Probability Zoo

The Probability Zoo is a community repository for pre-trained probabilistic models. It includes any parameters to the model as well as parameters to its inferred posterior (such as a variational approximation or posterior samples).

  • Under construction. Check back soon!

To contribute a pre-trained model to the repository, please submit a pull request. The parameters should be preferably stored in a TensorFlow checkpoint file.


The Probability Zoo is inspired by the model zoo in Caffe (Jia et al., 2014), which provides many pre-trained discriminative neural networks. It is also inspired by Forest (Stuhlmüller, 2012), which provides examples of probabilistic programs.


Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., … Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. ArXiv Preprint ArXiv:1408.5093.

Stuhlmüller, A. (2012). Forest: A repository for generative models. Retrieved from