Density estimation using Real NVP

Code

• github.com/tensorflow/models
  tf★ 77,694
• github.com/ANLGBOY/RealNVP-with-PyTorch
  pytorch★ 15
• github.com/CompPhysVienna/paper_NF_for_rare_events
  pytorch★ 3
• github.com/SamArgt/AudioSourceSep
  tf★ 3
• github.com/desreslab/invaert4cardio
  pytorch★ 1
• gitlab.com/h2t/SALaT
  tf★ 0
• github.com/ispamm/realnvp-demo-pytorch
  pytorch★ 0
• github.com/e-hulten/real_nvp_2d
  pytorch★ 0
• github.com/gtegner/real_nvp
  pytorch★ 0
• github.com/wjy5446/pytorch-Real-NVP
  pytorch★ 0

Abstract

Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation and latent variable manipulations.

Tasks

Benchmark Results

Reproductions