将数据集分成训练集和测试集

具体代码（带详细注释）

import os
import json
import random
import matplotlib.pyplot as plt

"""
假设数据集文件夹中有三类
class_indices.json
{
    "0": "AD",
    "1": "CN",
    "2": "MCI"
}
"""
def read_split_data(root: str, val_rate: float = 0.2):
    random.seed(0)  # 保证随机结果可复现
    assert os.path.exists(root), "dataset root: {} does not exist.".format(root)

    # 遍历文件夹，一个文件夹对应一个类别
    data_class = [cla for cla in os.listdir(root) if os.path.isdir(os.path.join(root, cla))]
    # 排序，保证各平台顺序一致
    data_class.sort()  # ['AD', 'CN', 'MCI']
    # 生成类别名称以及对应的数字索引
    class_indices = dict((k, v) for v, k in enumerate(data_class))
    json_str = json.dumps(dict((val, key) for key, val in class_indices.items()), indent=4)
    with open('class_indices.json', 'w') as json_file:
        json_file.write(json_str)

    train_images_path = []  # 存储训练集的所有图片路径
    train_images_label = []  # 存储训练集图片对应索引信息
    val_images_path = []  # 存储验证集的所有图片路径
    val_images_label = []  # 存储验证集图片对应索引信息
    every_class_num = []  # 存储每个类别的样本总数
    supported = [".jpg", ".JPG", ".png", ".PNG"]  # 支持的文件后缀类型
    # 遍历每个文件夹下的文件
    for cla in data_class:
        cla_path = os.path.join(root, cla) # 类别文件夹的具体路径
        # 遍历获取supported支持的所有文件路径
        images = [os.path.join(root, cla, i) for i in os.listdir(cla_path)
                  if os.path.splitext(i)[-1] in supported]
        # 排序，保证各平台顺序一致
        images.sort() # 该类别文件夹下的所有图片 按名称字典顺序排列
        # 获取该类别对应的索引
        image_class = class_indices[cla]
        # 记录该类别的样本数量
        every_class_num.append(len(images))
        # 按比例随机采样验证样本
        val_path = random.sample(images, k=int(len(images) * val_rate))

        for img_path in images:
            if img_path in val_path:  # 如果该路径在采样的验证集样本中则存入验证集
                val_images_path.append(img_path)
                val_images_label.append(image_class)
            else:  # 否则存入训练集
                train_images_path.append(img_path)
                train_images_label.append(image_class)

    print("{} images were found in the dataset.".format(sum(every_class_num)))
    print("{} images for training.".format(len(train_images_path)))
    print("{} images for validation.".format(len(val_images_path)))
    assert len(train_images_path) > 0, "number of training images must greater than 0."
    assert len(val_images_path) > 0, "number of validation images must greater than 0."

    plot_image = True
    if plot_image:
        # 绘制每种类别个数柱状图
        plt.bar(range(len(data_class)), every_class_num, align='center')
        # 将横坐标0,1,2,3,4替换为相应的类别名称
        plt.xticks(range(len(data_class)), data_class)
        # 在柱状图上添加数值标签
        for i, v in enumerate(every_class_num):
            plt.text(x=i, y=v + 5, s=str(v), ha='center')
        # 设置x坐标
        plt.xlabel('image class')
        # 设置y坐标
        plt.ylabel('number of images')
        # 设置柱状图的标题
        plt.title('data class distribution')
        plt.show()

    return train_images_path, train_images_label, val_images_path, val_images_label

data_path = "D:\data_set" # 数据集所在（绝对/相对）路径
train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(data_path)