# Tencent/TFace

A trusty face analysis research platform developed by Tencent Youtu Lab

Repository: https://github.com/Tencent/TFace
Canonical: https://ross.abutalabs.com/products/tface
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-12-11T08:31:00+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 56, release rhythm 35, longevity 100
- inputs: {"age_days": 1931, "days_push": 265, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1521, forks 251 (observed 2026-08-28T04:04:57.832533+00:00)

## What it is
TFace is a research platform from Tencent Youtu Lab for trusty face analysis, covering face recognition, face security (anti-spoofing), face quality assessment, and facial attribute estimation. It provides a high-performance distributed training framework and implementations of state-of-the-art published algorithms.

## Use cases
- train face recognition models
- implement face anti-spoofing and liveness detection
- assess face image quality
- predict facial attributes
- reproduce CVPR/ICCV/ECCV face recognition papers
- apply privacy-preserving face recognition techniques

## When to choose
- you need state-of-the-art face recognition training recipes
- you research face security, quality, or privacy-preserving recognition
- you want a distributed training framework for face analysis tasks

## When to avoid
- you need a production-ready face recognition API out of the box
- your task is general object detection or non-face computer vision
- you need a lightweight inference-only SDK without training infrastructure

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing, llm-training
- domain: computer-vision, machine-learning, security, artificial-intelligence
- platform: python
- tags: face-recognition, face-anti-spoofing, face-quality, facial-attributes, research-platform, privacy-preserving, gpu, linux

## Member repositories
- Tencent/TFace (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:57.832533+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 2026-08-30T04:31:50.472346+00:00, confidence not recorded.
  - readme: https://github.com/Tencent/TFace (fetched 2026-08-28T04:04:57.832533+00:00, sha f23a245f9c03)
- Data as of 2026-08-30T08:39:29.467469+00:00.