms used in unsupervised machine learning, implemented by a system of two neural networks contesting with each other in a zero-sum game framework.
There are many architectures that have been worked upon. Currently I am working on different architectures of GANs to bring that in more domains. Some architectures include Conditional GANs (pix2pix), CycleGANs,Wasserstein GANs

Methodology / Approach

This project demonstrates different architectures of GANs.

Technologies Used

Tensorflow, Pytorch, DevCloud

Repository

https://github.com/prajjwal1/gans

Other links

• Better Generative modelling with Wasserstein GANs (Intel Developer Zone)