xml转txt，适应各种图片格式，如jpg，png，jpeg，PNG，JPEG等

import xml.etree.ElementTree as ET
import os
import cv2
import numpy as np
import globclasses = []def convert(size, box):dw = 1. / (size[0])dh = 1. / (size[1])x = (box[0] + box[1]) / 2.0 - 1y = (box[2] + box[3]) / 2.0 - 1w = box[1] - box[0]h = box[3] - box[2]x = x * dww = w * dwy = y * dhh = h * dhreturn (x, y, w, h)def get_image_file(imgpath, imgname_without_ext):# 匹配多种图像格式extensions = ['jpg', 'jpeg', 'png', 'JPG', 'JPEG', 'PNG']for ext in extensions:imgfile = os.path.join(imgpath, f'{imgname_without_ext}.{ext}')if os.path.exists(imgfile):return imgfilereturn Nonedef convert_annotation(xmlpath, xmlname):with open(xmlpath, "r", encoding='utf-8') as in_file:txtname = xmlname[:-4] + '.txt'txtfile = os.path.join(txtpath, txtname)tree = ET.parse(in_file)root = tree.getroot()imgfile = get_image_file(imgpath, xmlname[:-4])if imgfile is None:print(f'No matching image file for {xmlname}')returnimg = cv2.imdecode(np.fromfile(imgfile, np.uint8), cv2.IMREAD_COLOR)h, w = img.shape[:2]res = []for obj in root.iter('object'):cls = obj.find('name').textif cls not in classes:classes.append(cls)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.append(str(cls_id) + " " + " ".join([str(a) for a in bb]))# 即使 res 为空也要创建 .txt 文件with open(txtfile, 'w+') as f:f.write('\n'.join(res))if __name__ == "__main__":imgpath = r"VOCdevkit\JPEGImages"  #图片文件夹路径xmlpath = r"Annotations"           #xml格式文件夹txtpath = r"VOCdevkit\txt"         #txt格式文件夹if not os.path.exists(txtpath):os.makedirs(txtpath, exist_ok=True)list = os.listdir(xmlpath)error_file_list = []for i in range(0, len(list)):try:path = os.path.join(xmlpath, list[i])if ('.xml' in path):convert_annotation(path, list[i])print(f'file {list[i]} convert success.')else:print(f'file {list[i]} is not xml format.')except Exception as e:print(f'file {list[i]} convert error.')print(f'error message:\n{e}')error_file_list.append(list[i])print(f'this file convert failure\n{error_file_list}')print(f'Dataset Classes:{classes}')

注意需要改的的地方如下：
改为自己相应的路径

    imgpath = r"VOCdevkit\JPEGImages"  #图片文件夹路径xmlpath = r"Annotations"           #xml格式文件夹txtpath = r"VOCdevkit\txt"         #txt格式文件夹