数据标注检查（一行是否有多出的数据造成无法训练）

 正常数据集存放的应该是5列数据，第一列类别，后四列为坐标值，如果在训练时候报数据集错误，可以尝试检查一下是不是每一个标注文件都是5列

 

 代码通过判断一行是否有大于4个 ‘  ’来进行判断，并输出有问题的txt名称

import os

folder_path = 'G:\CF-data\data_cfphone\labels-0'

def print_lines_with_spaces(file_path, threshold=4):
    with open(file_path, 'r', encoding='utf-8') as file:
        for line_number, line in enumerate(file, start=1):
            if line.startswith(' ' * threshold):
                print(f'{file_path}, Line {line_number}: {line.strip()}')

def process_folder(folder):
    for root, dirs, files in os.walk(folder):
        for file in files:
            if file.endswith('.txt'):
                file_path = os.path.join(root, file)
                print_lines_with_spaces(file_path)

if __name__ == "__main__":
    process_folder(folder_path)

import os

folder_path = 'G:\CF-data\data_cfphone\labels-0'

def print_lines_with_spaces(file_path, threshold=4):
    """
    打印文件中以指定个数空格开头的行信息
    :param file_path: 文件路径
    :param threshold: 空格个数的阈值，默认为4
    """
    with open(file_path, 'r', encoding='utf-8') as file:
        for line_number, line in enumerate(file, start=1):
            if line.startswith(' ' * threshold):
                print(f'{file_path}, Line {line_number}: {line.strip()}')

def process_folder(folder):
    """
    处理文件夹中的所有txt文件
    :param folder: 文件夹路径
    """
    for root, dirs, files in os.walk(folder):
        for file in files:
            if file.endswith('.txt'):
                file_path = os.path.join(root, file)
                print_lines_with_spaces(file_path)

if __name__ == "__main__":
    process_folder(folder_path)