Home Projects CompressAI
CompressAI
Python

CompressAI

A PyTorch library and evaluation platform for end-to-end compression research

by InterDigitalInc · GitHub
Stars
Forks
BSD-3-Clause-Clear
License
Created
Last commit
Category
Language
compressiondeep-learningdeep-neural-networksBSD-3-Clause-ClearPython
View on GitHub
In plain words

Research and evaluate methods for compressing images and videos using deep learning.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
CompressAI — GitHub preview card
📈 Star history
1 6091 608
2026-07-202026-08-31
📈 Track CompressAI

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

A PyTorch library and evaluation platform for end-to-end compression research

CompressAI has 1.6k stars on GitHub. It has been forked 275 times. CompressAI is written mainly in Python. It has been in active development since 2020. CompressAI is available under the BSD-3-Clause-Clear license. Its main topics are compression, deep-learning, deep-neural-networks, machine-learning.

Frequently asked questions

What is CompressAI?

A PyTorch library and evaluation platform for end-to-end compression research

Is CompressAI open source?

CompressAI is an open-source project. It is released under the BSD-3-Clause-Clear license.

Is CompressAI free?

Yes. CompressAI is free and open source — you can use, modify and self-host it.

What license does CompressAI use?

CompressAI is available under the BSD-3-Clause-Clear license.

What language is CompressAI written in?

CompressAI is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — CompressAI

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=interdigitalinc-compressai)](https://olud.ai/project/interdigitalinc-compressai.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.