A
Angular-Penalty-Softmax-Losses-Pytorch
cvqluu/Angular-Penalty-Softmax-Losses-Pytorch
Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)
★499stars
Python
MIT
Updated: 1mo ago
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Models category, core strengths: am-softmax/arcface
Who made it?Maintained by cvqluu team, 499⭐ on GitHub, #1819 out of 3201 in Models
Why does it exist?The cvqluu team recognized that existing am-softmax tools in Models were hard to use. Angular-Penalty-Softmax-Losses-Pytorch was designed to make arcface more accessible.
What can it do?Key use cases: embedding, face-recognition, face-verification
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/cvqluu/Angular-Penalty-Softmax-Losses-Pytorch
🔗 github.com/cvqluu/Angular-Penalty-Softmax-Losses-Pytorch
Topics
am-softmaxarcfaceembeddingface-recognitionface-verificationfashion-mnistfmnist-datasetloss-functionloss-functionsmetric-learningnormfacepytorchspeaker-recognitionsphereface