2023 数据集自动分配为训练集，测试集，验证集 过程讲解

准备工作

然后执行下面一段代码，需要修改的地方已经详细标注，只需要替换为自己的路径即可

import random
import os
import shutil

#    共有3处需要修改

#需要修改   1

#  修改训练集、验证集和测试集的比例分配
#  要分割的数据集数量要能被分配比例整除

train_percent = 0.8
test_percent = 0.1
valid_percent = 0.1


#需要修改  2

# 原始标注文件的路径（被分割的原始文件）
# 改成自己的路径
image_path = '.../.../images'
label_path = '.../.../labels'

images_files_list = os.listdir(image_path)
labels_files_list = os.listdir(label_path)
print('images files: {}'.format(images_files_list))
print('labels files: {}'.format(labels_files_list))


total_num = len(images_files_list)
print('total_num: {}'.format(total_num))

test_num = int(total_num * test_percent)
valid_num = int(total_num * valid_percent)
train_num = int(total_num * train_percent)

# 对应文件的索引
test_image_index = random.sample(range(total_num), test_num)
valid_image_index = random.sample(range(total_num), valid_num)
train_image_index = random.sample(range(total_num), train_num)


#需要修改  3

for i in range(total_num):
    print('src image: {}, i={}'.format(images_files_list[i], i))
    if i in test_image_index:

        #   '.../.../images/{}' 原始标注文件的路径（被分割的原始文件）  ,  '...../test/images/{}'分配后的文件存放的地点
        #   改成自己的路径
        shutil.copyfile('.../.../images/{}'.format(images_files_list[i]), '...../test/images/{}'.format(images_files_list[i]))
        shutil.copyfile('.../.../labels/{}'.format(labels_files_list[i]), '...../test/labels/{}'.format(labels_files_list[i]))
    elif i in valid_image_index:
        shutil.copyfile('.../.../images/{}'.format(images_files_list[i]), '...../valid/images/{}'.format(images_files_list[i]))
        shutil.copyfile('.../.../labels/{}'.format(labels_files_list[i]), '...../valid/labels/{}'.format(labels_files_list[i]))
    else:
        shutil.copyfile('.../.../images/{}'.format(images_files_list[i]), '...../train/images/{}'.format(images_files_list[i]))
        shutil.copyfile('.../.../labels/{}'.format(labels_files_list[i]), '...../train/labels/{}'.format(labels_files_list[i]))

 执行完成后，数据集已分配完毕