JDAI-CV/FaceX-Zoo

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1999 stars · 431 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FaceX-Zoo is a PyTorch toolbox for face recognition that provides training modules with various state-of-the-art supervisory heads and backbones, plus a standardized evaluation module for popular benchmarks like LFW, MegaFace, and IJB-C. It also includes a functional face SDK for validating and applying trained models, and supports extensions like face parsing and facial expression recognition.

Use cases

• train a face recognition model in pytorch
• evaluate face recognition models on lfw and megaface benchmarks
• build a face verification sdk
• train face recognition with swin transformer or repvgg backbones
• convert a face recognition model to onnx
• research masked face recognition
• benchmark different loss heads like magface and circle loss

When to choose

• you need to train or benchmark face recognition models with modern backbones and loss functions
• you want reproducible evaluation on standard face recognition protocols
• you need a starting point for building a face recognition SDK

When to avoid

• you need a production-ready turnkey face recognition product rather than a research toolbox
• your task is general object detection or recognition unrelated to faces
• you need a framework other than PyTorch

Facets

library · maturity maintenance

machine-learning deep-learning image-processing computer-vision sdk computer-vision image-processing deep-learning machine-learning artificial-intelligence python face-recognition pytorch face-verification biometrics model-training model-evaluation lfw megaface circle-loss onnx docker gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="JDAI-CV/FaceX-Zoo")