znxlwm/pytorch-generative-model-collections resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2627 stars · 538 forks observed · 2026-08-28

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

A PyTorch collection implementing many GAN variants (GAN, LSGAN, WGAN, WGAN-GP, DRAGAN, CGAN, infoGAN, ACGAN, EBGAN, BEGAN) with a shared architecture for fair comparison. It is a research/educational code collection ported from a TensorFlow reference implementation.

Use cases

• learn how different GAN variants are implemented in PyTorch
• compare GAN loss functions on the same network architecture
• generate MNIST or Fashion-MNIST images with a GAN
• get a starting codebase for experimenting with GANs
• reproduce results from GAN papers on small datasets

When to choose

• you want reference implementations of many classic GAN variants in one place
• you are studying or teaching generative adversarial networks
• you need a simple PyTorch GAN baseline on MNIST-like datasets

When to avoid

• you need production-ready or actively maintained GAN code
• you want modern architectures like diffusion models or StyleGAN
• you need a pip-installable library with an API rather than scripts
• you require a permissively licensed project (no license is specified)

Facets

learning-resource · maturity maintenance

machine-learning deep-learning machine-learning deep-learning image-processing python gan pytorch generative-models mnist research-code educational gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="znxlwm/pytorch-generative-model-collections")