keras例子之Mnist案例

最新推荐文章于 2020-02-26 10:11:37 发布

原创最新推荐文章于 2020-02-26 10:11:37 发布 · 1.2k 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#keras #mnist #卷积神经网络

数据挖掘同时被 2 个专栏收录

20 篇文章

订阅专栏

机器学习

16 篇文章

订阅专栏

本文介绍了一个使用卷积神经网络(CNN)进行MNIST手写数字识别的例子。该模型包含多个卷积层、池化层及全连接层，并通过RMSprop优化器训练。实验结果显示，此模型在MNIST数据集上取得了良好的识别准确率。

#-*- coding: utf-8 -*-

"""
mnist识别例子,使用卷积神经网络
"""

import os
import sys
import time
import numpy as np
from keras.datasets import mnist
from keras.optimizers import SGD,RMSprop
from keras.utils import np_utils
from keras.models import Sequential
import keras.backend as K
from keras.models import load_model
from numpy import newaxis
import matplotlib.pyplot as plt
from keras.layers import Dense,Activation,Dropout,Conv2D,Flatten,MaxPool2D,Input,Conv1D
np.random.seed(1337)
reload(sys)
sys.setdefaultencoding('utf-8')




def loadMnistData():
    (x_train,y_train),(x_test,y_test)=mnist.load_data()
    x_train=x_train.astype('float32')
    x_test = x_test.astype('float32')
    y_train=np_utils.to_categorical(y_train,10)
    y_test = np_utils.to_categorical(y_test, 10)
    print np.shape(x_train), np.shape(x_test)
    return x_train,y_train,x_test,y_test

def buildModel(x_train, y_train, x_test, y_test):
    print K.image_data_format()
    if K.image_data_format()=='channels_first':
        x_train = x_train.reshape(60000, 1,28, 28)
        x_test = x_test.reshape(10000, 1, 28, 28)
        input_shape=(1,28,28)
    else:
        x_train = x_train.reshape(60000,28, 28,1)
        x_test = x_test.reshape(10000,28, 28,1)
        input_shape=(28,28,1)
    print K.backend(),input_shape
    model = Sequential()
    model.add(Conv2D(input_shape=input_shape,filters=32,kernel_size=(2,2)))
    model.add(Activation('relu'))
    model.add(MaxPool2D(pool_size=(2,2)))
    model.add(Dropout(0.2))

    model.add(Conv2D(filters=64, kernel_size=(3, 3)))
    model.add(Activation('relu'))
    model.add(MaxPool2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    print model.output_shape

    model.add(Flatten())

    model.add(Dense(128))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))

    model.add(Dense(10))
    model.add(Activation('softmax'))
    model.compile(optimizer=RMSprop(),loss='categorical_crossentropy',metrics=['accuracy'])

    model.fit(x_train,y_train,epochs=15,batch_size=128,verbose=1,validation_data=(x_test,y_test))
    score=model.evaluate(x_test,y_test,verbose=0)
    print('Test score:', score[0])
    print('Test accuracy:', score[1])


if __name__=="__main__":
    x_train, y_train, x_test, y_test=loadMnistData()
    buildModel(x_train, y_train, x_test, y_test)