From scratch, simple and easy-to-understand Pytorch implementation of various generative adversarial network (GAN): GAN, DCGAN, Conditional GAN (cGAN), WGAN, WGAN-GP, CycleGAN, LSGAN, and StarGAN.

ProGAN with Standard, WGAN, WGAN-GP, LSGAN, BEGAN, DRAGAN, Conditional GAN, InfoGAN, and Auxiliary Classifier GAN training methods

Exploring methods for synthetic data generation for time series, tabular and image data.

Block-by-block implementation from scratch of CNNs and GANs using PyTorch, with language models to be added later.

This code is for classifying spectrogram images of Motor Movement/Imagery tasks using a CNN and WGAN.

Wasserstein GAN (WGAN) is a variant of the traditional Generative Adversarial Network (GAN) that aims to improve training stability and address issues like mode collapse.

Code for our paper "Generative Adversarial Network with Soft-Dynamic Time Warping and Parallel Reconstruction for Energy Time Series Anomaly Detection" and its extension.

Creating Anime Faces using Generative Adversarial Networks (GAN) techniques such as: DCGAN, WGAN, StyleGAN, StyleGAN2 and StyleGAN3. Top repos on GitHub for AnimeFace GAN Generative AI Models

Learning GANs: WGAN, Relativistic GAN, StyleGAN, pix2pix...

wg899 openwrt

This project trains a WGAN on the MNIST dataset to generate images of handwritten digits.

Implementations of GANs

My own GAN implementation (WGAN-GP with Pytorch)

Maze generation using VAE and GAN

머신러닝 프레임워크를 활용한 비교사(Unsupervised) 학습 모델 구현 프로젝트

Keras implementations of Generative Adversarial Networks. GANs, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.

Application of Wasserstein Generative Adversarial Networks on Fashion MNIST using PyTorch

WGAN Image generator using custom eulers rotations for activations and multi kernel concatenations.