You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
24 lines
873 B
24 lines
873 B
import os
|
|
import shutil
|
|
import pandas as pd
|
|
|
|
# 读取包含索引和标签的数据文件
|
|
df = pd.read_csv('data/data.csv', encoding='GBK')
|
|
|
|
# 设置原始文件夹路径和目标文件夹路径
|
|
source_folder = 'data/train' # 原始文件夹路径
|
|
target_folder = 'data_classification/train' # 目标文件夹路径
|
|
|
|
# 遍历 DataFrame
|
|
for index, row in df.iterrows():
|
|
file_index = row['索引'] # 索引对应的列名
|
|
file_label = row['标签'] # 标签对应的列名
|
|
|
|
source_file = os.path.join(source_folder, f'{file_index}.jpg') # 原始文件路径
|
|
target_folder_label = os.path.join(target_folder, str(file_label)) # 目标文件夹路径
|
|
|
|
# 创建对应标签的目标文件夹（如果不存在）
|
|
os.makedirs(target_folder_label, exist_ok=True)
|
|
|
|
# 复制文件到目标文件夹
|
|
shutil.copy(source_file, target_folder_label) |