# caogang/wgan-gp

A pytorch implementation of Paper "Improved Training of Wasserstein GANs"

Repository: https://github.com/caogang/wgan-gp
Canonical: https://ross.abutalabs.com/products/wgan-gp
Language: Python
License: MIT
License Family: permissive
Topics: wgan-gp, pytorch
Last push: 2023-07-18T07:54:22+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3408, "days_push": 1142, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1547, forks 345 (observed 2026-08-28T04:05:01.718252+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: wgan-gp, gan, pytorch, generative-models, research-code, gpu

## Member repositories
- caogang/wgan-gp (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:01.718252+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:28.551788+00:00, confidence not recorded.
  - readme: https://github.com/caogang/wgan-gp (fetched 2026-08-28T04:05:01.718252+00:00, sha beffc4af15c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.