eriklindernoren/Keras-GAN
Keras implementations of Generative Adversarial Networks.
Implements 21+ GAN variants from research papers including conditional, image-to-image translation (Pix2Pix, CycleGAN), super-resolution, and domain adaptation architectures. Each model is built with Keras' functional API using paired generator-discriminator networks, simplified to emphasize core algorithmic differences rather than exhaustive layer tuning. Designed as reference implementations for researchers and practitioners to understand and experiment with different GAN formulations.
9,226 stars. No commits in the last 6 months.
Stars
9,226
Forks
3,096
Language
Python
License
MIT
Category
Last pushed
Dec 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eriklindernoren/Keras-GAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
NVlabs/MUNIT
Multimodal Unsupervised Image-to-Image Translation