python使用yolo来进行目标检测与识别代码

代码语言:python

所属分类:人工智能

代码描述:python使用yolo来进行目标检测与识别代码,可以识别人和物

代码标签: 目标 检测 识别

下面为部分代码预览,完整代码请点击下载或在bfwstudio webide中打开

import cv2
#import argparse
import numpy as np
import sys

#parser = argparse.ArgumentParser()
#parser.add_argument('--input', help='Path to input image.')
#args = parser.parse_args()

# Minimum confidence threshold. Increasing this will improve false positives but will also reduce detection rate.
min_confidence=0.14
model = '/data/wwwroot/default/model/yolov2.weights'
config = '/data/wwwroot/default/model/yolov2.cfg'


#Load names of classes
classes = None
with open('/data/wwwroot/default/model/labels.txt', 'rt') as f:
    classes = f.read().rstrip('\n').split('\n')
#print(classes)

# Load weights and construct graph
net = cv2.dnn.readNetFromDarknet(config, model)
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)

#winName = 'Running YOLO Model'
#cv2.namedWindow(winName, cv2.WINDOW_NORMAL)

#Read input image
frame = cv2.imread("/data/wwwroot/default/asset/test.jpg")

# Get width and height
height,width,ch=frame.shape

# Create a 4D blob from a frame.
blob = cv2.dnn.blobFromImage(frame, 1.0/2.........完整代码请登录后点击上方下载按钮下载查看

网友评论0