carpedm20/DiscoGAN-pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1095 stars · 218 forks observed · 2026-08-28

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

A PyTorch implementation of DiscoGAN, a generative adversarial network that discovers cross-domain relations in an unsupervised manner. It includes training scripts, dataset download utilities, and sample results for image-to-image translation tasks.

Use cases

• train a DiscoGAN model for cross-domain image translation
• reproduce results from the DiscoGAN paper
• translate edges to shoes or handbags images
• experiment with unsupervised GAN training in PyTorch
• run image-to-image translation on custom paired image datasets

When to choose

• you want a reference PyTorch implementation of the DiscoGAN paper
• you need unsupervised cross-domain image-to-image translation code
• you are studying GAN-based relation discovery between image domains

When to avoid

• you need a maintained or production-ready image translation tool
• you require Python 3 support or modern PyTorch versions
• you want CycleGAN or a more widely supported GAN framework

Facets

library · maturity abandoned

machine-learning deep-learning image-processing machine-learning deep-learning computer-vision image-processing python gan discogan pytorch unsupervised-learning image-to-image-translation research-code generative-models gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="carpedm20/DiscoGAN-pytorch")