CV项目——遍历文件夹下标签txt文件统计各属性图片张数和标签个数

import os

path = "../data_labels/"  # to change
txt_files= os.listdir(path)  #得到文件夹下的所有文件名称
txt_files = [x for x in txt_files if x.endswith('.txt')]
label_image_count_dict = dict()  # 每个 label 出现的图片个数
label_count_dict = dict()  # 每个 label 出现多少次

# todo: 每个 label, 保存一张出现这个 label 的图

for file in txt_files:  #遍历文件夹

    abs_txt_file = os.path.join(path, file)
    tmp_label_set = set()  # 记录当前标注文档出现的 label
    print(abs_txt_file)
    with open(abs_txt_file, "r",encoding='utf-8') as f:  #打开文件
        for line in f.readlines():
            split_line = line.split()
            if len(split_line) == 5:
                tmp_label = split_line[0]
                tmp_label_set.add(tmp_label)
                if tmp_label not in label_count_dict:
                    label_count_dict[tmp_label] = 0
                label_count_dict[tmp_label] = label_count_dict[tmp_label] + 1
    for y in tmp_label_set:
        if y not in label_image_count_dict:
            label_image_count_dict[y] = 0
        label_image_count_dict[y] = label_image_count_dict[y] + 1

print(label_image_count_dict)
print(label_count_dict)

本文地址：https://blog.csdn.net/mndlgzzd/article/details/107358891