1、从网上下载opencvDNN模块的程序
https://github.com/iArunava/YOLOv3-Object-Detection-with-OpenCV
此程序可以进行跳帧检测,适合部署工业端。
2、下载U版YOLOv3-8.0版本,开始进行行人训练,对VOC数据集通过以下程序进行自动划分:https://www.cnblogs.com/pprp/p/10863496.html
使用YOLOv3-tiny模型,修改cfg参数:class,3*(class+5).
3、训练完成后转换模型至.weights格式:$ git clone https://github.com/ultralytics/yolov3 && cd yolov3
# convert darknet cfg/weights to pytorch model
$ python3 -c "from models import *; convert('cfg/yolov3-tiny.cfg', 'weights/yolov3-tiny.weights')"
Success: converted 'weights/yolov3-tiny.weights' to 'weights/yolov3-tiny.pt'
# convert cfg/pytorch model to darknet weights
$ python3 -c "from models import *; convert('cfg/yolov3-tiny.cfg', 'weights/best.pt')"
Success: converted 'weights/yolov3-tiny.pt' to 'weights/yolov3-tiny.weights'
4、修改摄像头模块,改为1外置摄像头.
5.下一步进行部署到openvino推理引擎上,加油!