yolov8特殊xml转txt

xml标注没有高度和宽度信息或者执行python脚本时报错：AttributeError: 'NoneType' object has no attribute 'find'？报这个错误查看xml文件里有没有这个height或者weight

import xml.etree.ElementTree as ET
import os
import cv2
from tqdm import tqdm

classes = ["holothurian", "echinus", "scallop", "starfish"]  # 类别
xml_path = "xml标签文件夹路径"
txt_path = "txt标签存储路径"
image_path = "图像文件夹路径"


# 将原有的xmax,xmin,ymax,ymin换为x,y,w,h
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)


# 输入时图像和图像的宽高
def convert_annotation(image_id, width, hight):
    in_file = open(xml_path + '\\{}.xml'.format(image_id), encoding='UTF-8')
    out_file = open(txt_path + '\\{}.txt'.format(image_id), 'w')  # 生成同名的txt格式文件
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')	# 此处是获取原图的宽高，便于后续的归一化操作
    if size is not None:
        w = int(size.find('width').text)
        h = int(size.find('height').text)
    else:
        w = width
        h = hight
        
    for obj in root.iter('object'):
        cls = obj.find('name').text
        # print(cls)
        if cls not in classes:	# 此处会将cls里没有的类别打印，以便后续添加
            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')


# 遍历图片文件将对应的宽高输入convert_annotation，并通过图片名称搜索相对应的xml文件获取label
if __name__  == "__main__":
    img_list = os.listdir(image_path)
    for img in tqdm(img_list):
        label_name = img.split('.')[0]
        print(label_name)
        w, h = cv2.imread(os.path.join(image_path, img)).shape[:2]
        convert_annotation(label_name, w, h)

如果还报错那就是程序文件路径有问题按下面格式改

 

import xml.etree.ElementTree as ET
import os
import cv2
from tqdm import tqdm

classes = ["holothurian", "echinus", "scallop", "starfish"]  # 类别
xml_path = "C:\\Users\\sc\\Desktop\\Mydataset\\data\\Annotations"
txt_path = "C:\\Users\\sc\\Desktop\\Mydataset\\data\\txtlabel"
image_path = "C:\\Users\\sc\\Desktop\\Mydataset\\data\\images"


# 将原有的xmax,xmin,ymax,ymin换为x,y,w,h
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)


# 输入时图像和图像的宽高
def convert_annotation(image_id, width, hight):
    in_file = open(xml_path + '\\{}.xml'.format(image_id), encoding='UTF-8')
    out_file = open(txt_path + '\\{}.txt'.format(image_id), 'w')  # 生成同名的txt格式文件
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')  # 此处是获取原图的宽高，便于后续的归一化操作
    if size is not None:
        w = int(size.find('width').text)
        h = int(size.find('height').text)
    else:
        w = width
        h = hight

    for obj in root.iter('object'):
        cls = obj.find('name').text
        # print(cls)
        if cls not in classes:  # 此处会将cls里没有的类别打印，以便后续添加
            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')


# 遍历图片文件将对应的宽高输入convert_annotation，并通过图片名称搜索相对应的xml文件获取label
if __name__ == "__main__":
    img_list = os.listdir(image_path)
    for img in tqdm(img_list):
        label_name = img.split('.')[0]
        print(label_name)
        w, h = cv2.imread(os.path.join(image_path, img)).shape[:2]
        convert_annotation(label_name, w, h)