赞
踩
- import xml.etree.ElementTree as ET
-
- import pickle
- import os
- from os import listdir, getcwd
- from os.path import join
- import glob
-
- classes = ["", "", "", ""] #这里是需要改的第一个地方,写入自己的标签类型,不可多写,不可少写
-
-
- def convert(size, box):
- dw = 1.0 / size[0]
- dh = 1.0 / size[1]
- x = (box[0] + box[1]) / 2.0
- y = (box[2] + box[3]) / 2.0
- w = box[1] - box[0]
- h = box[3] - box[2]
- x = x * dw
- w = w * dw
- y = y * dh
- h = h * dh
- return (x, y, w, h)
-
-
- def convert_annotation(image_name):
- in_file = open("D:\\data set\\Pepper_3.0\\test\\xmllabels\\" + image_name[:-3] + 'xml') # 这里是需要改的第二个地方,输入xml文件的路径
- out_file = open("D:\\data set\\Pepper_3.0\\test\\labels\\" + image_name[:-3] + 'txt', 'w') # 这里是需要改的第三个地方,输入用于存放转换后的txt文件的路径
-
- f = open("D:\\data set\\Pepper_3.0\\test\\xmllabels\\"+ image_name[:-3] + 'xml')
- xml_text = f.read()
- root = ET.fromstring(xml_text)
- f.close()
- size = root.find('size')
- w = int(size.find('width').text)
- h = int(size.find('height').text)
-
- for obj in root.iter('object'):
- cls = obj.find('name').text
- if cls not in classes:
- print(cls)
- continue
- cls_id = classes.index(cls)
- xmlbox = obj.find('bndbox')
- b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
- float(xmlbox.find('ymax').text))
- bb = convert((w, h), b)
-
- out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
-
-
-
-
-
- wd = getcwd()
-
- if __name__ == '__main__':
-
- for image_path in glob.glob("D:\\data set\\Pepper_3.0\\test\\images\\*.jpg"): # 这里是需要改的最后一个地方,输入图片的路径,每一张图图片都要有一个xml文件对应,没有对应xml文件的图片要删除,当然,这里图片的命名要和对应xml文件的命名一致,之后就可以输出对应命名的txt文件
- image_name = image_path.split('\\')[-1]
- convert_annotation(image_name)
'运行
- from xml.dom.minidom import Document
- import os
- import cv2
-
-
- def makexml(picPath, txtPath, xmlPath): # txt所在文件夹路径,xml文件保存路径,图片所在文件夹路径
- """此函数用于将yolo格式txt标注文件转换为voc格式xml标注文件
- 在自己的标注图片文件夹下建三个子文件夹,分别命名为picture、txt、xml
- """
- # 创建字典用来对类型进行转换,要与classes.txt文件中的类对应,且顺序要一致
- dic = {'0': "Capsicum anthracnose", '1': "Viral diseases", '2': "Bacterial diseases", '3': "Umbilical rot"}
- files = os.listdir(txtPath)
- for i, name in enumerate(files):
- xmlBuilder = Document()
- annotation = xmlBuilder.createElement("annotation") # 创建annotation标签
- xmlBuilder.appendChild(annotation)
- txtFile = open(txtPath + name)
- txtList = txtFile.readlines()
- img = cv2.imread(picPath + name[0:-4] + ".jpg") # 注意这里的图片后缀,.jpg/.png
- Pheight, Pwidth, Pdepth = img.shape
-
- folder = xmlBuilder.createElement("folder") # folder标签
- foldercontent = xmlBuilder.createTextNode("datasetRGB")
- folder.appendChild(foldercontent)
- annotation.appendChild(folder)
-
- filename = xmlBuilder.createElement("filename") # filename标签
- filenamecontent = xmlBuilder.createTextNode(name[0:-4] + ".jpg")
- filename.appendChild(filenamecontent)
- annotation.appendChild(filename)
-
- size = xmlBuilder.createElement("size") # size标签
- width = xmlBuilder.createElement("width") # size子标签width
- widthcontent = xmlBuilder.createTextNode(str(Pwidth))
- width.appendChild(widthcontent)
- size.appendChild(width)
-
- height = xmlBuilder.createElement("height") # size子标签height
- heightcontent = xmlBuilder.createTextNode(str(Pheight))
- height.appendChild(heightcontent)
- size.appendChild(height)
-
- depth = xmlBuilder.createElement("depth") # size子标签depth
- depthcontent = xmlBuilder.createTextNode(str(Pdepth))
- depth.appendChild(depthcontent)
- size.appendChild(depth)
-
- annotation.appendChild(size)
-
- for j in txtList:
- oneline = j.strip().split(" ")
- object = xmlBuilder.createElement("object") # object 标签
- picname = xmlBuilder.createElement("name") # name标签
- namecontent = xmlBuilder.createTextNode(dic[oneline[0]])
- picname.appendChild(namecontent)
- object.appendChild(picname)
-
- pose = xmlBuilder.createElement("pose") # pose标签
- posecontent = xmlBuilder.createTextNode("Unspecified")
- pose.appendChild(posecontent)
- object.appendChild(pose)
-
- truncated = xmlBuilder.createElement("truncated") # truncated标签
- truncatedContent = xmlBuilder.createTextNode("0")
- truncated.appendChild(truncatedContent)
- object.appendChild(truncated)
-
- difficult = xmlBuilder.createElement("difficult") # difficult标签
- difficultcontent = xmlBuilder.createTextNode("0")
- difficult.appendChild(difficultcontent)
- object.appendChild(difficult)
