MNIST逻辑回归实现

先放代码

import os
import struct
import numpy as np
import matplotlib.pyplot as plt
import gzip
import tempfile
import random
import tensorflow as tf

#*****************************************************************************************
#从文件中读入数据

def load_mnist(labels_path,images_path):
    """Load MNIST data from `path`"""
    with open(labels_path, 'rb') as lbpath:
        magic, n = struct.unpack('>II',
                                 lbpath.read(8))
        labels = np.fromfile(lbpath,
                             dtype=np.uint8)

    with open(images_path, 'rb') as imgpath:
        magic, num, rows, cols = struct.unpack('>IIII',
                                               imgpath.read(16))
        images = np.fromfile(imgpath,
                             dtype=np.uint8).reshape(len(labels), 784)

    return images, labels

train_labels_path = 'C:/Users/cxt66/Desktop/MNISTdata/MNISTdata/train-labels.idx1-ubyte'
train_images_path = 'C:/Users/cxt66/Desktop/MNISTdata/MNISTdata/train-images.idx3-ubyte'
test_labels_path = 'C:/Users/cxt66/Desktop/MNISTdata/MNISTdata/t10k-labels.idx1-ubyte'
test_images_path = 'C:/Users/cxt66/Desktop/MNISTdata/MNISTdata/t10k-images.idx3-ubyte'
(train_images,train_labels)= load_mnist(train_labels_path,train_images_path)
(test_images,test_labels)= load_mnist(test_labels_path,test_images_path)
#************************************************************************************************
#对数据进行转化，使其符合格式

def transfer(labels,number):#对labels进行转化，从单个数字变成one-hot向量
    final_labels=[]
    for i in range(number):
        if(labels[i] == 0):
            label = [1.0,0,0,0,0,0,0,0,0,0]
        elif(labels[i] == 1):
            label = [0,1,0,0,0,0,0,0,0,0]
        elif(labels[i] == 2):
            label = [0,0,1,0,0,0,0,0,0,0]
        elif(labels[i] == 3):
            label = [0,0,0,1,0,0,0,0,0,0]
        elif(labels[i] == 4):
            label = [0,0,0,0,1,0,0,0,0,0]
        elif(labels[i] == 5):
            label = [0,0,0,0,0,1,0,0,0,0]
        elif(labels[i] == 6):
            label = [0,0,0,0,0,0,1,0,0,0]
        elif(labels[i] == 7):
            label = [0,0,0,0,0,0,0,1,0,0]
        elif(labels[i] == 8):
            label = [0,0,0,0,0,0,0,0,1,0]
        else:
            label = [0,0,0,0,0,0,0,0,0,1]
        final_labels.append(label)
    return final_labels

train_new_images = train_images.astype(dtype = np.float)/255
test_new_images = test_images.astype(dtype = np.float)/255

test_new_labels = np.array(transfer(test_labels,10000)).astype(dtype = np.float)
train_new_labels = np.array(transfer(train_labels,60000)).astype(dtype = np.float)

#********************************************************************************
#训练核心代码
def next_batch(number):
    i = random.randrange(0,59899)
    batch_xs = train_new_images[i:i+number]
    batch_ys = train_new_labels[i:i+number]
    return batch_xs,batch_ys

x = tf.placeholder(tf.float32,[None,784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W)+b)
y_ = tf.placeholder("float",[None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for i in range(10000):
    batch_xs,batch_ys = next_batch(100)
    print('loss',sess.run(cross_entropy,feed_dict = {x: batch_xs,y_: batch_ys}))                                                      
    sess.run(train_step,feed_dict = {x: batch_xs,y_: batch_ys})

#********************************
#结果检验
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print(sess.run(accuracy, feed_dict={x:test_new_images, y_: test_new_labels}))

 

 

 这个是在极客学院的入门代码上改的。

因为没法直接下载到解数据的函数，只能自己写。

可以从网上找到压缩包，解压之后是这样的

四个ubyte文件

然后用第一段的函数读进来，再用第二段的函数转成标准数据流。

第三段是核心的训练过程，第四段是用测试集来进行检验。

原文地址：

http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_beginners.html

作为刚转专业过来，还没入门的小菜鸟，表示写一写很头痛，又很开心，遇到好多问题，慢慢的都解决掉了，希望以后能再接再厉。