VOC格式和YOLO格式标注互转

xml2txt.py

import xml.etree.ElementTree as ET
import os
 
 
voc_folder = r"xmls" #储存voc格式的标注文件的文件夹
yolo_folder = r"labels" #转换后的yolo格式标注文件的储存文件夹
 
class_id = ["100","200","300","400","500"] #储存数据集中目标种类名称的列表，接下来的转换函数中会将该列表中种类名称对应的列表索引号作为写入yolo标注文件中该类目标的种类序号
 
#voc标注的目标框坐标值转换到yolo标注的目标框坐标值的函数
def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / 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)
 
#对单个voc标注文件进行转换成其对应的yolo文件的函数
def convert_annotation(xml_file):
    file_name = xml_file.strip(".xml")  # 这一步将所有voc格式标注文件取出后缀名“.xml”，方便接下来作为yolo格式标注文件的名称
    in_file = open(os.path.join(voc_folder,xml_file)) #打开当前转换的voc标注文件
    out_file = open(os.path.join(yolo_folder,file_name + ".txt",),'w') #创建并打开要转换成的yolo格式标注文件
    tree = ET.parse(in_file)
    root = tree.getroot()
    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
        cls_id = class_id.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')
 
 
 
xml_fileList = os.listdir(voc_folder) #将所有voc格式的标注文件的名称取出存放到列表xml_fileList中
for xml_file in xml_fileList: #这里的for循环开始依次对所有voc格式标注文件生成其对应的yolo格式的标注文件
    convert_annotation(xml_file)

txt2xml.py

from xml.dom.minidom import Document
import os
import cv2
from tqdm import tqdm


# def makexml(txtPath, xmlPath, picPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径
def makexml(picPath, txtPath, xmlPath, datasetName):  # 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
    """
    dic = {'0': "100",  # 创建字典用来对类型进行转换
           '1': "200",  # 此处的字典要与自己的classes.txt文件中的类对应，且顺序要一致
           '2': "300",
           '3': "400",
           '4': "500"
           }
    files = os.listdir(txtPath)
    for i, name in enumerate(tqdm(files)):
        if name == 'classes.txt':
            continue
        xmlBuilder = Document()
        annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签
        xmlBuilder.appendChild(annotation)
        txtFile = open(os.path.join(txtPath, name))
        txtList = txtFile.readlines()
        img = cv2.imread(os.path.join(picPath, name.replace('txt', 'jpg')))
        Pheight, Pwidth, Pdepth = img.shape

        folder = xmlBuilder.createElement("folder")  # folder标签
        foldercontent = xmlBuilder.createTextNode(datasetName)
        folder.appendChild(foldercontent)
        annotation.appendChild(folder)  # folder标签结束

        filename = xmlBuilder.createElement("filename")  # filename标签
        filenamecontent = xmlBuilder.createTextNode(name[0:-4] + ".jpg")
        filename.appendChild(filenamecontent)
        annotation.appendChild(filename)  # filename标签结束

        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)  # size子标签width结束

        height = xmlBuilder.createElement("height")  # size子标签height
        heightcontent = xmlBuilder.createTextNode(str(Pheight))
        height.appendChild(heightcontent)
        size.appendChild(height)  # size子标签height结束

        depth = xmlBuilder.createElement("depth")  # size子标签depth
        depthcontent = xmlBuilder.createTextNode(str(Pdepth))
        depth.appendChild(depthcontent)
        size.appendChild(depth)  # size子标签depth结束

        annotation.appendChild(size)  # size标签结束

        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)  # name标签结束

            pose = xmlBuilder.createElement("pose")  # pose标签
            posecontent = xmlBuilder.createTextNode("Unspecified")
            pose.appendChild(posecontent)
            object.appendChild(pose)  # pose标签结束

            truncated = xmlBuilder.createElement("truncated")  # truncated标签
            truncatedContent = xmlBuilder.createTextNode("0")
            truncated.appendChild(truncatedContent)
            object.appendChild(truncated)  # truncated标签结束

            difficult = xmlBuilder.createElement("difficult")  # difficult标签
            difficultcontent = xmlBuilder.createTextNode("0")
            difficult.appendChild(difficultcontent)
            object.appendChild(difficult)  # difficult标签结束

            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)  # xmin标签结束

            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)  # ymin标签结束

            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)  # xmax标签结束

            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)  # ymax标签结束

            object.appendChild(bndbox)  # bndbox标签结束

            annotation.appendChild(object)  # object标签结束

        f = open(os.path.join(xmlPath, name.replace('txt', 'xml')), 'w')
        xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
        f.close()


if __name__ == "__main__":
    picPath = r"images/"         # 原图文件夹路径
    txtPath = r"labels/"    # 原txt标签文件夹路径
    xmlPath = r"xmls/"    # 保存xml文件夹路径
    datasetName = r'MyDataset'      # 数据集名称
    os.makedirs(xmlPath) if not os.path.exists(xmlPath) else None
    makexml(picPath, txtPath, xmlPath, datasetName)

    # tasks = ['train', 'test', 'val']          # 当前任务
    # for task in tasks:
    #     picPath = r"...\images\{}".format(task)         # 原图文件夹路径
    #     txtPath = r"...\labels\{}".format(task)         # 原txt标签文件夹路径
    #     xmlPath = r"...\labels\{}_xml".format(task)     # 保存xml文件夹路径
    #     datasetName = r'MyDataset'
    #     os.makedirs(xmlPath) if not os.path.exists(xmlPath) else None
    #     makexml(picPath, txtPath, xmlPath, datasetName)