Home Projects clean-fid
clean-fid
Python

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

by GaParmar · GitHub
Stars
Forks
License
Created
Last commit
Language
computer-graphicscomputer-visiondeep-learningMITPython
View on GitHub
In plain words

Calculate image quality scores to compare different image generation methods.

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 →
clean-fid — GitHub preview card
📈 Star history
1 1671 166
2026-07-202026-08-31
📈 Track clean-fid

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

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

clean-fid has 1.2k stars on GitHub. It has been forked 82 times. clean-fid is written mainly in Python. It has been in active development since 2021. clean-fid is available under the MIT license. Its main topics are computer-graphics, computer-vision, deep-learning, fid.

Frequently asked questions

What is clean-fid?

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

Is clean-fid open source?

clean-fid is an open-source project. It is released under the MIT license.

Is clean-fid free?

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

What license does clean-fid use?

clean-fid is available under the MIT license.

What language is clean-fid written in?

clean-fid is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — clean-fid

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

[![olud.ai](https://olud.ai/badge.php?tool=gaparmar-clean-fid)](https://olud.ai/project/gaparmar-clean-fid.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.