opencv-python使用基于caffe的训练模型处理视频流

最新推荐文章于 2024-07-30 22:43:37 发布

satomic

最新推荐文章于 2024-07-30 22:43:37 发布

阅读量1.7k

点赞数 2

分类专栏： python 文章标签： caffe 图像识别

本文链接：https://blog.csdn.net/satomic/article/details/80413619

版权

pre notice

to visit the orignal article, please click here A gentle guide to deep learning object detection
things need to be clarified: the cv2 version must be 3.3+, no metter python2 or python3, with the right cv2 version, this python script can run very well.

how to run the python script

python filter_object_detection.py --prototxt MobileNetSSD_deploy.prototxt --model MobileNetSSD_deploy.caffemodel

where can we download the caffe trained model files

model files what we need is MobileNetSSD_deploy.prototxt and MobileNetSSD_deploy.caffemodel, we can download them here caffe models link

python script

# coding=utf-8
# import the necessary packages
from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import cv2

# construct the argument