Skip to content

PyTorch Glow: Generative Flow with Invertible 1x1 Convolutions

Notifications You must be signed in to change notification settings

kashperova/glow-pytorch

Repository files navigation

PyTorch Glow: Generative Flow with Invertible 1x1 Convolutions

MIT License Paper

Glow is a normalizing flow model introduced by OpenAI that uses an invertible generative architecture. Glow’s flow blocks consist of 3 components: act norm, 1x1 invertible convolutions and affine coupling layers.

This repository contains the complete workflow for training and testing Glow. All code was developed during the GenAI UCU course. Here are presented:

  • model implementation from scratch
  • train script with hydra configs
  • tensorboard logging
  • DDP trainer
  • tests with pytest
  • CI using github actions

About

PyTorch Glow: Generative Flow with Invertible 1x1 Convolutions

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages