ZhuSuan 是建立在Tensorflow上的贝叶斯深层学习的 python 库。 与现有的主要针对监督任务设计的深度学习库不同，ZhuSuan 的特点是深入到贝叶斯推理中，从而支持各种生成模式：传统的分层贝叶斯模型和近代深层次的生成模式。

用 ZhuSuan ，用户可以享受深度学习的强大适合和多GPU培训，同时可以使用生成模型来模拟复杂世界，利用未标记的数据，通过执行原理贝叶斯推理来处理不确定性。

项目地址：https://github.com/thu-ml/zhusuan

文档地址：http://zhusuan.readthedocs.io/en/latest/

ZhuSuan is a python library for Bayesian Deep Learning, built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for supervised tasks, ZhuSuan is featured for its deep root into Bayesian Inference, thus supporting various kinds of generative models: both the traditional hierarchical Bayesian models and recent deep generative models.

With ZhuSuan, users can enjoy powerful fitting and multi-GPU training of deep learning, while at the same time they can use generative models to model the complex world, exploit unlabeled data and deal with uncertainty by performing principled Bayesian inference.

更多 TensorFlow 教程：http://www.tensorflownews.com