junyanz/pytorch-CycleGAN-and-pix2pix

Project overview

This project provides PyTorch implementations for unpaired (CycleGAN) and paired (pix2pix) image-to-image translation. It supports training, testing, and applying pre-trained models to translate visual styles and content across image datasets.

Project type

Image & Vision · Infrastructure

Use cases

Image Processing

Deployment

Refer to project documentation

License

License pending

Best for

• Researchers, developers, and educators working on image-editing and image-to-image translation tasks.
• Users needing templates to implement custom models and datasets for new applications.

Key capabilities

• Train and test unpaired image-to-image translation models using CycleGAN.
• Train and test paired image-to-image translation models using pix2pix.
• Download and apply pre-trained CycleGAN and pix2pix models to generate results on new datasets.
• Supports Distributed Data Parallel (DDP) for single-machine multiple-GPU training.
• Provides templates for implementing custom models and datasets for new applications.
• Train and test pix2pix-based colorization models.

Limitations and risks

• The batch norm setting (--norm batch) is not compatible with Distributed Data Parallel (DDP) training.
• The implementation may not reproduce the exact same results as original Torch implementation papers.
• GPU usage is optional, and telemetry is optional. Coding is required, and data processing is local only.

Getting started

• Difficulty is medium and requires command-line knowledge. Clone the repository, install dependencies via conda, download a dataset using the provided shell scripts, and run training or testing via the command-line interface.

Evidence and sources

• GitHub project description: Image-to-Image Translation in PyTorch
• README: We provide PyTorch implementations for both unpaired and paired image-to-image translation.
• README: This PyTorch implementation produces results comparable to or better than our original Torch software.
• README: - To log training progress and test images to W&B dashboard, set the `--use_wandb` flag with training script - Train a model: ```bash #!./scripts/train_cyclegan.sh python train.py…
• README: - To log training progress and test images to W&B dashboard, set the `--use_wandb` flag with training script - Train a model: ```bash #!./scripts/train_pix2pix.sh python train.py…

Reviewed at: 2026-07-17T22:12:43Z