Cifar-10数据预处理andNearest Neighbor算法

*由于5万训练集以及1万测试集较大，运行程序时间较长
因此我们抽取了1/10的训练集
以及1/10的测试集
方便初学者理解*

更改后的代码

#coding=utf-8
#author='HL'
'''
利用pickle模块存储对象
dump类似于write
load类似于read
完成对象的上传以及读取
'''

import cPickle as pickle
import numpy as np


class NearestNeighbor(object):
    def __init__(self):
        pass

    def train(self,x,y):
        self.x_Tr = x
        self.y_Tr = y

    def predict(self,x):
        y_Pre = np.zeros(x.shape[0],dtype=type(self.y_Tr))

        for i in range(x.shape[0]):

            distance = np.sum(abs(self.x_Tr-x[i,]),axis=1)
            min_index = np.argmin(distance)
            y_Pre[i] = self.y_Tr[min_index]
        print y_Pre
        return y_Pre



def un_P(path):
    f = file(path,'rb')
    dict1 = pickle.load(f)
    f.close()
    return dict1


data_Train = []
labels_Train = []
path = "A:/python_test/cifar-10-batches-py/"
for i in range(1,6):
    now_Path = path+'data_batch_'+str(i)
    dict1 = un_P(now_Path)
    it  = 0
    while it <len(dict1['data']):
        data_Train.append(dict1['data'][it])
        labels_Train.append(dict1['labels'][it])
        it+=10
    '''
     for item in dict1['data']:
        data_Train.append(item)
    for item in dict1['labels']:
        labels_Train.append(item)
    '''



data_Test = []
labels_Test = []
dict1 = un_P(path+'test_batch')
for item in dict1['data'][:1000]:
    data_Test.append(item)
for item in dict1['labels'][:1000]:
    labels_Test.append(item)



data_Tr = np.asarray(data_Train)
data_Te = np.asarray(data_Test)
labels_Tr = np.asarray(labels_Train)
labels_Te = np.asarray(labels_Test)
print data_Tr.shape
print data_Te.shape
print labels_Tr.shape
print labels_Te.shape




zz = NearestNeighbor()
zz.train(data_Tr,labels_Train)
out = zz.predict(data_Te)
print  np.mean(out==labels_Te)

• 程序运行结果展示

---

原始代码

#coding=utf-8
#author='HL'
'''
利用pickle模块存储对象
dump类似于write
load类似于read
完成对象的上传以及读取
'''

import cPickle as pickle
import numpy as np

'''
算法部分
其实就是每个比较距离
找出最短的
然后判断就可以了
很简单
刚开始做 
纯粹练习
'''
class NearestNeighbor(object):
    def __init__(self):
        pass

    def train(self,x,y):
        self.x_Tr = x
        self.y_Tr = y

    def predict(self,x):
        y_Pre = np.zeros(x.shape[0],dtype=type(self.y_Tr))

        for i in range(x.shape[0]):
            distance = np.sum(abs(self.x_Tr-x[i,]),axis=1)
            min_index = np.argmin(distance)
            y_Pre[i] = self.y_Tr[min_index]
        return y_Pre



def un_P(path):
    f = file(path,'rb')
    dict1 = pickle.load(f)
    f.close()
    return dict1


data_Train = []
labels_Train = []
path = "A:/python_test/cifar-10-batches-py/"
for i in range(1,6):
    now_Path = path+'data_batch_'+str(i)
    dict1 = un_P(now_Path)
    for item in dict1['data']:
        data_Train.append(item)
    for item in dict1['labels']:
        labels_Train.append(item)


data_Test = []
labels_Test = []
dict1 = un_P(path+'test_batch')
for item in dict1['data']:
    data_Test.append(item)
for item in dict1['labels']:
    labels_Test.append(item)



data_Tr = np.asarray(data_Train)
data_Te = np.asarray(data_Test)
labels_Tr = np.asarray(labels_Train)
labels_Te = np.asarray(labels_Test)

print data_Tr
print data_Tr.shape
print data_Te
print data_Te.shape
print labels_Tr
print labels_Tr.shape
print labels_Te
print labels_Te.shape




zz = NearestNeighbor()
zz.train(data_Tr,labels_Train)
out = zz.predict(data_Te)
print  np.mean(out==labels_Te)

---