Welcome to ZhuSuan-Jittor

ZhuSuan-Jittor is a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Jittor. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan-Jittor provides deep learning style primitives and algorithms for building probabilistic models and applying Bayesian inference. The supported inference algorithms include:

• Variational inference with programmable variational posteriors, various objectives and advanced gradient estimators (SGVB, SWI, etc.).

• Importance sampling for learning and evaluating models, with programmable proposals.

• MCMC samplers: Hamiltonian Monte Carlo (HMC) with parallel chains, and Stochastic Gradient MCMC (sgmcmc).

Installation

ZhuSuan-Jittor is still under development. Before the first stable release (1.0), please clone the GitHub repository and run

pip install .

in the main directory. This will install ZhuSuan-Jittor and its dependencies automatically. ZhuSuan-Jittor is compatible with the lastest version of Jittor.

If you are developing ZhuSuan-Jittor, you may want to install in an “editable” or “develop” mode. Please refer to the Contributing section.

After installation, open your python console and type:

>>> import zhusuan as zs

If no error occurs, you’ve successfully installed ZhuSuan.

Tutorials

• Basic Concepts in ZhuSuan
• Variational Autoencoders
• Bayesian Neural Networks

API Docs

• zhusuan.distributions
• zhusuan.framework
• zhusuan.variational
• zhusuan.mcmc
• zhusuan.flows
• zhusuan.transforms

Community

• Contributing

Indices and tables

• Index

• Module Index

• Search Page