vanhuyz/CycleGAN-TensorFlow

Health v2 · maintenance only

Adoption not part of the score

1189 stars · 432 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning image-processing deep-learning computer-vision image-processing python cyclegan gan image-to-image-translation tensorflow unpaired-image-translation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vanhuyz/CycleGAN-TensorFlow")