Skip to content
This repository has been archived by the owner on Mar 8, 2023. It is now read-only.

Latest commit

 

History

History
22 lines (16 loc) · 1.02 KB

README.md

File metadata and controls

22 lines (16 loc) · 1.02 KB
Raw

Generative Adversarial Networks

The aim of the project was to learn about Generative Adversarial Networks and explore the various types of GAN objectives and architectures. We also studied the problem of Multi-Domain image to image translation, and implemented StarGAN to perform the same on the celebA dataset.

Structure

  • learning-phase contains the models implemented during the learning phase of the project. This includes:
    • Convolutional Neural Network for classification of MNIST dataset.
    • Vanilla GAN
    • DCGAN
  • archived contains a Tensorflow implementation of StarGAN that was archived due to the issues with the data loader.
  • StarGAN contains a Tensorflow implementation of StarGAN for multi-domain image to image translation on the celebA dataset.

Requirements

  • Tensorflow

Team

  • Moksh Jain
  • Mahim Agrawal
  • Mahir Jain
  • Palak Singhal