# ronghuaiyang/arcface-pytorch

Repository: https://github.com/ronghuaiyang/arcface-pytorch
Canonical: https://ross.abutalabs.com/products/arcface-pytorch
Language: Python
License Family: other
Last push: 2021-12-09T11:00:04+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3010, "days_push": 1728, "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 1901, forks 401 (observed 2026-08-28T04:05:51.617682+00:00)

## What it is
A PyTorch implementation of ArcFace, a deep metric learning approach for face recognition that adds angular margin penalties to face embeddings. It includes model definitions, training and testing scripts, and a pretrained ResNet-18 model evaluated on the LFW dataset.

## Use cases
- train a face recognition model with arcface loss
- generate face embeddings for identity verification
- evaluate face recognition accuracy on lfw
- implement metric learning with angular margin loss in pytorch
- build a face matching or verification system
- compare arcface with cosface loss implementations

## When to choose
- you want a simple, readable PyTorch ArcFace implementation to train or fine-tune face recognition models
- you need a pretrained face embedding model for quick experiments on LFW
- you are learning how angular margin losses work in face recognition

## When to avoid
- you need a production-grade, actively maintained face recognition toolkit with many models and pipelines
- you require a permissive license - the repository has no license file
- you need multi-GPU training, ONNX export, or deployment tooling out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, cross-platform
- tags: face-recognition, arcface, pytorch, metric-learning, face-embedding, lfw

## Member repositories
- ronghuaiyang/arcface-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:51.617682+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 2026-08-30T03:11:57.561643+00:00, confidence not recorded.
  - readme: https://github.com/ronghuaiyang/arcface-pytorch (fetched 2026-08-28T04:05:51.617682+00:00, sha 114ace5055b0)
- Data as of 2026-08-30T08:39:29.467469+00:00.