西瓜书课后题5.10(卷积神经网络)

题目

从网上下载或自己变成实现一个卷积神经网络，并在手写字符识别数据MNIST上进行试验测试。
代码直接从“python深度学习”这本书上copy下来的，用的是keras框架。以前看过，以后若有需要再细看这里的内容。

代码

from keras import layers
from keras import models
from keras.datasets import mnist
from keras.utils import to_categorical  # one-hot编码
# 获得数据
from keras.datasets import mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()


# 构造模型
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

# 处理数据
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

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

# 训练模型
model.fit(train_images, train_labels, epochs=5, batch_size=64)

# 测试集精度
test_loss, test_acc = model.evaluate(test_images, test_labels)
print(test_acc)

数据

模型

训练结果

测试结果