serengil/retinaface

RetinaFace: Deep Face Detection Library for Python

What it solves

RetinaFace is a deep learning-based facial detector that identifies faces in images, even in crowded scenes. Beyond simple detection, it provides precise facial landmarks (eyes, nose, and mouth) which are essential for aligning faces to improve the accuracy of subsequent face recognition tasks.

How it works

It is a Python implementation of the RetinaFace model, based on the original insightface project. The library allows users to detect faces and extract facial landmarks using a pre-trained model. It supports multiple deep learning backends, including ONNX Runtime (default), TensorFlow, and PyTorch, allowing it to run across different environments without requiring a specific framework installation.

Who it’s for

This tool is for Python developers and researchers building computer vision applications that require robust face detection and alignment, particularly those integrating it into a larger face recognition pipeline.

Highlights

  • Crowd Detection: High performance in detecting faces within crowded images.
  • Facial Landmarks: Provides coordinates for the right eye, left eye, nose, and mouth corners.
  • Face Alignment: Includes functionality to align detected faces, which can increase recognition accuracy by nearly 7%.
  • Flexible Backends: Compatible with ONNX Runtime, TensorFlow, and PyTorch.

Related

  • Project
    deepinsight/insightface

    InsightFace is an open‑source 2D/3D face analysis library offering detection, recognition, alignment, video redaction, person‑level matching, and a self‑hosted server with REST API. Implemented in PyTorch/MXNet, it provides pretrained models, automatic hardware backend selection, and tools for large‑scale face search.

  • Project
    hysts/anime-face-detector

    A PyTorch-based tool for detecting anime faces and estimating 28 facial landmark points using pretrained Faster R-CNN, YOLOv3, and HRNetV2 models.

  • Project
    serengil/deepface

    A lightweight Python framework for face recognition and facial attribute analysis that wraps multiple state-of-the-art models for identity verification and demographic prediction.

  • Project
    yakhyo/uniface

    UniFace is a Python library that unifies 15 face‑analysis tasks—detection, landmarks, 3‑D mesh, parsing, matting, gaze, head pose, demographics, emotion, quality, anti‑spoofing, recognition, anonymisation, and FAISS‑based similarity—into a single, easy‑to‑install package (CPU, Apple Silicon, or CUDA). It provides a consistent API, auto‑downloads verified model weights, and includes extensive docs, notebooks, and a community Discord.

  • Project
    cmusatyalab/openface

    An open-source face recognition library using deep neural networks to identify people from images and real-time video streams.