Home Projects SimCLR
SimCLR
Jupyter Notebook

SimCLR

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

by sthalles · GitHub
Stars
Forks
License
Created
Last commit
contrastive-lossdeep-learningmachine-learningMITJupyter Notebook
View on GitHub
In plain words

Run experiments to learn visual features from images using a simple framework for contrastive 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 →
SimCLR — GitHub preview card
📈 Star history
2.50k2.49k
2026-07-072026-08-31
📈 Track SimCLR

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 implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

SimCLR has 2.5k stars on GitHub. It has been forked 494 times. SimCLR is written mainly in Jupyter Notebook. It has been in active development since 2020. SimCLR is available under the MIT license. Its main topics are contrastive-loss, deep-learning, machine-learning, pytorch.

Frequently asked questions

What is SimCLR?

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

Is SimCLR open source?

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

Is SimCLR free?

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

What license does SimCLR use?

SimCLR is available under the MIT license.

What language is SimCLR written in?

SimCLR is written mainly in Jupyter Notebook.

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

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

[![olud.ai](https://olud.ai/badge.php?tool=sthalles-simclr)](https://olud.ai/project/sthalles-simclr.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.