tensorflow學習系列四：卷積神經網絡

    卷積神經網絡毋庸置疑是深度學習的基石，基於卷積神經網絡在很多方面都取得了傳統算法所無法匹敵的性能，因而作爲深度學習的入門，卷積神經網絡必須瞭如指掌。本文主要基於tensorflow實現手寫字體識別，網絡結構爲LeNet-5。可以說該網絡應該是卷積神經網絡中的hellworld，下面就是LeNet-5的具體實現

# -*- coding: utf-8 -*-
"""
Created on Sun Jun 10 11:14:00 2018

@author: kuangyongjian
"""
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

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

#定義權重變量
def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev = 0.1)
    return tf.Variable(initial)

#定義偏置向量
def bias_variable(shape):
    initial = tf.constant(0.1,shape = shape)
    return tf.Variable(initial)

#定義卷積
def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides = [1,1,1,1],padding = 'SAME')

#定義池化層
def max_pool(x):
    return tf.nn.max_pool(x,ksize = [1,2,2,1],strides = [1,2,2,1],padding = 'SAME')

#定義計算圖的輸入
x = tf.placeholder(tf.float32,[None,784])
y_ = tf.placeholder(tf.float32,[None,10])
x_image = tf.reshape(x,[-1,28,28,1])

#定義網絡結構
#網絡的第一層
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool(h_conv1)

#網絡的第二層
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(h_conv2)

#網絡的第三層
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)

keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

#網絡的第四層
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)


#定義損失
loss = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices = [1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)


correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

#網絡訓練
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)

for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(session = sess,feed_dict = {x:batch[0],y_:batch[1],keep_prob:1.0})
        print('step %d, training accuracy %g'%(i,train_accuracy))   
    train_step.run(session = sess,feed_dict = {x:batch[0],y_:batch[1],keep_prob:0.5})

print('test accuracy %g'%accuracy.eval(session = sess,feed_dict = {x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))

若有不當之處，請指教，謝謝！