Pytorch source code for arXiv paper Neural Network Renormalization Group, a generative model using variational renormalization group and normalizing flow.

Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data

Understanding normalizing flows

Pytorch implementation of Planar Flow

A minimal working example of Free-Form Jacobian of Reversible Dynamics

Propensity Score based Matching via Distribution Learning

PyTorch implementation of Real NVP for density estimation

Real NVP PyTorch a Minimal Working Example | Normalizing Flow

PyTorch implementation of the Masked Autoregressive Flow

Speeding up sampling

This is clean implementation of paper "Glow: Generative Flow with Invertible 1x1 Convolutions" in pytorch.

Unsplash2K dataset: 2K resolution high quality images

Tensorflow implementation of SurVAE Flows, Nielsen et al., 2020.

This repository contains examples of simple implementation of NF. Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact.

Extending the SurVAE Flows library to super-resolution, compressive, gradient boosted, and conditional flows.

Regularized Neural ODEs (RNODE)

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

TensorFlow implementation of "Variational Inference with Normalizing Flows"

Unofficial Pytorch Lightning implementation of "Variational Inference with Normalizing Flows" by [Rezende, et al., 2015]

Deep Probabilistic Imaging (DPI): Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging