# GAN implementations collection

PyTorch implementations of Generative Adversarial Networks.

Repository: https://github.com/eriklindernoren/PyTorch-GAN
Canonical: https://ross.abutalabs.com/products/gan-implementations-collection
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-18T07:08:31+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": 3056, "days_push": 806, "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 17446, forks 4063 (observed 2026-08-28T04:11:19.677304+00:00)

## What it is
A collection of clean PyTorch (and companion Keras) implementations of dozens of Generative Adversarial Network variants from research papers, such as CycleGAN, Pix2Pix, WGAN-GP, and InfoGAN. Each implementation focuses on the core ideas of the paper rather than exact architecture reproduction, making it a reference for learning and experimentation.

## Use cases
- learn how GAN architectures work with readable pytorch code
- find a reference implementation of cyclegan or pix2pix
- compare different gan variants like wgan-gp and infogan
- get a starting point for implementing a generative adversarial network
- study gan paper implementations for a course or research project

## When to choose
- you want simple, readable implementations of many GAN variants in one place
- you are learning generative models and want paper-to-code references
- you need a baseline implementation to modify for your own experiments

## When to avoid
- you need a production-ready, actively maintained GAN training framework
- you require exact reproductions of paper architectures or state-of-the-art results
- you need timely bug fixes or support for the latest PyTorch versions

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing, tutorials
- platform: python, cross-platform
- tags: gan, pytorch, keras, generative-models, reference-implementations, research-papers

## Member repositories
- eriklindernoren/PyTorch-GAN (main) score 32
- eriklindernoren/Keras-GAN (mirror) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:19.677304+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 2026-08-29T17:02:57.211995+00:00, confidence not recorded.
  - readme: https://github.com/eriklindernoren/PyTorch-GAN (fetched 2026-08-28T04:11:19.677304+00:00, sha 2244f5168c3a)
- Data as of 2026-08-30T08:39:29.467469+00:00.