Turbot-DL入门教程篇-TensorFlow应用-MNIST例程

说明：

• 介绍如何使用tensorflow实现MNIST例程

环境：

• Python 3.5.2

步骤：

• 下载MNIST数据集：http://yann.lecun.com/exdb/mnist/

  t10k-images-idx3-ubyte.gz
  t10k-labels-idx1-ubyte.gz
  train-images-idx3-ubyte.gz
  train-labels-idx1-ubyte.gz

• 把下载的数据集放到文件夹MNIST_data中

• 新建文件

$ vim tensorflow_mnist.py

• 内容如下

#!/usr/bin/env python3  
# -*- coding: utf-8 -*-  

import input_data  
import tensorflow as tf  

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)  

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(1000):  
    batch_xs, batch_ys = mnist.train.next_batch(100)  
    sess.run(train_step, feed_dict={x:batch_xs,y_:batch_ys})  
  
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:mnist.test.images, y_:mnist.test.labels}) )  

• 执行

pythton3 tensorflow_mnist.py

• 结果如下

Extrackting MNIST_data/train-images-idx3-ubyte.gz
Extrackting MNIST_data/train-labels-idx1-ubyte.gz
Extrackting MNIST_data/t10k-images-idx3-ubyte.gz
Extrackting MNIST_data/t10k-labels-idx1-ubyte.gz
I tensorflow/core/platform/cpu_feature_guard.cc:137 Your CPU supports instructions that this Tensorflow binary was not compiled to use: SSE4.
I SSE4.2 AVX AVX2 FMA
0.9179    

• 最终结果应该在91%左右