如何在TensorFlow中加载下载的图像数据集(the300w_lp)？

import tensorflow as tf
import numpy as np

# 下载数据集并进行预处理

# 导入TensorFlow和相关库

# 加载图像数据集
image_paths = [...]  # 图像文件路径列表
labels = [...]  # 图像标签列表

# 创建数据集对象
dataset = tf.data.Dataset.from_tensor_slices((image_paths, labels))

# 数据集处理和转换
def preprocess_image(image_path, label):
    # 加载图像并进行预处理
    image = tf.io.read_file(image_path)
    image = tf.image.decode_jpeg(image, channels=3)
    image = tf.image.resize(image, [224, 224])
    image = tf.cast(image, tf.float32) / 255.0  # 数据标准化
    return image, label

dataset = dataset.map(preprocess_image)

# 数据集划分
train_size = int(0.8 * len(image_paths))
train_dataset = dataset.take(train_size)
test_dataset = dataset.skip(train_size)

# 数据集迭代
train_iterator = train_dataset.make_one_shot_iterator()
test_iterator = test_dataset.make_one_shot_iterator()

# 获取每个批次的数据
batch_size = 32
train_batch = train_iterator.get_next()
test_batch = test_iterator.get_next()

# 在训练模型时使用train_batch和test_batch进行迭代训练和测试