注意：下面代码主要针对两种不同的xml写的，根据自身情况修改（分别是labelimg、标注精灵两款标注工具）
#解决了一个xml多个标签问题
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
"""两种不同标准工具的xml转换为CSV（两种标注出来的xml格式不一样）"""
def xml_to_csv(path):
xml_list = []
a=0
print(glob.glob(path + '/*.xml'))
for xml_file in glob.glob(path + '/*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
a+=1
print("地址：{}".format(xml_file),"第{}个".format(a))
if root.findall('object'):##labelimg标注工具
print("labelimg")
for member in root.findall('object'):
print(root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][3].text))
# ('133.jpg', 416, 416, 'phone', 82, 54, 339, 197)
value = (root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][3].text)
)
xml_list.append(value)
# column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
# xml_df = pd.DataFrame(xml_list, columns=column_name)
# return xml_df
else:##标注精灵
print("标注精灵")
for member in root.findall("outputs/object/item"):#利用xpath解析方式，百度自行了解
if member[0].text=="1":#判断一个xml中有我不想要的隔离出来
continue
print(root.find('path').text.split("\\")[-1],
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
max(int(member[1][0].text),0),
max(int(member[1][1].text),0),
max(int(member[1][2].text),0),
max(int(member[1][3].text),0))
# # ('133.jpg', 416, 416, 'phone', 82, 54, 339, 197)
value = (root.find('path').text.split("\\")[-1],
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
max(int(member[1][0].text), 0),
max(int(member[1][1].text), 0),
max(int(member[1][2].text), 0),
max(int(member[1][3].text), 0)
)
xml_list.append(value)
# column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
xml_df = pd.DataFrame(xml_list, columns=column_name)
return xml_df
def main():
image_path = os.path.join('/home/hanqing/SSD-Tensorflow-master/VOC2019/', 'Annotations/test')#读取
xml_df = xml_to_csv(image_path)
xml_df.to_csv('/home/hanqing/SSD-Tensorflow-master/VOC2019/ImageSets/Main/csv/sj_test.csv', index=None)#保存
print('Successfully converted xml to csv.')
main()
