写出卷积神经网络python

卷积神经网络 (Convolutional Neural Network, CNN) 是一种常用的深度学习模型，用于图像分类、物体检测和其他计算机视觉任务。

下面是一个简单的 CNN 的 Python 代码示例：

import tensorflow as tf

# 定义卷积层
def conv_layer(inputs, filters, kernel_size, strides, padding, activation=tf.nn.relu):
    layer = tf.keras.layers.Conv2D(filters=filters, kernel_size=kernel_size, strides=strides, padding=padding)(inputs)
    if activation:
        layer = tf.keras.layers.Activation(activation)(layer)
    return layer

# 定义池化层
def pool_layer(inputs, pool_size, strides, padding):
    return tf.keras.layers.MaxPool2D(pool_size=pool_size, strides=strides, padding=padding)(inputs)

# 定义全连接层
def dense_layer(inputs, units, activation=tf.nn.relu):
    layer = tf.keras.layers.Dense(units=units)(inputs)
    if activation:
        layer = tf.keras.layers.Activation(activation)(layer)
    return layer

# 定义输入层
inputs = tf.keras.layers.Input(shape=(224, 224, 3))

# 定义卷积层和池化层
x = conv_layer(inputs, filters=32, kernel_size=3, strides=1, padding='same')
x = conv_layer(x, filters=32, kernel_size=3, strides=1, padding='same')
x = pool_layer(x, pool_size=2, strides=2, padding='valid')

# 定义更多的卷积层和池化层
x = conv_layer(x, filters=64, kernel_size=3, strides=1, padding='same')
x = conv_layer(x, filters=64, kernel_size=3, strides=1, padding='same')
x = pool_layer(x, pool_size=2, strides=2, padding='valid')

# 定义全连接层
x = dense_layer(x, units=1024)
x = dense_layer(x, units=1024)

# 定义输出层
outputs = dense_layer(x, units=10, activation=None)

# 创建