Institute Homepage
Institute Homepage DE Sign In

Back

Empirical Inference The MIT License

normflows: A PyTorch Package for Normalizing Flows

Thumb ticker sm 2023 09 s
Empirical Inference
Vincent Stimper
  • Doctoral Researcher
Thumb ticker sm 2018 10 25
Empirical Inference
Timothy Gebhard
  • Doctoral Researcher
Normflow

normflows is a PyTorch implementation of discrete normalizing flows. Many popular flow architectures are implemented. The package can be easily installed via pip. The basic usage is described here, and a full documentation is available as well. A more detailed description of this package is given in out accompanying paper.

Implemented Flows

Architecture Reference
Planar Flow Rezende & Mohamed, 2015
Radial Flow Rezende & Mohamed, 2015
NICE Dinh et al., 2014
Real NVP Dinh et al., 2017
Glow Kingma et al., 2018
Masked Autoregressive Flow Papamakarios et al., 2017
Neural Spline Flow Durkan et al., 2019
Circular Neural Spline Flow Rezende et al., 2020
Residual Flow Chen et al., 2019
Stochastic Normalizing Flow Wu et al., 2020

licence_type: The MIT License
Authors: Vincent Stimper, Lukas Ryll, Timothy Gebhard, David Liu
Repository: https://github.com/VincentStimper/normalizing-flows
Documentation: https://vincentstimper.github.io/normalizing-flows/