tensorflow学习笔记——卷积神经网络的简单应用

本文用卷积神经网络实现MNIST数据集分类。可在这个网站下载MNIST数据集。下载后的数据如下图所示：

代码如下：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#载入数据
mnist = input_data.read_data_sets("E:/mnist",one_hot=True)
#每个批次大小
batch_size = 200
#计算一共有多少个批次
n_batch = mnist.train.num_examples//batch_size #整除

def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev = 0.1)#用截断正态分布初始化
    return tf.Variable(initial)

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

def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
#步长4个值分别表示图片步长（一个批次多张图片），向右移动步长，向下移动步长，层数移动步长，SAME表示边缘补0

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

x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])

#第一维：每个批次图片数，第二三维：图像宽高，第四维：图像层数
x_image = tf.reshape(x,[-1,28,28,1])
#第一层卷积
W_conv1 = weight_variable([5,5,1,32])#5×5的卷积核，图像层数为1，卷积核32个
b_conv1 = bias_variable([32])

conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
pool1 = max_pool(conv1)

#第二层卷积
W_conv2 = weight_variable([5,5,32,64])#5×5的卷积核，图像层数为32，卷积核64个
b_conv2 = bias_variable([64])

conv2 = tf.nn.relu(conv2d(pool1,W_conv2)+b_conv2)
pool2 = max_pool(conv2)

pool2_flat = tf.reshape(pool2,[-1,7*7*64])#将64张7×7的图片拉平

# 第一层全连接
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])

fc1 = tf.nn.relu(tf.matmul(pool2_flat,W_fc1)+b_fc1)
keep_prob = tf.placeholder(tf.float32)
fc1_drop = tf.nn.dropout(fc1,keep_prob)

#第二层全连接
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])

prediction = tf.nn.softmax(tf.matmul(fc1_drop,W_fc2)+b_fc2)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,logits=prediction))
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)

correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#equl判断是否相等，argmax返回张量最大值的索引
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) #将布尔型转换为浮点型

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(21):
        for batch in range(n_batch):
            batch_xs,batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.7})
        
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        print("Iter " + str(epoch) + " Accuracy" + str(acc)) 

运行结果如下：