Skip to content

zhangkaij/pyro

Repository files navigation


Build Status Latest Version

Installation | Examples | Getting Started | Contributing | Discussion

Pyro is a flexible, scalable deep probabilistic programming library built on PyTorch. Notably, it was designed with these principles in mind:

  • Universal: Pyro is a universal PPL -- it can represent any computable probability distribution.
  • Scalable: Pyro scales to large data sets with little overhead compare to hand-written code.
  • Minimal: Pyro is agile and maintainable. It is implemented with a small core of powerful, composable abstractions.
  • Flexible: Pyro aims for automation when you want it, control when you need it. This is accomplished through high-level abstractions to express generative and inference models, while allowing experts easy-access to customize inference.

Pyro is developed and maintained by Uber AI Labs.

Installation

First install Pytorch.

Install via pip:

pip install pyro-ppl

Install from source:

git clone [email protected]:uber/pyro.git
cd pyro
pip install .

About

Deep universal probabilistic programming with Python and PyTorch

Resources

License

Contributing

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 52.9%
  • Jupyter Notebook 46.4%
  • Other 0.7%