比较图片和标签文件个数是否一致，并将多余的移动到另外的文件夹

最新推荐文章于 2024-07-12 10:21:37 发布

Junsun Chen

最新推荐文章于 2024-07-12 10:21:37 发布

阅读量190

点赞数 3

文章标签： windows microsoft 服务器

本文链接：https://blog.csdn.net/TYHsunflower/article/details/140163533

版权

# 图片文件夹和标签文件夹对比

# -*- coding: utf-8 -*-
import os
import shutil

# # path1和path2分别列出两个文件夹路径，自己根据情况更换
# path1 = r'/home/qq/Downloads/vota/image/train2017/images'   #图片的
# path2 = r'/home/qq/Downloads/vota/image/train2017/labelTxt'#txt的
# path3duoyu = r'/media/qq/work/drone/test/testxml'
# path1和path2分别列出两个文件夹路径，自己根据情况更换
path1 = r'/media/qq/work/drone/test/labels'
path2 = r'/media/qq/work/drone/test/testxml'
path3duoyu = r'/media/qq/work/drone/test/duoyu'


def file_name(image_dir, xml_dir):
    jpg_list = []
    xml_list = []
    for root, dirs, files in os.walk(image_dir):
        for file in files:
            jpg_list.append(os.path.splitext(file)[0])
    for root, dirs, files in os.walk(xml_dir):
        for file in files:
            xml_list.append(os.path.splitext(file)[0])
    print(len(jpg_list))
    diff = set(xml_list).difference(set(jpg_list))  # 差集，在 txt 中但不在 jpg  中的元素
    for name in diff:
        # print("no jpg", name + ".txt")#需修改　　path2对应的文件后缀　
        # namecs = name + ".txt"
        print("no jpg", name + ".xml")#需修改　　path2对应的文件后缀　
        namecs = name + ".xml"
        shutil.move(os.path.join(path2, namecs), path3duoyu)

    diff2 = set(jpg_list).difference(set(xml_list))  # 差集，在jpg中但不在txt中的元素
    print(len(diff2))
    for name in diff2:
        # print("no xml", name + ".jpg")#需修改　　path１对应的文件后缀
        # namecs = name + ".jpg"
        print("no xml", name + ".txt")  # 需修改　　path１对应的文件后缀
        namecs = name + ".txt"
        shutil.move(os.path.join(path1, namecs), path3duoyu)


if __name__ == '__main__':
    file_name(path1, path2)
# ————————————————

#                             版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

# 原文链接：https://blog.csdn.net/m0_46653805/article/details/129838221