InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy

TL;DR

InferPy is a user-friendly Python library that simplifies the creation, training, and evaluation of hierarchical probabilistic models with deep neural networks, built on TensorFlow Probability and Keras.

Contribution

It introduces a simplified API for probabilistic modeling with deep neural networks, balancing model complexity and usability.

Findings

Enables easy definition of hierarchical probabilistic models

Supports training and evaluation within a compact API

Built on TensorFlow Probability and Keras for flexibility

Abstract

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.