tensoflow练习3：卷积神经网络用于分类

再次利用卷积神经网络对手写体进行识别；卷积神经网络是一种非常强大的神经网络模型（可应用于图像识别，语音处理等领域）。下面将给出源码：

#coding = utf-8
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data/',one_hot=True)

n_output_layer = 10

#定义待训练的神经网络
def convoluional_neural_network(data):
    weights = {'w_conv1':tf.Variable(tf.random_normal([5,5,1,32])),
               'w_conv2':tf.Variable(tf.random_normal([5,5,32,64])),
               'w_fc':tf.Variable(tf.random_normal([7*7*64,1024])),
               'out':tf.Variable(tf.random_normal([1024,n_output_layer])),

               }
    biases = { 'b_conv1':tf.Variable(tf.random_normal([32])),
               'b_conv2':tf.Variable(tf.random_normal([64])),
               'b_fc':tf.Variable(tf.random_normal([1024])),
               'out':tf.Variable(tf.random_normal([n_output_layer]))

    }
    data = tf.reshape(data,[-1,28,28,1])

    conv1 = tf.nn.relu(tf.add(tf.nn.conv2d(data,weights['w_conv1'],strides=[1,1,1,1],padding='SAME'),biases['b_conv1']))
    #池化
    conv1 = tf.nn.max_pool(conv1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')

    #第二层
    conv2 = tf.nn.relu(tf.add(tf.nn.conv2d(conv1,weights['w_conv2'],strides=[1,1,1,1],padding='SAME'),biases['b_conv2']))
    conv2 = tf.nn.max_pool(conv2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
    #全连接层
    fc = tf.reshape(conv2,[-1,7*7*64])
    fc = tf.nn.relu(tf.add(tf.matmul(fc,weights['w_fc']),biases['b_fc']))#输出节点为1024

    #dropout 可选
    output = tf.add(tf.matmul(fc,weights['out']),biases['out'])

    return output


batch_size = 100

X= tf.placeholder('float',[None,28*28])
Y= tf.placeholder('float')

def train_neural_network(X, Y):
    predict = convoluional_neural_network(X)
    cost_func = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(predict,Y))
    optimizer = tf.train.AdamOptimizer().minimize(cost_func)
    epochs = 13

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        epoch_loss = 0
        print('training begins:')
        for epoch in range(epochs):
            for i in range(int(mnist.train.num_examples/batch_size)):
                x, y  = mnist.train.next_batch(batch_size)
                _, c = sess.run([optimizer,cost_func],feed_dict={X:x,Y:y})
                epoch_loss += c
            print(epoch, ' : ', epoch_loss)

        correct = tf.equal(tf.argmax(predict,1),tf.argmax(Y,1))
        accuracy = tf.reduce_mean(tf.cast(correct,'float'))
        print('精确率:', accuracy.eval({X:mnist.test.images,Y:mnist.test.labels}))

train_neural_network(X,Y)

相同部分就不加描述了，这里主要讲一下卷积过程；
（1）第一次卷积与池化：（特征个数从1变为32）

conv1 = tf.nn.relu(tf.add(tf.nn.conv2d(data,weights['w_conv1'],strides=[1,1,1,1],padding='SAME'),biases['b_conv1']))
    #池化
    conv1 = tf.nn.max_pool(conv1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')

padding=’SAME’时，表示0边距；strides=[1,1,1,1]：表示1步长；卷积后尺寸不变；然后池化操作变为14*14；
（2）第二次卷积与池化将尺寸变为7*7；（32变为64）

#第二层
    conv2 = tf.nn.relu(tf.add(tf.nn.conv2d(conv1,weights['w_conv2'],strides=[1,1,1,1],padding='SAME'),biases['b_conv2']))
    conv2 = tf.nn.max_pool(conv2,ksize=[1,2,2,1],strides=[1,2,2,1],padding

（3）全连接

fc = tf.reshape(conv2,[-1,7*7*64])
fc=tf.nn.relu(tf.add(tf.matmul(fc,weights['w_fc']),biases['b_fc']))#输出节点为1024

结果：