得到xml所有label 名字和数量 get_xml_lab.py,get_json_lab.py

import os
import xml.etree.ElementTree as ET

rootdir2 = r"F:\images3\xmls"
file_list = os.listdir(rootdir2)  # 列出文件夹下所有的目录与文件

# 初始化字典
classes_dict = {}

for file_name in file_list:
    path = os.path.join(rootdir2, file_name)
    if os.path.isfile(path):
        # 解析XML文件
        tree = ET.parse(path)
        root = tree.getroot()

        # 获取所有object标签中的name子标签
        for obj in root.findall('object'):
            name = obj.find('name').text
            if name not in classes_dict:
                classes_dict[name] = 1
            else:
                classes_dict[name] += 1

# 打印统计结果
for k, v in classes_dict.items():
    print(k, v)
print(classes_dict.keys())

print("图片总数：", len(file_list))

import os
import json

rootdir2 = r"F:\images3\jsons"
file_list = os.listdir(rootdir2)  # 列出文件夹下所有的目录与文件

# 初始化字典
label_count = {}

for file_name in file_list:
    path = os.path.join(rootdir2, file_name)
    if os.path.isfile(path) and path.endswith('.json'):
        # 打开并读取JSON文件
        with open(path, 'r', encoding='utf-8') as f:
            data = json.load(f)
        
        # 遍历shapes列表中的所有对象并统计label
        if 'shapes' in data:
            for shape in data['shapes']:
                label = shape.get('label')
                if label:
                    if label not in label_count:
                        label_count[label] = 1
                    else:
                        label_count[label] += 1

# 打印统计结果
for k, v in label_count.items():
    print(k, v)
print(label_count.keys())

print("文件总数：", len(file_list))