《TensorFlow+Keras深度学习人工智能实践应用》林大贵著第八章代码

Keras卷积神经网络识别手写数字

卷积神经网络和多层感知机的差别就在于CNN多了卷积层和池化层，这两个层的层数可以自行设定，

和用多层感知机相比只有建立卷积层那里不同

from keras.datasets import mnist
from keras.utils import np_utils
import numpy as np
np.random.seed(10)

#读取数据
(x_Train,y_Train),(x_Test,y_Test)=mnist.load_data()
#将数字图像特征值转化为4D
x_Train4D=x_Train.reshape(x_Train.shape[0],28,28,1).astype('float32')
x_Test4D=x_Test.reshape(x_Test.shape[0],28,28,1).astype('float32')
#标准化
x_Train4D_normalize=x_Train4D/255
x_Test4D_normalize=x_Test4D/255
#标签的热码转换
y_TrainOneHot=np_utils.to_categorical(y_Train)
y_TestOneHot=np_utils.to_categorical(y_Test)

from keras.models import Sequential
from keras.layers import Dropout,Dense,Flatten,Conv2D,MaxPooling2D   #CNN中的层
model=Sequential()
#建立卷积层1
#16个滤镜，每个滤镜（5,5），卷积产生的图像大小不变，单色灰度图
model.add(Conv2D(filters=16,kernel_size=(5,5),padding='same',input_shape=(28,28,1),activation='relu'))
#建立池化层1
model.add(MaxPooling2D(pool_size=(2,2)))
#建立卷积层2
#36个滤镜，每个滤镜（5,5），卷积产生的图像大小不变，单色灰度图
model.add(Conv2D(filters=36,kernel_size=(5,5),padding='same',input_shape=(28,28,1),activation='relu'))
#建立池化层2
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))
#建立平坦层
model.add(Flatten())
#建立隐藏层
model.add(Dense(128,activation='relu'))
model.add(Dropout(0.5))
#建立输出层
model.add(Dense(10,activation='softmax'))#10个神经元，10个数字
print(model.summary())

 

#进行训练
#compile对训练模型进行设置
#loss为交叉熵，adam优化器，metrics模型评估的方式是准确率
model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
train_history=model.fit(x=x_Train4D_normalize,y=y_TrainOneHot,validation_split=0.2,
                        epochs=10,batch_size=300,verbose=2)

import matplotlib.pyplot as plt
def show_train_history(train_history,train,validation):
    plt.plot(train_history.history[train])
    plt.plot(train_history.history[validation])
    plt.title('train history')
    plt.xlabel('Epoch')
    plt.ylabel('train')
    plt.legend(['train','validation'],loc='upper left')
    plt.show()
show_train_history(train_history,'acc','val_acc')

show_train_history(train_history,'loss','val_loss')

#评估模型准确率
scores=model.evaluate(x_Test4D_normalize,y_TestOneHot)
print('accuracy=',scores[1])

#进行预测
prediction=model.predict_classes(x_Test4D_normalize)
prediction[:10]

def plot_images_labels_prediction(image,labels,prediction,idx,num=10):   
#num要显示的数据项数，默认为10，最大25
    fig=plt.gcf()
    fig.set_size_inches(12,14)
    if num>25:num=25
    for i in range(0,num):
        ax=plt.subplot(5,5,1+i)
        ax.imshow(image[idx],cmap='binary')
        title="label="+str(labels[idx])
        itle='label='+str(labels[idx])
        if(len(prediction)>0):
            title+=",prediction="+str(prediction[idx])
        ax.set_title(title,fontsize=10)
        ax.set_xticks([])
        ax.set_yticks([])
        idx+=1
    plt.show()
plot_images_labels_prediction(x_Test,y_Test,prediction,idx=0)

#建立混淆矩阵
import pandas as pd
pd.crosstab(y_Test,prediction,rownames=['label'], colnames=['predict'])