搭建CNN网络训练mnist数据集

1. 加载需要的包

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, optimizers, losses, datasets, Sequential
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D, GlobalMaxPool2D
from tensorflow.keras.optimizers import RMSprop
import matplotlib.pyplot as plt
import numpy as np

2. 载入数据集

# 将数据集载入，x_train为训练集数据,y_train为训练集标签，x_test为测试集数据,y_test为测试集标签
(x_train, y_train), (x_test, y_test) = mnist.load_data()

#数据集的变换
x_train = x_train.reshape(60000, 28, 28, 1)
x_test = x_test.reshape(10000, 28, 28, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255 #把数值变成0-1之间的浮点数。
x_test /=255
y_train = keras.utils.to_categorical(y_train, num_classes=10)
y_test = keras.utils.to_categorical(y_test, num_classes=10)

3. 搭建网络模型

# 构建CNN网络
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:])) # 卷积层
model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2))) # 最大池化层

model.add(Conv2D(64, (3, 3), padding='same')) # 卷积层
model.add(Activation('relu'))

model.add(GlobalMaxPool2D()) # 全局池化层

model.add(Flatten())

model.add(Dense(10)) # 全连接输出层
model.add(Activation('softmax'))
print(model.summary())
model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy'])

4. 模型训练

#模型训练
history = model.fit(x_train, y_train, 
                    batch_size=128, 
                    epochs=10, 
                    verbose=1, 
                    validation_data=(x_test, y_test))

5. 模型测试

# 模型测试
score = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', score[0])
print('Test accuracy:', score[1]) # 识别准确率

6. 训练过程可视化

# 绘制CNN网络训练过程中训练集和测试集合的准确率值
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()

# 绘制CNN网络训练过程中训练集和测试集合的损失值
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()