https://github.com/facebookincubator/flowtorch

This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a community of users and contributors by focusing initially on complete infra and documentation for how to use and create components.
https://github.com/facebookincubator/flowtorch

Last synced: 3 months ago
JSON representation

This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a community of users and contributors by focusing initially on complete infra and documentation for how to use and create components.

• Host: GitHub
• URL: https://github.com/facebookincubator/flowtorch
• Owner: facebookincubator
• License: mit
• Created: 2021-02-22T21:07:21.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2024-10-28T19:26:13.000Z (3 months ago)
• Last Synced: 2024-10-28T20:27:34.468Z (3 months ago)
• Language: Jupyter Notebook
• Homepage: https://flowtorch.ai
• Size: 7.23 MB
• Stars: 300
• Watchers: 30
• Forks: 21
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE.txt
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• awesome-normalizing-flows - flowtorch

README

        


[![](https://github.com/facebookincubator/flowtorch/workflows/Python%20package/badge.svg)](https://github.com/facebookincubator/flowtorch/actions?query=workflow%3A%22Python+package%22)

Copyright © Meta Platforms, Inc

This source code is licensed under the MIT license found in the

[LICENSE.txt](https://github.com/facebookincubator/flowtorch/blob/main/LICENSE.txt) file in the root directory of this source tree.

> :warning: **Development of FlowTorch has moved**: This repo will be frozen, and development continued at [stefanwebb/flowtorch](https://github.com/stefanwebb/flowtorch).

# Overview

FlowTorch is a PyTorch library for learning and sampling from complex probability distributions using a class of methods called [Normalizing Flows](https://arxiv.org/abs/1908.09257).

# Installing

An easy way to get started is to install from source:

    git clone https://github.com/facebookincubator/flowtorch.git

    cd flowtorch

    pip install -e .

# Further Information

We refer you to the [FlowTorch website](https://flowtorch.ai) for more information about installation, using the library, and becoming a contributor. Here is a handy guide:

* [What are normalizing flows?](https://flowtorch.ai/users)

* [How do I install FlowTorch?](https://flowtorch.ai/users/installation)

* [How do I construct and train a distribution?](https://flowtorch.ai/users/start)

* [How do I contribute new normalizing flow methods?](https://flowtorch.ai/dev)

* [Where can I report bugs?](https://github.com/facebookincubator/flowtorch/issues)

* [Where can I ask general questions and make feature requests?](https://github.com/facebookincubator/flowtorch/discussions)

* [What features are planned for the near future?](https://github.com/facebookincubator/flowtorch/projects)