这个也不错:轻量级的:
https://github.com/DayBreak-u/yolo-face-with-landmark
最强人脸检测 yolov5 face:
https://blog.csdn.net/jacke121/article/details/116166641
https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB
Model | Easy Set | Medium Set | Hard Set |
---|---|---|---|
libfacedetection v1(caffe) | 0.741 | 0.683 | 0.421 |
libfacedetection v2(caffe) | 0.773 | 0.718 | 0.485 |
Retinaface-Mobilenet-0.25 (Mxnet) | 0.879 | 0.807 | 0.481 |
version-slim | 0.853 | 0.819 | 0.539 |
version-RFB | 0.855 | 0.822 | 0.579 |
向大家推荐一款基于PyTorch实现的快速高精度人脸特征点检测库,其在CPU上的运行速度可达100 fps。
项目地址:
https://github.com/cunjian/pytorch_face_landmark
68个关键点,正脸还行,半边脸回归是错误的,戴口罩也能检测,但是不是特别准。
https://sites.google.com/view/xjguo/fld
PFLD
cpu超过30fps:linux
https://github.com/markson14/Face-Recognition-Cpp
这个很牛叉的样子:人脸检测,无关键点
https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB
一款比mini-caffe更快的Forward库,觉得好用请点星啊,400星公布快速人脸检测模型,500星公布106点landmark,600星公布人头检测模型,700星公布人脸检测套餐(六种pnet,两种rnet随意混合使用满足各种速度/精度要求),800星公布更准的106点模型
https://github.com/zuoqing1988/ZQCNN
训练性别年龄:https://github.com/zuoqing1988/train-GenderAge
训练MTCNN:https://github.com/zuoqing1988/train-mtcnn
训练SSD: https://github.com/zuoqing1988/train-ssd
训练MTCNN用于人头检测:https://github.com/zuoqing1988/train-mtcnn-head
带人脸检测 ,人脸识别
https://github.com/JerryJiaGit/facenet_trt
这个能检测侧脸,效果可能好: