dag-gans

Image-to-Image Translation in PyTorch

Workflow Engine for Kubernetes

An open-source runtime for composable workflows. Great for AI agents and CI/CD.

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Build data pipelines, the easy way ?️

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

The author's officially unofficial PyTorch BigGAN implementation.

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

【A common used C++ DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流

wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch