State-of-the-art 2D and 3D Face Analysis Project

Implementation of popular deep learning networks with TensorRT network definition API

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

RetinaFace: Deep Face Detection Library for Python

基于Yolov5车牌检测,更快更准.

yolov8 face detection with landmark

InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.

UniFace: An All-in-One Open-Source Face Analysis Library - Face Detection, Face Recognition, Landmark Localization, Face Parsing, Gaze Estimation, and Attribute Estimation (Age, Gender, Race)

nniefacelib是一个在海思35xx系列芯片上运行的人脸算法库

TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

yolov7 face detection with landmark

The remake of the https://github.com/biubug6/Pytorch_Retinaface

适用于复杂场景的人脸识别身份认证系统

Face Analysis: Detection, Age Gender Estimation & Recognition

Reimplement RetinaFace use C++ and TensorRT

RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.

基于人脸关键区域提取的人脸识别（LFW:99.82%+ CFP_FP:98.50%+ AgeDB30:98.25%+）

RetinaFace (RetinaFace: Single-stage Dense Face Localisation in the Wild, published in 2019) reimplemented in Tensorflow 2.0, with pretrained weights available !

Support Yolov5(4.0)/Yolov5(5.0)/YoloR/YoloX/Yolov4/Yolov3/CenterNet/CenterFace/RetinaFace/Classify/Unet. use darknet/libtorch/pytorch/mxnet to onnx to tensorrt

[CVPR 2020] Reimplementation of RetinaFace, faster and stronger.