# kuaikuaikim/dface

Deep learning face detection and recognition, implemented by pytorch. (pytorch实现的人脸检测和人脸识别)

Repository: https://github.com/kuaikuaikim/dface
Canonical: https://ross.abutalabs.com/products/dface
Homepage: http://dface.tech
Language: Python
License: Apache-2.0
License Family: permissive
Topics: facedetection, facerecognition, deeplearning, pytorch, mtcnn, mtcnn-pytorch
Last push: 2024-02-21T03:26:35+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3209, "days_push": 924, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1339, forks 348 (observed 2026-08-28T04:04:25.910199+00:00)

## What it is
DFace is an open-source Python library implementing face detection and recognition with PyTorch, based on the MTCNN cascaded convolutional network architecture and FaceNet-style embeddings. It supports NVIDIA CUDA GPU acceleration for real-time performance and is released under the Apache-2.0 license.

## Use cases
- detect faces in images with pytorch
- build a face recognition system in python
- mtcnn face detection implementation
- extract face embeddings for identification
- real-time face detection on gpu
- face detection and alignment from webcam

## When to choose
- you need a pure PyTorch MTCNN face detection pipeline you can modify
- you want GPU-accelerated face detection and recognition in Python
- you want an Apache-2.0 licensed face recognition starting point

## When to avoid
- you need production-grade anti-spoofing, tracking, and support - the commercial DFace SDK covers that instead
- you need actively maintained models or recent research architectures
- you work outside Python/PyTorch ecosystems

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, windows
- tags: face-detection, face-recognition, mtcnn, pytorch, facenet, cuda, linux, macos, gpu

## Member repositories
- kuaikuaikim/dface (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.910199+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 2026-08-30T04:43:55.259695+00:00, confidence not recorded.
  - readme: https://github.com/kuaikuaikim/dface (fetched 2026-08-28T04:04:25.910199+00:00, sha 9c08e2ea2adc)
- Data as of 2026-08-30T08:39:29.467469+00:00.