svae | code for Structured Variational Autoencoders | Machine Learning library

svae is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch, Tensorflow applications. svae has no bugs, it has no vulnerabilities, it has build file available and it has low support. You can download it from GitHub.

Code for Composing graphical models with neural networks for structured representations and fast inference, a.k.a. structured variational autoencoders. NOTE: This code isn't yet compatible with a recent rewrite of autograd. To use an older, compatible version of autograd, clone autograd and check out commit 0f026ab. We propose a general modeling and inference framework that composes probabilistic graphical models with deep learning methods and combines their respective strengths. Our model family augments graphical structure in latent variables with neural network observation models. For inference we extend variational autoencoders to use graphical model approximating distributions, paired with recognition networks that output conjugate potentials. All components of these models are learned simultaneously with a single objective, giving a scalable algorithm that leverages stochastic variational inference, natural gradients, graphical model message passing, and the reparameterization trick. We illustrate this framework with several example models and an application to mouse behavioral phenotyping.