WassersteinGAN
GAN generator
Implementing a Wasserstein GAN to generate high-quality samples with improved model stability and reproducibility of LSUN experiments.
3k stars
104 watching
725 forks
Language: Python
last commit: about 6 years ago Related projects:
Repository | Description | Stars |
---|---|---|
| A collection of strategies and techniques to improve the stability and performance of Generative Adversarial Networks (GANs) for generating high-quality images. | 11,473 |
| A training methodology for generative adversarial networks to improve quality and stability | 6,110 |
| An official PyTorch implementation of the StyleGAN2-ADA algorithm for generating images with a focus on stability and performance. | 4,144 |
| A dataset designed to replace the MNIST dataset for benchmarking machine learning algorithms, offering a more challenging and representative set of images for computer vision tasks. | 12,022 |
| Improves the performance of Generative Adversarial Networks by normalizing weights and batch data | 181 |
| A collection of software frameworks and implementations for training generative models using GANs, VAEs, RBMs, and other techniques. | 7,351 |
| An empirical evaluation of generic convolutional and recurrent networks for sequence modeling | 4,204 |
| Improves GAN training efficiency by incorporating data augmentation | 1,286 |
| An implementation of the Graph Attention Network model using PyTorch. | 2,935 |
| A collection of PyTorch implementations of Generative Adversarial Networks for image synthesis and other applications. | 16,570 |
| Implementations of various deep learning algorithms and techniques with accompanying documentation | 57,177 |
| An open-source project that investigates the stability of Generative Adversarial Networks (GANs) and provides experiments to evaluate their convergence. | 918 |
| An implementation of DALL-E 2's text-to-image synthesis neural network in PyTorch | 11,184 |
| This project is a software implementation of a diffusion model architecture, allowing users to generate synthetic images based on a learned distribution. | 6,366 |
| An unofficial implementation of PyTorch BigGANs for generating high-fidelity natural images | 2,874 |