InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy
C\'ozar, Javier, Caba\~nas, Rafael, Salmer\'on, Antonio, Masegosa, Andr\'es R. · arXiv (Cornell University) · 2019
InferPy is a Python package for probabilistic modeling with deep neural networks. It defines a user-friendly API that trades-off model complexity with ease of use, unlike other libraries whose focus is on dealing with very general probabilistic models at the cost of having a more complex API. In particular, this package allows to define, learn and evaluate general hierarchical probabilistic models containing deep neural networks in a compact and simple way. InferPy is built on top of Tensorflow Probability and Keras.