如何使用tensorflow成对导入jpg和npy文件进行深度学习？

import tensorflow as tf
import numpy as np
import os

def read_jpg(file_path):
    image = tf.io.read_file(file_path)
    image = tf.image.decode_jpeg(image, channels=3)
    image = tf.image.convert_image_dtype(image, tf.float32)
    return image

def read_npy(file_path):
    data = np.load(file_path)
    return data

def process_data(image, data):
    # 在这里进行数据预处理，例如调整图像大小、归一化等操作
    # 返回处理后的图像和数据
    return processed_image, processed_data

def load_dataset(image_dir, data_dir):
    image_files = os.listdir(image_dir)
    data_files = os.listdir(data_dir)
    dataset = tf.data.Dataset.from_tensor_slices((image_files, data_files))
    dataset = dataset.map(lambda x, y: (read_jpg(os.path.join(image_dir, x)), read_npy(os.path.join(data_dir, y))))
    dataset = dataset.map(process_data)
    return dataset

image_dir = 'path/to/image/directory'
data_dir = 'path/to/npy/directory'
batch_size = 32
shuffle_buffer_size = 1000

dataset = load_dataset(image_dir, data_dir)
dataset = dataset.shuffle(shuffle_buffer_size).batch(batch_size)

model = tf.keras.Sequential(...)
model.compile(...)
model.fit(dataset, epochs=num_epochs)