概念
搭建神经网络块是一种常见的做法，它可以帮助你更好地组织和复用网络结构。神经网络块可以是一些相对独立的模块，例如卷积块、全连接块等，用于构建更复杂的网络架构。
代码实现
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers# 定义一个卷积块
def convolutional_block(x, num_filters, kernel_size, pool_size):x = layers.Conv2D(num_filters, kernel_size, activation='relu', padding='same')(x)x = layers.MaxPooling2D(pool_size)(x)return x# 构建神经网络模型
def build_model():inputs = layers.Input(shape=(28, 28, 1)) # 输入数据为28x28的灰度图像x = convolutional_block(inputs, num_filters=32, kernel_size=(3, 3), pool_size=(2, 2))x = convolutional_block(x, num_filters=64, kernel_size=(3, 3), pool_size=(2, 2))x = layers.Flatten()(x)x = layers.Dense(128, activation='relu')(x)outputs = layers.Dense(10, activation='softmax')(x) # 输出层，10个类别model = keras.Model(inputs, outputs)return model# 加载数据
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = np.expand_dims(x_train, axis=-1).astype('float32') / 255.0
x_test = np.expand_dims(x_test, axis=-1).astype('float32') / 255.0
y_train = keras.utils.to_categorical(y_train, num_classes=10)
y_test = keras.utils.to_categorical(y_test, num_classes=10)# 构建模型
model = build_model()# 编译模型
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])# 训练模型
model.fit(x_train, y_train, batch_size=64, epochs=10, validation_split=0.1)# 评估模型
test_loss, test_accuracy = model.evaluate(x_test, y_test)
print("Test Loss:", test_loss)
print("Test Accuracy:", test_accuracy)
)
 ？)
)
