TensorFlow的MNIST手写数字分类问题 完善篇_使用tensorflow编写mnist手写数字分类问题

 上期介绍了tensorflow手写数字识别的基础篇，接下来介绍一下使用卷积神经完善后的代码部分

一、往期代码

基础篇代码如下：

import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
 
import tensorflow as tf sess = tf.InteractiveSession()
 
x = tf.placeholder("float", shape=[None, 784]) y_ = tf.placeholder("float", shape=[None, 10])
 
W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10]))
 
sess.run(tf.initialize_all_variables())
 
y = tf.nn.softmax(tf.matmul(x,W) + b)
 
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
 
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
 
for i in range(1000): batch = mnist.train.next_batch(50) train_step.run(feed_dict={x: batch[0], y_: batch[1]})
 
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
 
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
 
print accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels})

二、卷积完善代码过程

下面介绍经过卷积神经网络完善后的代码

权重初始化

 def weight_variable(shape): 
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)
 def bias_variable(shape): 
    initial = tf.constant(0.1, shape=shape) 
    return tf.Variable(initial)
 

卷积和池化： 

def conv2d(x, W):
 
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1],padding='SAME')
 
def max_pool_2x2(x): 
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
 

 第一层卷积

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

x_image和权值向量进行卷积,加上偏置项,然后应用ReLU激活函数,最后进行 max pooling.

x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

 第二层的卷积

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
 
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

 加上权重矩阵，然后加上relu

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
 
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

使用dropout防止过拟合 

keep_prob = tf.placeholder("float") 
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 

 最后,我们添加一个 softmax 输出层

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
 
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

进行模型评估

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print "step %d, training accuracy %g"%(i, train_accuracy)
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
 
print "test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})

以上代码,在最终测试集上的准确率为99.2%.