xml转txt格式标注数据

import xml.etree.ElementTree as ET
import os
from os import getcwd
from os.path import join
import glob

classes = ['pig']  # 标注时的标签


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)


def convert_annotation(data_dir, image_id):
    in_file = open(data_dir + '/annotations/%s.xml' % (image_id), encoding="utf-8")  # 读取xml
    out_file = open(data_dir + '/labels/%s.txt' % (image_id), 'w', encoding="utf-8")  # 保存txt

    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
        # clss = obj.find('name').text
        clss = 'pig'  # 1类
        if clss not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(clss)  # 获取类别索引
        # cls_id = '1'
        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('%.6f' % a) for a in bb]) + '\n')


wd = getcwd()
print(wd)  # 当前路径

data_dir = r'C:\Users\haohao\Desktop\all_outputs'
os.makedirs(data_dir + "/labels", exist_ok=True)

image_ids = []
for x in glob.glob(data_dir + '/annotations' + '/*.xml'):
    print(x)
    image_ids.append(os.path.basename(x)[:-4])
print('\n数量:', len(image_ids))  # 确认数量
i = 0
for image_id in image_ids:
    i = i + 1
    convert_annotation(data_dir, image_id)
    print("数据:%s/%s文件完成！" % (i, len(image_ids)))

print("Done!!!")