Generative adversarial networks (GAN) are a class of generative machine learning frameworks. A GAN consists of two competing neural networks, often termed the Discriminator network and the Generator network. GANs have been shown to be powerful generative models and are able to successfully generate new data given a large enough training dataset.
Using Generative Adversarial Networks to generate bird photos.
This repository contains a Convolutional GAN which generates faces based on the CelebFaces dataset.
The code for "Text-to-image synthesis with self-supervised bi-stage generative adversarial network"
This is a repository that contains an implementation of Wassertein-GAN (Generative Adversarial Network) using the PyTorch framework for generating batik patterns.
[2022/23] A study of Generative Adversarial Networks, including experiments using anime faces dataset.
GAN trained to produce hand gesture images.
Implementation of Generative Adversarial Networks paper plus training on tiny problems.
Basic implementation of Generative Adversarial Neural Network and its types
The goal is to create new faces of anime characters using a Deep Convolutional Generative Adversarial Network (DCGAN).
Using VAEs and GANs to understand how to generate images, over the CelebA dataset
GAN and VAE on MNIST and Face
Generative adversarial networks (GANs) are a powerful type of machine learning model that can be used to generate new, synthetic data that is similar to a training datasets. They consist of two networks: a generator network and a discriminator network. The generator network is responsible for generating new data, while the discriminator network is
Implement GAN (Generative Adversarial Network) on MNIST dataset. Vary the hyperparameters and analyze the corresponding results.
This project uses Generative Adversarial Networks (GANs) to generate synthetic electrocardiogram (ECG) data from a dataset of 5000 ECGs obtained from PhysioNet. The generated data includes both normal and abnormal ECG patterns, providing a valuable resource for research and development of machine learning models
generating synthetic images to enhance Optical Character Recognition (OCR) systems
Simple DCGAN implementation
Generative Adversarial Network that creates images of handwritten numeral digits or faces
Experiments that accompany a paper in which Transfer-Learning applied to GAN is examined
Released June 10, 2014