教育领域“知之”大模型--山东大学软件学院2024年项目实训（四）

 维基百科中爬取的数据集：

代码如下：

import os
import requests
from bs4 import BeautifulSoup

# 设置要爬取的维基百科页面
wiki_page = "https://en.wikipedia.org/wiki/ImageNet"

# 创建用于保存图片的目录
dataset_dir = "wiki_image_dataset"
os.makedirs(dataset_dir, exist_ok=True)

# 发送 HTTP 请求获取页面内容
response = requests.get(wiki_page)
html_content = response.content

# 使用 BeautifulSoup 解析 HTML 内容
soup = BeautifulSoup(html_content, "html.parser")

# 查找页面中的所有图片链接
img_tags = soup.find_all("img")

# 遍历图片链接,下载并保存图片
for i, img_tag in enumerate(img_tags):
    img_src = img_tag.get("src")
    if img_src.startswith("//"):
        img_src = "https:" + img_src

    # 构建图片文件名
    img_filename = os.path.join(dataset_dir, f"image_{i}.jpg")

    # 下载并保存图片
    img_response = requests.get(img_src)
    with open(img_filename, "wb") as f:
        f.write(img_response.content)

    print(f"Downloaded and saved image: {img_filename}")

print(f"Total {len(img_tags)} images have been saved to the '{dataset_dir}' directory.")

将维基百科中的数据集划分为训练集测试集验证集合

代码如下：

import random
from shutil import copy2


def data_set_split(src_data_folder, target_data_folder, train_scale=0.8, val_scale=0.0, test_scale=0.2):
    '''
    读取源数据文件夹，生成划分好的文件夹，分为trian、val、test三个文件夹进行
    :param src_data_folder: 源文件夹
    :param target_data_folder: 目标文件夹
    :param train_scale: 训练集比例
    :param val_scale: 验证集比例
    :param test_scale: 测试集比例
    :return:
    '''
    print("开始数据集划分")
    class_names = os.listdir(src_data_folder)
    # 在目标目录下创建文件夹
    split_names = ['train', 'val', 'test']
    for split_name in split_names:
        split_path = os.path.join(target_data_folder, split_name)
        if os.path.isdir(split_path):
            pass
        else:
            os.mkdir(split_path)
        # 然后在split_path的目录下创建类别文件夹
        for class_name in class_names:
            class_split_path = os.path.join(split_path, class_name)
            if os.path.isdir(class_split_path):
                pass
            else:
                os.mkdir(class_split_path)

    # 按照比例划分数据集，并进行数据图片的复制
    # 首先进行分类遍历
    for class_name in class_names:
        current_class_data_path = os.path.join(src_data_folder, class_name)
        current_all_data = os.listdir(current_class_data_path)
        current_data_length = len(current_all_data)
        current_data_index_list = list(range(current_data_length))
        random.shuffle(current_data_index_list)

        train_folder = os.path.join(os.path.join(target_data_folder, 'train'), class_name)
        val_folder = os.path.join(os.path.join(target_data_folder, 'val'), class_name)
        test_folder = os.path.join(os.path.join(target_data_folder, 'test'), class_name)
        train_stop_flag = current_data_length * train_scale
        val_stop_flag = current_data_length * (train_scale + val_scale)
        current_idx = 0
        train_num = 0
        val_num = 0
        test_num = 0
        for i in current_data_index_list:
            src_img_path = os.path.join(current_class_data_path, current_all_data[i])
            if current_idx <= train_stop_flag:
                copy2(src_img_path, train_folder)
                # print("{}复制到了{}".format(src_img_path, train_folder))
                train_num = train_num + 1
            elif (current_idx > train_stop_flag) and (current_idx <= val_stop_flag):
                copy2(src_img_path, val_folder)
                # print("{}复制到了{}".format(src_img_path, val_folder))
                val_num = val_num + 1
            else:
                copy2(src_img_path, test_folder)
                # print("{}复制到了{}".format(src_img_path, test_folder))
                test_num = test_num + 1

            current_idx = current_idx + 1

        print("*********************************{}*************************************".format(class_name))
        print(
            "{}类按照{}：{}：{}的比例划分完成，一共{}张图片".format(class_name, train_scale, val_scale, test_scale,
                                                                 current_data_length))
        print("训练集{}：{}张".format(train_folder, train_num))
        print("验证集{}：{}张".format(val_folder, val_num))
        print("测试集{}：{}张".format(test_folder, test_num))


if __name__ == '__main__':
    src_data_folder = r"D:\Chinese Medicine"  # todo 原始数据集目录
    target_data_folder = r"D:\1"  # todo 数据集分割之后存放的目录
    data_set_split(src_data_folder, target_data_folder)