yfeng95/GAN resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3098 stars · 794 forks observed · 2026-08-28

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

A collection of simple, educational implementations of classic Generative Adversarial Networks (GAN, DCGAN, WGAN, CGAN, InfoGAN) in Python with TensorFlow, tested on MNIST. It is organized for learning how GAN math and loss functions translate into actual code.

Use cases

• learn how GANs are implemented in code
• understand DCGAN architecture on MNIST
• study Wasserstein GAN loss implementation
• compare conditional GAN training strategies
• see how InfoGAN disentangled representations work
• find papers and blogs about adversarial nets

When to choose

• you want minimal, readable GAN implementations for study
• you are learning GAN theory alongside practical TensorFlow code
• you want to experiment with classic GAN variants on MNIST

When to avoid

• you need production-ready or maintained GAN code
• you require modern frameworks like PyTorch or recent GAN variants
• you need a supported library with a license and active maintenance

Facets

learning-resource · maturity abandoned

machine-learning deep-learning image-processing deep-learning machine-learning computer-vision tutorials python gan dcgan wgan cgan infogan tensorflow mnist educational linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yfeng95/GAN")