代码和MobileNet训练模型能够从如下位置下载:html
https://github.com/djmv/MobilNet_SSD_opencvpython
http://www.ebenezertechs.com/mobilenet-ssd-using-opencv-3-4-1-deep-learning-module-python/git
https://github.com/djmv/MobilNet_SSD_opencv github
网友加速框架
https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi#6-detect-objects性能
https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi学习
https://www.youtube.com/watch?v=gGqVNuYol6o&feature=youtu.bespa
https://blog.csdn.net/weixin_43558453/article/details/85175253.net
Tensorflow官方提供的本地编译的方式在arm嵌入式设备运行Tensorflow Lite3d
https://blog.csdn.net/weixin_43558453/article/details/86507764
即便是在实时检测并亮灯的时候树莓派的CPU的占用率也65%左右,因此小小的树莓派用Tengine仍是有能够继续发掘的潜力的。
若是你们对Tengine框架的性能有兴趣能够参考一下我以前写的那篇文章,关于Tengine和
http://shumeipai.nxez.com/2018/12/07/tengine-inference-engine-raspberry-pi-deep-learning.html
能够看到单帧耗时有所降低(400ms-700ms),
https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers/viola-cvpr-01.pdf