# vanhuyz/CycleGAN-TensorFlow

An implementation of CycleGan using TensorFlow

Repository: https://github.com/vanhuyz/CycleGAN-TensorFlow
Canonical: https://ross.abutalabs.com/products/cyclegan-tensorflow
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, generative-adversarial-network, cyclegan, gan
Last push: 2021-07-29T17:53:15+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3432, "days_push": 1861, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1189, forks 432 (observed 2026-08-28T04:03:55.481838+00:00)

## What it is
A TensorFlow implementation of CycleGAN for unpaired image-to-image translation, based on the original CycleGAN paper. It includes scripts for dataset preparation, training, and testing with configurable hyperparameters.

## Use cases
- translate photos between two unpaired image domains like apples and oranges
- train a CycleGAN model on my own image datasets
- convert horses to zebras in images with a GAN
- learn how CycleGAN works by reading a TensorFlow implementation
- experiment with GAN hyperparameters like cycle loss weights and instance norm

## When to choose
- you want a simple, readable CycleGAN reference implementation in TensorFlow 1.x
- you need to do unpaired image-to-image translation experiments
- you are learning GANs and want to study training code

## When to avoid
- you need TensorFlow 2.x or PyTorch support
- you need a production-ready, actively maintained image translation pipeline
- you need paired image translation like pix2pix

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, computer-vision, image-processing
- platform: python
- tags: cyclegan, gan, image-to-image-translation, tensorflow, unpaired-image-translation

## Member repositories
- vanhuyz/CycleGAN-TensorFlow (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.481838+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 2026-08-30T06:23:21.740789+00:00, confidence not recorded.
  - readme: https://github.com/vanhuyz/CycleGAN-TensorFlow (fetched 2026-08-28T04:03:55.481838+00:00, sha 32b6f6e1e79a)
- Data as of 2026-08-30T08:39:29.467469+00:00.