# aitorzip/PyTorch-CycleGAN

A clean and readable Pytorch implementation of CycleGAN

Repository: https://github.com/aitorzip/PyTorch-CycleGAN
Canonical: https://ross.abutalabs.com/products/pytorch-cyclegan
Homepage: https://arxiv.org/abs/1703.10593
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: generative-adversarial-network, deep-learning, pytorch, cyclegan, artificial-intelligence, computer-vision, image-generation, image-processing, computer-graphics
Last push: 2022-04-20T23:23:16+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3187, "days_push": 1596, "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 1319, forks 297 (observed 2026-08-28T04:04:21.332583+00:00)

## What it is
A clean, readable PyTorch implementation of CycleGAN for unpaired image-to-image translation using cycle-consistent adversarial networks. It includes training and testing scripts, dataset download helpers, and Visdom-based loss visualization.

## Use cases
- convert photos to paintings in the style of Monet or Van Gogh
- translate images between two domains without paired training data
- train a CycleGAN model on my own image dataset
- perform style transfer with a GAN in PyTorch
- season or object transfiguration on images
- learn how CycleGAN is implemented from readable code

## When to choose
- you want a minimal, readable CycleGAN reference implementation in PyTorch
- you have unpaired image sets from two domains and want to learn the translation
- you want to experiment with or extend CycleGAN hyperparameters

## When to avoid
- you need paired image-to-image translation (use pix2pix instead)
- you need a production-ready, actively maintained pipeline
- you need a no-code or GUI tool for image style transfer

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision, graphics
- domain: deep-learning, computer-vision, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: cyclegan, gan, pytorch, image-to-image-translation, style-transfer, unpaired-data, generative-models, gpu

## Member repositories
- aitorzip/PyTorch-CycleGAN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:21.332583+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 2026-08-30T04:47:53.203148+00:00, confidence not recorded.
  - readme: https://github.com/aitorzip/PyTorch-CycleGAN (fetched 2026-08-28T04:04:21.332583+00:00, sha 717ed71f776b)
  - homepage: https://arxiv.org/abs/1703.10593 (fetched 2026-08-29T12:06:34.391617+00:00, sha 53ba2f744c48)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:06:34.418830+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:06:34.422587+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:06:34.424943+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:06:34.420810+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.