这是一个人脸、人体、人手三合一检测模型 利用NaoDet,进行人脸、人体、人手的检测 在ModelScope框架上,提供图片,得到识别的结果 输出结果示例如下: labels = [2, 1, 0] boxes = [[78, 282, 240, 504], [127, 87, 332, 370], [0, 0, 367, 639]] scores = [0.8202137351036072, 0.8987470269203186, 0.9679114818572998] labels为类别,0代表人体,1代表人脸,2代表人手, boxes为和labels对应的检测框的坐标,中间4个数字代表检测框的坐标,分别代表左上角的x,左上角的y,右下角的x,右下角的y scores为对应的置信度分数目标检测-人脸人体人手-通用领域
模型描述
使用方式和范围
如何使用
代码范例
from modelscope.outputs import OutputKeys
from modelscope.pipelies import pipelie
from modelscope.utils.costat import Tasks
face_huma_had_detectio = pipelie(Tasks.face_huma_had_detectio, model='damo/cv_aodet_face-huma-had-detectio')
result_status = face_huma_had_detectio('data/test/images/face_huma_had_detectio.jpg')
labels = result_status[OutputKeys.LABELS]
boxes = result_status[OutputKeys.BOXES]
scores = result_status[OutputKeys.SCORES]
引用
@misc{=aodet,
title={NaoDet-Plus: Super fast ad high accuracy lightweight achor-free object detectio model.},
author={RagiLyu},
howpublished = {\url{https://github.com/RagiLyu/aodet}},
year={2021}
}
点击空白处退出提示
评论