現(xiàn)在的許多手寫字體識別代碼都是基于已有的mnist手寫字體數據集進行的，而kaggle需要用到網站上給出的數據集并生成測試集的輸出用于提交。這里選擇keras搭建卷積網絡進行識別，可以直接生成測試集的結果,最終結果識別率大概97%左右的樣子。

創(chuàng)新互聯(lián)專注于做網站、成都網站設計、網頁設計、網站制作、網站開發(fā)。公司秉持“客戶至上,用心服務”的宗旨,從客戶的利益和觀點出發(fā),讓客戶在網絡營銷中找到自己的駐足之地。尊重和關懷每一位客戶，用嚴謹的態(tài)度對待客戶，用專業(yè)的服務創(chuàng)造價值，成為客戶值得信賴的朋友，為客戶解除后顧之憂。

# -*- coding: utf-8 -*-
"""
Created on Tue Jun 6 19:07:10 2017

@author: Administrator
"""

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten 
from keras.layers import Convolution2D, MaxPooling2D 
from keras.utils import np_utils
import os
import pandas as pd
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
from keras import backend as K
import tensorflow as tf

# 全局變量 
batch_size = 100 
nb_classes = 10 
epochs = 20
# input image dimensions 
img_rows, img_cols = 28, 28 
# number of convolutional filters to use 
nb_filters = 32 
# size of pooling area for max pooling 
pool_size = (2, 2) 
# convolution kernel size 
kernel_size = (3, 3) 

inputfile='F:/data/kaggle/mnist/train.csv'
inputfile2= 'F:/data/kaggle/mnist/test.csv'
outputfile= 'F:/data/kaggle/mnist/test_label.csv'


pwd = os.getcwd()
os.chdir(os.path.dirname(inputfile)) 
train= pd.read_csv(os.path.basename(inputfile)) #從訓練數據文件讀取數據
os.chdir(pwd)

pwd = os.getcwd()
os.chdir(os.path.dirname(inputfile)) 
test= pd.read_csv(os.path.basename(inputfile2)) #從測試數據文件讀取數據
os.chdir(pwd)

x_train=train.iloc[:,1:785] #得到特征數據
y_train=train['label']
y_train = np_utils.to_categorical(y_train, 10)

mnist=input_data.read_data_sets("MNIST_data/",one_hot=True) #導入數據
x_test=mnist.test.images
y_test=mnist.test.labels
# 根據不同的backend定下不同的格式 
if K.image_dim_ordering() == 'th': 
 x_train=np.array(x_train)
 test=np.array(test)
 x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols) 
 x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols) 
 input_shape = (1, img_rows, img_cols) 
 test = test.reshape(test.shape[0], 1, img_rows, img_cols) 
else: 
 x_train=np.array(x_train)
 test=np.array(test)
 x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1) 
 X_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1) 
 test = test.reshape(test.shape[0], img_rows, img_cols, 1) 
 input_shape = (img_rows, img_cols, 1) 

x_train = x_train.astype('float32') 
x_test = X_test.astype('float32') 
test = test.astype('float32') 
x_train /= 255 
X_test /= 255
test/=255 
print('X_train shape:', x_train.shape) 
print(x_train.shape[0], 'train samples') 
print(x_test.shape[0], 'test samples') 
print(test.shape[0], 'testOuput samples') 

model=Sequential()#model initial
model.add(Convolution2D(nb_filters, (kernel_size[0], kernel_size[1]), 
      padding='same', 
      input_shape=input_shape)) # 卷積層1 
model.add(Activation('relu')) #激活層 
model.add(Convolution2D(nb_filters, (kernel_size[0], kernel_size[1]))) #卷積層2 
model.add(Activation('relu')) #激活層 
model.add(MaxPooling2D(pool_size=pool_size)) #池化層 
model.add(Dropout(0.25)) #神經元隨機失活 
model.add(Flatten()) #拉成一維數據 
model.add(Dense(128)) #全連接層1 
model.add(Activation('relu')) #激活層 
model.add(Dropout(0.5)) #隨機失活 
model.add(Dense(nb_classes)) #全連接層2 
model.add(Activation('softmax')) #Softmax評分 

#編譯模型 
model.compile(loss='categorical_crossentropy', 
    optimizer='adadelta', 
    metrics=['accuracy']) 
#訓練模型 

model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs,verbose=1) 
model.predict(x_test)
#評估模型 
score = model.evaluate(x_test, y_test, verbose=0) 
print('Test score:', score[0]) 
print('Test accuracy:', score[1]) 

y_test=model.predict(test)

sess=tf.InteractiveSession()
y_test=sess.run(tf.arg_max(y_test,1))
y_test=pd.DataFrame(y_test)
y_test.to_csv(outputfile)

文章標題：kaggle+mnist實現(xiàn)手寫字體識別-創(chuàng)新互聯(lián)
分享網址：http://www.chinadenli.net/article40/djhseo.html

成都網站建設公司_創(chuàng)新互聯(lián)，為您提供手機網站建設、移動網站建設、域名注冊、云服務器、定制網站、網頁設計公司

廣告

聲明：本網站發(fā)布的內容（圖片、視頻和文字）以用戶投稿、用戶轉載內容為主，如果涉及侵權請盡快告知，我們將會在第一時間刪除。文章觀點不代表本網站立場，如需處理請聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內容未經允許不得轉載，或轉載時需注明來源： 創(chuàng)新互聯(lián)