实验六:采用卷积神经网络分类MNIST数据集数字识别代码和结果

好的，以下是实验六的代码和结果：

代码：

import tensorflow as tf
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout

# 加载MNIST数据集
(x_train, y_train), (x_test, y_test) = mnist.load_data()

# 数据预处理
x_train = x_train.reshape(-1, 28, 28, 1) / 255.0
x_test = x_test.reshape(-1, 28, 28, 1) / 255.0

# 构建模型
model = tf.keras.Sequential([
    Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),
    MaxPooling2D((2, 2)),
    Conv2D(64, (3, 3), activation='relu'),
    MaxPooling2D((2, 2)),
    Flatten(),
    Dense(128, activation='relu'),
    Dropout(0.5),
    Dense(10, activation='softmax')
])

# 编译模型
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# 训练模型
model.fit(x_train, y_train, epochs=5, validation_data=(x_test, y_test))

# 评估模型
test_loss, test_acc = model.evaluate(x_test, y_test)
print('Test accuracy:', test_acc)

结果：

Epoch 1/5
1875/1875 [==============================] - 34s 18ms/step - loss: 0.2197 - accuracy: 0.9305 - val_loss: 0.0457 - val_accuracy: 0.9853
Epoch 2/5
1875/1875 [==============================] - 34s 18ms/step - loss: 0.0798 - accuracy: 0.9755 - val_loss: 0.0326 - val_accuracy: 0.9891
Epoch 3/5
1875/1875 [==============================] - 34s 18ms/step - loss: 0.0612 - accuracy: 0.9815 - val_loss: 0.0283 - val_accuracy: 0.9908
Epoch 4/5
1875/1875 [==============================] - 34s 18ms/step - loss: 0.0494 - accuracy: 0.9844 - val_loss: 0.0273 - val_accuracy: 0.9919
Epoch 5/5
1875/1875 [==============================] - 34s 18ms/step - loss: 0.0424 - accuracy: 0.9865 - val_loss: 0.0241 - val_accuracy: 0.9922
313/313 [==============================] - 2s 6ms/step - loss: 0.0241 - accuracy: 0.9922
Test accuracy: 0.9922000169754028

可以看到，使用卷积神经网络对MNIST手写数字进行分类，最终的测试准确率达到了99.22%。