face recognition / facial embeddings
A TensorFlow implementation of FaceNet for face recognition, with MTCNN-based detection/alignment and training/validation code.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
choose for a maintained Python library that exposes FaceNet and other embedding backends without TF1-era code.
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose when face recognition/analysis must run in the browser or Node rather than as a Python/TensorFlow library.
Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition
choose if you need an SDK-style package with liveness/anti-spoofing in addition to basic face recognition.
Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks
choose if you want face parsing/gaze/attributes combined with recognition in one PyTorch API.
UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, face-mesh, recognition, parsing, gaze, attributes and anti-spoofing under one API.
choose if you want PyTorch training/benchmark baselines for face recognition rather than FaceNet's TensorFlow code.
A powerful baseline for image classification, face recognition and image retrieval with Pytorch
choose when you want an Apache-2.0 Torch/Python face-recognition stack with dlib integration instead of TensorFlow.
Face recognition with deep neural networks.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose for Go services that can use a dlib-backed binding, accepting its stale maintenance.
:mag: Face recognition with Go
older research framework; choose only for prototypes needing liveness and speech combined with face recognition.
libfaceid is a research framework for prototyping of face recognition solutions. It seamlessly integrates multiple detection, recognition and liveness models w/ speech synthesis and speech recognition.
older PyTorch face detection/recognition baseline; use when you need its self-contained legacy PyTorch pipeline.
Deep learning face detection and recognition, implemented by pytorch. (pytorch实现的人脸检测和人脸识别)
older SphereFace embedding implementation; useful for reproducing that particular loss/research approach.
Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.
old PyTorch VGGFace2 recognizer; choose if you specifically need those pretrained embeddings.
PyTorch Face Recognizer based on 'VGGFace2: A dataset for recognising faces across pose and age'
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
choose when you want to deploy a self-hosted Docker face-recognition REST service rather than embed a Python model.
Leading free and open-source face recognition system
choose for a ready-to-run webcam face-recognition demo using dlib rather than a FaceNet library.
Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别
These projects were analysed and named facenet among their alternatives. The relationship is not symmetric — how facenet rates them is a separate judgement, made when facenet is analysed in its own right.
calls facenet “TensorFlow implementation of the original FaceNet; choose it if you specifically need that TF training/reference code and accept that it is unmaintained.”
Face recognition with deep neural networks.
calls facenet “Choose if you specifically need the original TensorFlow FaceNet models/research baseline, but it is no longer maintained.”
The world's simplest facial recognition api for Python and the command line