# martinarjovsky/WassersteinGAN

Repository: https://github.com/martinarjovsky/WassersteinGAN
Canonical: https://ross.abutalabs.com/products/wassersteingan
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2018-12-26T16:46:00+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": 3502, "days_push": 2807, "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 3243, forks 722 (observed 2026-08-28T04:07:50.575082+00:00)

## What it is
Reference PyTorch implementation of the Wasserstein GAN paper, providing training scripts for DCGAN and MLP architectures on datasets like LSUN. It is research code accompanying the arXiv paper rather than a reusable library.

## Use cases
- reproduce Wasserstein GAN experiments from the paper
- train a WGAN on the LSUN dataset
- compare Wasserstein loss curves with DCGAN baselines
- learn how to implement WGAN critic and generator training in PyTorch
- study improved GAN training stability techniques

## When to choose
- you want the official reference code for the Wasserstein GAN paper
- you need to reproduce the paper's LSUN experiments exactly
- you are studying WGAN training dynamics and loss behavior

## When to avoid
- you need a maintained, production-ready GAN library
- you want a flexible framework for many generative model types
- you need Windows support or extensive documentation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: gan, wasserstein-gan, pytorch, research-code, generative-models, paper-reproduction, linux, macos, gpu

## Member repositories
- martinarjovsky/WassersteinGAN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:50.575082+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 2026-08-30T07:24:30.156521+00:00, confidence not recorded.
  - readme: https://github.com/martinarjovsky/WassersteinGAN (fetched 2026-08-28T04:07:50.575082+00:00, sha bad6c15b9622)
- Data as of 2026-08-30T08:39:29.467469+00:00.