统计xml文件信息--比赛数据分析

这部分先贴出分析类别的代码，后续会继续添加分析bbox的shape等的信息的代码

import os
import xml.etree.ElementTree as ET
from collections import Counter
import numpy as np

ann_path = '/训练集/Annotations/'
ann_list = os.listdir(ann_path)

img_num = len(ann_list)
cat = []

for xml in ann_list:
    xml_path = ann_path + xml
    tree = ET.parse(xml_path)
    root = tree.getroot()
    for object in root.findall('object'):
        object_name = object.find('name').text
        cat.append(object_name)
data_cls = dict(Counter(cat))
for key in data_cls.keys():
    print(key,':', data_cls[key])
print("图片总量：", img_num)