caogang/wgan-gp

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1547 stars · 345 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of the 'Improved Training of Wasserstein GANs' (WGAN-GP) paper, covering toy datasets, MNIST, CIFAR-10, and character-level language modeling. It serves as reference research code for training Wasserstein GANs with gradient penalty.

Use cases

• train a wasserstein gan with gradient penalty in pytorch
• reproduce wgan-gp results on mnist or cifar-10
• learn how gradient penalty improves gan training
• generate samples on toy datasets like 8 gaussians and swiss roll
• character-level language generation with wgan-gp

When to choose

• you want a minimal, readable PyTorch reference for WGAN-GP
• you are studying or reproducing the Improved WGAN training paper
• you need a starting point for GAN experiments on small datasets

When to avoid

• you need production-ready or actively maintained GAN tooling
• you want high-resolution image generation or modern architectures
• you need a framework with extensive configuration and model zoo support

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning artificial-intelligence python wgan-gp gan pytorch generative-models research-code gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="caogang/wgan-gp")