MNIST预测手写数字图片的数据处理

引用部分代码:https://blog.csdn.net/simple_the_best/article/details/75267863

# -*- coding: utf-8 -*-
import tensorflow as tf
import os
import struct
import numpy as np
import matplotlib.pyplot as plt

#数据处理
"""
60000行的训练数据集（mnist.train）和10000行的测试数据集（mnist.test）。
一张包含手写数字的图片mnist.train.images 和一个对应的标签 mnist.train.labels。

mnist.train.images[60000, 784] 
mnist.train.images[1至60000张的图片索引, 每张图片中的像素点] 
每一张图片包含28X28个像素点,总共784个像素点,
文件 = 'train-images.idx3-ubyte'

mnist.train.labels[60000, 10]
mnist.train.labels[1至60000张的图片索引, 每张图片中表示的数字] 
数字n将表示成一个只有在第n维度（从0开始）数字为1的10维向量。
比如，标签0将表示成([1,0,0,0,0,0,0,0,0,0,0])。
文件 = train-labels.idx1-ubyte
"""

train_images_path =r'D:\MNIST_data\train-images.idx3-ubyte'
train_labels_path =r'D:\MNIST_data\train-labels.idx1-ubyte'


train_images=[]  #=mnist.train.images
train_labels=[]  #=mnist.train.labels

"""Load MNIST data from `path`"""
with open(train_labels_path, 'rb') as lbpath:
    magic, n = struct.unpack('>II',lbpath.read(8))
    train_labels = np.fromfile(lbpath,dtype=np.uint8)
with open(train_images_path, 'rb') as imgpath:
    magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))
    train_images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(train_labels), 784)

 #train_labels 修改形状和值(=1)
new_train_labels=np.zeros((60000, 10),np.float32) 
i=0
for item in train_labels:
    new_train_labels[i][item]=1.0
    i=i+1
train_labels=new_train_labels

#验证形状
print('train_images.shape =>' +str(train_images.shape))
print('train_labels.shape =>' +str(train_labels.shape))

print(train_labels[0:10])

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])     #计算交叉熵
cross_entropy = -tf.reduce_sum(y_*tf.log(y))     #计算交叉熵

#以0.01的学习速率最小化交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

#初始化我们创建的变量
init = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init)

#每批训练数量
banch_size=64
#训练
for i in range(1000):
    batch_xs=train_images[i*banch_size:((i+1)*banch_size)]
    batch_ys=train_labels[i*banch_size:((i+1)*banch_size)]
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})


 #下面验证测试部分
test_images_path =r'D:\MNIST_data\t10k-images.idx3-ubyte'
test_labels_path =r'D:\MNIST_data\t10k-labels.idx1-ubyte'


test_images=[]  #=mnist.train.images
test_labels=[]  #=mnist.train.labels

"""Load MNIST data from `path`"""
with open(test_labels_path, 'rb') as lbpath:
    magic, n = struct.unpack('>II',lbpath.read(8))
    test_labels = np.fromfile(lbpath,dtype=np.uint8)
with open(test_images_path, 'rb') as imgpath:
    magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))
    test_images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(test_labels), 784)
    
 #test_labels    修改形状和值(=1)
new_test_labels=np.zeros((10000, 10),np.float32) 
i=0
for item in test_labels:
    new_test_labels[i][item]=1.0
    i=i+1
test_labels=new_test_labels

#验证形状
print('test_images.shape =>' +str(test_images.shape))
print('test_labels.shape =>' +str(test_labels.shape))


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_images, y_: test_labels}))

#显示0至24索引的图片
fig, ax = plt.subplots(
    nrows=5,
    ncols=5,
    sharex=True,
    sharey=True, )

ax = ax.flatten()
for i in range(25):
    img = train_images[i].reshape(28, 28)
    ax[i].imshow(img, cmap='Greys', interpolation='nearest')

ax[0].set_xticks([])
ax[0].set_yticks([])
plt.tight_layout()
plt.show()