-
- bndbox = xmlBuilder.createElement("bndbox") # bndbox标签
- xmin = xmlBuilder.createElement("xmin") # xmin标签
- mathData = int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)
- xminContent = xmlBuilder.createTextNode(str(mathData))
- xmin.appendChild(xminContent)
- bndbox.appendChild(xmin)
-
- ymin = xmlBuilder.createElement("ymin") # ymin标签
- mathData = int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)
- yminContent = xmlBuilder.createTextNode(str(mathData))
- ymin.appendChild(yminContent)
- bndbox.appendChild(ymin)
-
- xmax = xmlBuilder.createElement("xmax") # xmax标签
- mathData = int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)
- xmaxContent = xmlBuilder.createTextNode(str(mathData))
- xmax.appendChild(xmaxContent)
- bndbox.appendChild(xmax)
-
- ymax = xmlBuilder.createElement("ymax") # ymax标签
- mathData = int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)
- ymaxContent = xmlBuilder.createTextNode(str(mathData))
- ymax.appendChild(ymaxContent)
- bndbox.appendChild(ymax)
-
- object.appendChild(bndbox) # bndbox标签结束
-
- annotation.appendChild(object)
-
- f = open(xmlPath + name[0:-4] + ".xml", 'w')
- xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
- f.close()
-
-
- if __name__ == "__main__":
- picPath = "D:\\data set\\d1_2.0\\d1_2.0\\" # 图片所在文件夹路径,后面的\\一定要带上
- txtPath = "D:\\data set\\d1_2.0\\d1_2.0txt\\" # txt所在文件夹路径,后面的\\一定要带上
- xmlPath = "D:\\data set\\d1_2.0\\d1_2.0xml\\" # xml文件保存路径,后面的\\一定要带上
- makexml(picPath, txtPath, xmlPath)
3 数据集划分训练集验证集及测试集
- import os
- import shutil
- import random
-
- random.seed(0)
-
-
- def split_data(file_path,xml_path, new_file_path, train_rate, val_rate, test_rate):
- each_class_image = []
- each_class_label = []
- for image in os.listdir(file_path):
- each_class_image.append(image)
- for label in os.listdir(xml_path):
- each_class_label.append(label)
- data=list(zip(each_class_image,each_class_label))
- total = len(each_class_image)
- random.shuffle(data)
- each_class_image,each_class_label=zip(*data)
- train_images = each_class_image[0:int(train_rate * total)]
- val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
- test_images = each_class_image[int((train_rate + val_rate) * total):]
- train_labels = each_class_label[0:int(train_rate * total)]
- val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
- test_labels = each_class_label[int((train_rate + val_rate) * total):]
-
- for image in train_images:
- print(image)
- old_path = file_path + '/' + image
- new_path1 = new_file_path + '/' + 'train' + '/' + 'images'
- if not os.path.exists(new_path1):
- os.makedirs(new_path1)
- new_path = new_path1 + '/' + image
- shutil.copy(old_path, new_path)
-
- for label in train_labels:
- print(label)
- old_path = xml_path + '/' + label
- new_path1 = new_file_path + '/' + 'train' + '/' + 'labels'
- if not os.path.exists(new_path1):
- os.makedirs(new_path1)
- new_path = new_path1 + '/' + label
- shutil.copy(old_path, new_path)
-
- for image in val_images:
- old_path = file_path + '/' + image
- new_path1 = new_file_path + '/' + 'val' + '/' + 'images'
- if not os.path.exists(new_path1):
- os.makedirs(new_path1)
- new_path = new_path1 + '/' + image
- shutil.copy(old_path, new_path)
-
- for label in val_labels:
- old_path = xml_path + '/' + label
- new_path1 = new_file_path + '/' + 'val' + '/' + 'labels'
- if not os.path.exists(new_path1):
- os.makedirs(new_path1)
- new_path = new_path1 + '/' + label
- shutil.copy(old_path, new_path)
-
- for image in test_images:
- old_path = file_path + '/' + image
- new_path1 = new_file_path + '/' + 'test' + '/' + 'images'
- if not os.path.exists(new_path1):
- os.makedirs(new_path1)
- new_path = new_path1 + '/' + image
- shutil.copy(old_path, new_path)
-
- for label in test_labels:
- old_path = xml_path + '/' + label
- new_path1 = new_file_path + '/' + 'test' + '/' + 'labels'
- if not os.path.exists(new_path1):
- os.makedirs(new_path1)
- new_path = new_path1 + '/' + label
- shutil.copy(old_path, new_path)
-
-
- if __name__ == '__main__':
- file_path = "D:/data set/Pepper_data/image"
- xml_path = "D:/data set/Pepper_data/label"
- new_file_path = "D:/data set/Pepper_3.0"
- split_data(file_path, xml_path, new_file_path, train_rate=0.6, val_rate=0.2, test_rate=0.2)
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。