# davidsandberg/facenet

Face recognition using Tensorflow

Repository: https://github.com/davidsandberg/facenet
Canonical: https://ross.abutalabs.com/products/facenet
Language: Python
License: MIT
License Family: permissive
Topics: face-recognition, tensorflow, facenet, deep-learning, computer-vision, face-detection, mtcnn
Last push: 2023-07-24T12:43:21+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": 3855, "days_push": 1136, "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 14343, forks 4774 (observed 2026-08-28T04:11:06.799964+00:00)

## What it is
A TensorFlow implementation of the FaceNet face recognizer that generates 128-dimensional face embeddings, including face detection via MTCNN and pretrained Inception ResNet v1 models. It also supports training classifiers on custom face datasets.

## Use cases
- recognize faces in images with deep learning
- generate face embeddings for clustering
- train a face classifier on my own photos
- detect and align faces with mtcnn
- compare two face images for identity
- build a face verification system

## When to choose
- you need a well-known FaceNet implementation with pretrained models and LFW benchmark results
- you want to train a face classifier on your own image dataset
- you are working with TensorFlow 1.x and Python 2.7/3.5

## When to avoid
- you need modern TensorFlow 2.x support or active maintenance
- you need state-of-the-art face recognition accuracy on recent benchmarks
- you need production support or timely bug fixes

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: facenet, face-recognition, face-embeddings, mtcnn, tensorflow, pretrained-models, lfw, linux

## Member repositories
- davidsandberg/facenet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:06.799964+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 2026-08-29T17:12:38.735594+00:00, confidence not recorded.
  - readme: https://github.com/davidsandberg/facenet (fetched 2026-08-28T04:11:06.799964+00:00, sha 62ce84c681a5)
- Data as of 2026-08-30T08:39:29.467469+00:00.