Home Projects sphereface
sphereface
Jupyter Notebook

sphereface

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

by wy1iu · GitHub
Stars
Forks
License
Created
Last commit
angular-softmaxcaffecvpr-2017MITJupyter Notebook
View on GitHub
In plain words

Implement a method for face recognition that uses deep learning to improve accuracy in identifying individuals.

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 →
sphereface — GitHub preview card
📈 Star history
1.61k1.60k
2026-07-202026-08-31
📈 Track sphereface

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

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

sphereface has 1.6k stars on GitHub. It has been forked 531 times. sphereface is written mainly in Jupyter Notebook. It has been in active development since 2017. sphereface is available under the MIT license. Its main topics are angular-softmax, caffe, cvpr-2017, deep-learning.

Frequently asked questions

What is sphereface?

Implementation for in CVPR'17.

Is sphereface open source?

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

Is sphereface free?

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

What license does sphereface use?

sphereface is available under the MIT license.

What language is sphereface written in?

sphereface is written mainly in Jupyter Notebook.

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

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

[![olud.ai](https://olud.ai/badge.php?tool=wy1iu-sphereface)](https://olud.ai/project/wy1iu-sphereface.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.