# JDAI-CV/FaceX-Zoo

A PyTorch Toolbox for Face Recognition

Repository: https://github.com/JDAI-CV/FaceX-Zoo
Canonical: https://ross.abutalabs.com/products/facex-zoo
Homepage: https://arxiv.org/pdf/2101.04407.pdf
Language: Python
License: NOASSERTION
License Family: other
Topics: face-recognition, masked-face-recognition, face-sdk, semi-siamese-training, megaface, lfw, circleloss, adam-softmax, mv-softmax, magface
Last push: 2024-02-16T02:03:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2058, "days_push": 930, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1999, forks 431 (observed 2026-08-28T04:06:03.811278+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision, sdk
- domain: computer-vision, image-processing, deep-learning, machine-learning, artificial-intelligence
- platform: python
- tags: face-recognition, pytorch, face-verification, biometrics, model-training, model-evaluation, lfw, megaface, circle-loss, onnx, docker, gpu

## Member repositories
- JDAI-CV/FaceX-Zoo (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.811278+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:09.674160+00:00, confidence not recorded.
  - readme: https://github.com/JDAI-CV/FaceX-Zoo (fetched 2026-08-28T04:06:03.811278+00:00, sha 66d7c0cc6a5d)
- Data as of 2026-08-30T08:39:29.467469+00:00.