keras入门 利用卷积神经网络进行手写数字识别

# -*- coding: utf-8 -*-
"""
Created on Tue Nov 21 16:22:40 2017

@author: www
"""
#利用卷积神经网络进行手写数字识别



from keras.models import Sequential
from keras.layers import Dense,Dropout,Flatten
from keras.layers.convolutional import Conv2D,MaxPooling2D
from keras.datasets import mnist
import numpy as np

def load_data():
    (X_train,y_train),(X_test,y_test) = mnist.load_data()
    return X_train,y_train,X_test,y_test
#print(X_train[0].shape)
#print(y_train[0])


def preprocessing(data_x):
#把训练集中数据变为标准的思维张量形式，并把像素变成浮点型
#归一化
#返回值：DatraFrame
    data_x = data_x.reshape(data_x.shape[0],28,28,1).astype('float32')
    data_x /= 255
    return data_x

    
def train_y(y):
#说明：哑编码
#参数：
    y_one = np.zeros(10)
    y_one[y] = 1
    return y_one
    
def model(X_train, y_train_one, X_test,y_test_one):
    model = Sequential()
    model.add(Conv2D(64, kernel_size=(3, 3), strides=(1, 1),
                     padding='same', input_shape=(28,28,1), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(0.5))
    model.add(Conv2D(128, kernel_size=(3,3), strides=(1,1), 
                     padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(0.5))
    model.add(Conv2D(256, kernel_size=(3,3), strides=(1,1), 
                     padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(0.5))
    
    model.add(Flatten())
    
    model.add(Dense(128, activation='relu'))
    model.add(Dense(64,  activation='relu'))
    model.add(Dense(32,  activation='relu'))
    model.add(Dense(10,  activation='softmax'))
    
    model.compile(loss = 'categorical_crossentropy', optimizer='adagrad', metrics=['accuracy'])
    model.fit(X_train,y_train_one, validation_data=(X_test,y_test_one),
          epochs = 20,batch_size = 128)

    scores = model.evaluate(X_test, y_test_one, verbose=0)
    return scores

    
def main():
    X_train,y_train,X_test,y_test = load_data()
    
    X_train = preprocessing(X_train)
    X_test = preprocessing(X_test)
    
    y_train_one = np.array([train_y(y_train[i]) for i in range(len(y_train))])
    y_test_one  = np.array([train_y(y_test[i] ) for i in range(len(y_test))])

    scores = model(X_train, y_train_one,  X_test,y_test_one)
    print(scores)

main()


    

注：以上由于机器原因，代码没有跑完。所以我也不清楚准确率。。。