This repository encompasses a comprehensive research of Generative Adversarial Networks (GANs) for Biomaterial Discovery. Our research delves into the generation of intricate biomaterial topographies through the innovative application of AI/ML techniques. Discover our findings, code implementations and datasets in this repository!

Implementations of different Generative Adversarial Networks

These tutorials are for beginners who need to understand deep generative models.

Image generation using Vanilla GAN (General Adversarial Network)

Vanilla GAN implementation on MNIST dataset using PyTorch

Vanilla GAN implementation with PyTorch

Simulate experiments with the Vanilla GAN architecture and training algorithm in PyTorch using this package.

Synthetic Data Generation (SDG) Using Vanilla GAN

Standard Deep Learning Models implemented in pytorch framework

TensorFlow Generative Adversarial Networks (GANs)

Speech-Recognition STT Project

Implement multiple gan including vanilla_gan, dcgan, cgan, infogan and wgan with tensorflow and dataset including mnist.

PyTorch implementation of Vanilla GAN

Generative Adversarial Networks in TensorFlow 2.0

My implementation of various GAN (generative adversarial networks) architectures like vanilla GAN (Goodfellow et al.), cGAN (Mirza et al.), DCGAN (Radford et al.), etc.

Simple Implementation of many GAN models with PyTorch.