目标检测标签文件txt转成xml

最近在用ppyolo训练好的模型对新采集的数据进行标记，再人工微调，减少从头打标签的时间，但是推理保存的结果都是txt格式的，想要在labelimg中可视化，那就需要将txt转换成xml。

以下代码即可完成这一功能。

# -*- coding:UTF-8 -*-
import os
import cv2

def txt_to_xml(classname_path, txt_path, img_path, xml_path):
    # 1.读取txt文件中的标签类别
    with open(classname_path, 'r') as f:
        classes = f.readlines()  # list, 每个类别末尾都有'\n'
        classes = [cls.strip('\n') for cls in classes]

    # 2.找到txt标签文件夹
    files = os.listdir(txt_path)
    # 用于存储 "老图"
    pre_img_name = ''
    # 3.遍历文件夹
    for i, name in enumerate(files):
        # mac系统中文件夹里有该文件，默认的也删不掉，那就直接pass
        if name == '.DS_Store':
            continue
        print(name)
        # 4.打开txt
        txtFile = open(txt_path + name)
        # 读取所有内容
        txtList = txtFile.readlines()
        # 读取图片名称
        img_name = name.split(".")[0]
        pic = cv2.imread(img_path + img_name + ".jpg")
        # 获取图像大小信息
        Pheight, Pwidth, Pdepth = pic.shape
        # 5.遍历txt文件中每行内容
        for row in txtList:
            # 按' '分割txt的一行的内容
            oneline = row.strip().split(" ")
            # 遇到的是一张新图片
            if img_name != pre_img_name:
                # 6.新建xml文件
                xml_file = open((xml_path + img_name + '.xml'), 'w')
                xml_file.write('<annotation>\n')
                xml_file.write('    <folder>billiards</folder>\n')
                xml_file.write('    <filename>' + img_name + '.jpg' + '</filename>\n')
                xml_file.write('    <path>E:/Images</path>\n')
                xml_file.write('    <source>\n')
                xml_file.write('        <database>orgaquant</database>\n')
                xml_file.write('    </source>\n')
                xml_file.write('    <size>\n')
                xml_file.write('        <width>' + str(Pwidth) + '</width>\n')
                xml_file.write('        <height>' + str(Pheight) + '</height>\n')
                xml_file.write('        <depth>' + str(Pdepth) + '</depth>\n')
                xml_file.write('    </size>\n')
                xml_file.write('    <object>\n')
                xml_file.write('        <name>' + classes[int(oneline[0])] + '</name>\n')
                xml_file.write('        <difficult>' + str(0) + '</difficult>\n')
                xml_file.write('        <bndbox>\n')
                xml_file.write('            <xmin>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)) + '</xmin>\n')
                xml_file.write('            <ymin>' + str(
                    int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)) + '</ymin>\n')
                xml_file.write('            <xmax>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)) + '</xmax>\n')
                xml_file.write('            <ymax>' + str(
                    int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)) + '</ymax>\n')
                xml_file.write('        </bndbox>\n')
                xml_file.write('    </object>\n')
                xml_file.close()
                pre_img_name = img_name  # 将其设为"老"图
            else:  # 不是新图而是"老图"
                # 7.同一张图片，只需要追加写入object
                xml_file = open((xml_path + img_name + '.xml'), 'a')
                xml_file.write('    <object>\n')
                xml_file.write('        <name>' + classes[int(oneline[0])] + '</name>\n')
                xml_file.write('        <difficult>' + str(0) + '</difficult>\n')
                '''  按需添加这里和上面
                xml_file.write('        <pose>Unspecified</pose>\n')
                xml_file.write('        <truncated>0</truncated>\n')
                xml_file.write('        <difficult>0</difficult>\n')
                '''
                xml_file.write('        <bndbox>\n')
                xml_file.write('            <xmin>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)) + '</xmin>\n')
                xml_file.write('            <ymin>' + str(
                    int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)) + '</ymin>\n')
                xml_file.write('            <xmax>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)) + '</xmax>\n')
                xml_file.write('            <ymax>' + str(
                    int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)) + '</ymax>\n')
                xml_file.write('        </bndbox>\n')
                xml_file.write('    </object>\n')
                xml_file.close()

        # 8.读完txt文件最后写入</annotation>
        xml_file1 = open((xml_path + pre_img_name + '.xml'), 'a')
        xml_file1.write('</annotation>')
        xml_file1.close()
    print("Done !")

if __name__== '__main__':
    classname_path = '/Users/h1y/Documents/mac2server/billiards/billiards_classes.txt'  # names文件的路径
    # 修改成自己的文件夹 注意文件夹最后要加上/
    txt_path = "/Users/h1y/Documents/mac2server/billiards/txt2xml/labels/"
    img_path = "/Users/h1y/Documents/mac2server/billiards/txt2xml/images/"
    xml_path = "/Users/h1y/Documents/mac2server/billiards/txt2xml/"
    txt_to_xml(classname_path, txt_path, img_path, xml_path)

其中，代码中第一步提到的类别标签txt文件内容格式如下，每一行为一个类别

转换后的xml文件和labelimg生成的格式一样，如下所示