Keras多层感知机识别MNIST数据集

#windows 10, python=3.5

import numpy as np
import pandas as pd
from keras.utils import np_utils
from keras.datasets import mnist
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
np.random.seed(10)

#导入数据集mnist
(x_train_image, y_train_label), \
(x_test_image, y_test_label) =  mnist.load_data()

#函数：显示原图片、预测值、label值
def plot_images_labels_prediction(images,labels,prediction,idx,num=10):
    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(images[idx], cmap='binary')
        title = 'label=' +str(labels[idx])
        if len(prediction)>0:
            title+=',predict='+str(prediction[idx])
        ax.set_title(title,fontsize=10)
        ax.set_xticks([]),ax.set_yticks([])
        idx+=1
    plt.show()

#将图片矩阵数据转为单行数据
x_train = x_train_image.reshape(60000, 784).astype('float32')
x_test = x_test_image.reshape(10000, 784).astype('float32')

#标准化
x_train_normalize = x_train/255
x_test_normalize = x_test/255

#将标签值转换为OneHot Encoding
y_trainOneHot = np_utils.to_categorical(y_train_label)
y_testOneHot = np_utils.to_categorical(y_test_label)

#利用kares构建模型，两个1000个神经元的隐藏层，并忽略百分之五十的神经元避免过拟合
model = Sequential()
model.add(Dense(units=1000,
               input_dim=784,
               activation='relu'
               ))
model.add(Dropout(0.5))
model.add(Dense(units=1000,
               activation='relu'
               ))
model.add(Dropout(0.5))
model.add(Dense(units=10,
               activation='softmax'))
print(model.summary())

#设置损失函数、优化器
model.compile(loss='categorical_crossentropy',
             optimizer ='adam',metrics=['accuracy'])

#开始训练
train_history = model.fit(x=x_train_normalize,
                       y=y_trainOneHot, validation_split=0.2,
                       epochs=10, batch_size=200, verbose=2)

#函数：显示训练数据
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.ylabel(train)
    plt.xlabel('Epoch')
    plt.legend(['train','validation'],loc='upper left')
    plt.show()

#显示训练过程中得准确度、损失值
show_train_history(train_history, 'acc', 'val_acc')
show_train_history(train_history, 'loss', 'val_loss')

#测试集测试准确率
scores = model.evaluate(x_test_normalize, y_testOneHot)

#混淆矩阵
prediction = model.predict_classes(x_test)
pd.crosstab(y_test_label,prediction,
           rownames=['label'], colnames=['predict'])