This repository contains different GAN architectures for data generation and posterior sampling to solve inverse problems featured in my Master's Thesis.

Implementation of some types of GANs (Deep convolutional GAN - Wasserstein GAN - conditional GAN) with PyTorch library

This repository contains some code for demonstrating the application of Wasserstein GANs (WGANs)

Project to get attention from discriminator: 1st combination

WGAN-GP Implementation of Pokémon Image Dataset

Keras implementation of Deep Learning Models applied to the MNIST and Polynomial datasets. Repository for the Software and Computing for Nuclear and Subnuclear Physics Project.

Master's Thesis Project: Text generation with GANs and Autoencoders

Using DCGAN to generate abstract art

All GAN models in Keras

Progressive Growing of GANS

TensorFlow implementation of Wasserstein GAN (WGAN) with MNIST dataset.

This project implements the Wasserstein-GAN approach to estimate Wasserstein distances and benchmarks it against other approaches.

Inpainting on MSCOCO

Sampling from the solution of the Zakai equation, using the Signature and Conditional Wasserstein GANs

WGAN with feedback from discriminator& LayerNorm instead of BatchNorm

PyTorch implementation of WGAN-GP-based video generation. Includes functionality for measuring Frechet Video Distance and implementing recent research improvements of WGAN-GP. Read paper at https://github.com/talcron/frame-prediction-pytorch/blob/media/paper.pdf

A Wasserstein Generative Adversarial Network that learns the distribution of a Mixture of Gaussian, using weight clipping or spectral normalization

A generative adversarial network engineered that utilizes a discriminator and a generator. The GAN can be trained using a Binary Cross Entropy Loss or a Wasserstein Distance Loss to generate replicate images based on input data.

Implementation of WGAN to generation of Atari Games Images. (GAN, WGAN, ATARI, Generative)