txt转xml

from xml.dom.minidom import Document
import os
import cv2
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
    """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
    chirography
    color dot
    hole
    drawnwork
    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
    """
    # 本例中的标签有5个类,按照自己的类别进行更改
    dic = {'0': "chirography",  # 创建字典用来对类型进行转换
           '1': "color dot",  # 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': "hole",
           '3': "drawnwork"
           }
    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] + ".bmp")
        Pheight, Pwidth, Pdepth = img.shape

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

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

        path = xmlBuilder.createElement("path")  # path标签
        pathcontent = xmlBuilder.createTextNode(r"E:\My_project\projectCode\Python\new_things\datasets\datasets_13\\"+name[0:-4] + ".bmp")
        path.appendChild(pathcontent)
        annotation.appendChild(path)  # path标签结束

        source = xmlBuilder.createElement("source")  # source标签
        database = xmlBuilder.createElement("database")  # source子标签database
        databasecontent = xmlBuilder.createTextNode("Unknown")
        database.appendChild(databasecontent)
        source.appendChild(database)  # source子标签database结束
        annotation.appendChild(source)  # source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 ) - (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) - (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 ) + (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(xmlPath + name[0:-4] + ".xml", 'w')
        xmlBuilder.writexml(f, indent='', newl='\n', addindent='\t', encoding='utf-8')
        f.close()

# 注意下面的路径要换成自己文件夹的路径,否则会报错
makexml(r"E:\My_project\projectCode\Python\new_things\datasets\datasets_13\label/", 
        r"E:\My_project\projectCode\Python\new_things\datasets\datasets_13\label_xml/",
        r"E:\My_project\projectCode\Python\new_things\datasets\datasets_13\img/") 
# yolo标签的txt格式所在文件夹路径,voc标签的xml格式的文件保存路径,图片所在文件夹路径   !!!注意39行处还需要修改成自己文件夹的路径

xml转txt

import xml.etree.ElementTree as ET
import os
from glob import glob


# VOC格式的xml转YOLO格式的txt
def convert(size, box):
    '''
    size = (w, h)
    box = (xmin, xmax, ymin, ymax)
    '''
    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


# 单个标注文件的转换
def convert_annotation(image_id):
    res = ""
    in_file = open('{}/{}.xml'.format(xml_path, image_id))
    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'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            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)
        res += "{} {} {} {} {}\n".format(cls_id, bb[0], bb[1], bb[2], bb[3])
    return res


# 写文件
def write_file(fname, content):
    with open(fname, 'w') as f:
        f.write(content)


# 批量转换
def generate_label_file():
    # 获取所有xml文件
    xmls = glob("{}/*.xml".format(xml_path))
    xml_ids = [v.split(os.sep)[-1].split('.xml')[0] for v in xmls]
    for xml_id in xml_ids:
        content = convert_annotation(xml_id)
        if content != "":
            lable_file = "{}/{}.txt".format(txt_path, xml_id)
            write_file(lable_file, content)


if __name__ == '__main__':
    # 填写xml文件路径、txt文件保存路径
    xml_path = r"xml"
    txt_path = r"txt"

    # 填写类别列表
    classes = ["chirography","color dot","hole","drawnwork"]

    # 执行转换
    generate_label_file()
Logo

欢迎加入我们的广州开发者社区,与优秀的开发者共同成长!

更多推荐