1.Introduction
利用卷积神经网络CNN对Mnist数据集手写数字进行分类。
2.Source code
Version1:
coding:utf-8
import input_data
import tensorflow as tf
log_dir = "cnn_mnist_logs"
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])
#权重初始化
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)#使用截尾Guass分布初始化权重
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')
#卷积使用1步长(stride size) 0边距(padding size的模板 保证输出和输入是同一个大小
#par1:x表示input #para1:batch_size #para2:in_height #para3:in_width #para4:in_channels
#par2:w表示filter #para1:filter_height #para2:filter_width #para3:in_channels #para4:out_channels
#par3:strides表示步长 #para1:batch_size #para2:height #para3:width #para4:in_channels
def max_pool_2x2(x): #池化用简单传统的2x2大小的模板做max pooling
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#para1:x, input
#para2:ksize, pooling size:2*2
#para3:strdes, 步长2*2 [1,2,2,1]表示步长2×2 不重叠
#第一层卷积
W_conv1 = weight_variable([5, 5, 1, 32]) #前两个表示filter大小接着是输入的通道数目，最后是输出的通道数目;为每个5×5小块提取32个特征
b_conv1 = bias_variable([32]) #对于每一个输出通道都有一个对应的偏置量
x_image = tf.reshape(x, [-1,28,28,1]) #第2、第3维对应图片的宽、高，最后一维代表图片的颜色通道数(因为是灰度图所以这里的通道数为1，如果是rgb彩色图，则为3)
#We then convolve x_image with the weight tensor, add the bias, apply the ReLU function, and finally max pool
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)#利用ReLU激活函数 conv2d得到28×28×32
h_pool1 = max_pool_2x2(h_conv1)#池化 得到14×14×32
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
#第二层卷积
#为了构建一个更深的网络，我们会把几个类似的层堆叠起来。第二层中，每个5x5的patch会得到64个特征
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) #得到14×14×64
h_pool2 = max_pool_2x2(h_conv2) #得到7×7×64
#密集连接层
#现在，图片尺寸减小到7x7，我们加入一个有1024个神经元的全连接层，用于处理整个图片
#我们把池化层输出的张量reshape成一些向量，乘上权重矩阵，加上偏置，然后对其使用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)
#Dropout
#减少过拟合，dropout可以屏蔽神经元的输出和某些突触
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#输出层 最后，我们添加一个softmax层，就像前面的单层softmax regression一样
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)
#训练和评估模型
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"))
train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph) #定义写入摘要数据到事件日志的操作
sess.run(tf.initialize_all_variables())
for i in range(20000): #20000
batch = mnist.train.next_batch(50)
if i%100 == 0: #每100次训练计算一次训练集正确率
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)
print "test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
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})
Version2:
#coding:utf-8
import input_data
import tensorflow as tf
import numpy as np
log_dir = "cnn_mnist_logs"
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#权重初始化
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)#使用截尾Guass分布初始化权重
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')
#卷积使用1步长(stride size) 0边距(padding size的模板 保证输出和输入是同一个大小
#par1:x表示input #para1:batch_size #para2:in_height #para3:in_width #para4:in_channels
#par2:w表示filter #para1:filter_height #para2:filter_width #para3:in_channels #para4:out_channels
#par3:strides表示步长 #para1:batch_size #para2:height #para3:width #para4:in_channels
def max_pool_2x2(x): #池化用简单传统的2x2大小的模板做max pooling
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#para1:x, input
#para2:ksize, pooling size:2*2
#para3:strdes, 步长2*2 [1,2,2,1]表示步长2×2 不重叠
graph = tf.Graph()
with graph.as_default():
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])
global_step = tf.Variable(0, trainable=False)
#第一层卷积
W_conv1 = weight_variable([5, 5, 1, 32]) #前两个表示filter大小接着是输入的通道数目，最后是输出的通道数目;为每个5×5小块提取32个特征
b_conv1 = bias_variable([32]) #对于每一个输出通道都有一个对应的偏置量
x_image = tf.reshape(x, [-1,28,28,1]) #第2、第3维对应图片的宽、高，最后一维代表图片的颜色通道数(因为是灰度图所以这里的通道数为1，如果是rgb彩色图，则为3)
#We then convolve x_image with the weight tensor, add the bias, apply the ReLU function, and finally max pool
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)#利用ReLU激活函数 conv2d得到28×28×32
h_pool1 = max_pool_2x2(h_conv1)#池化 得到14×14×32
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
#第二层卷积
#为了构建一个更深的网络，我们会把几个类似的层堆叠起来。第二层中，每个5x5的patch会得到64个特征
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) #得到14×14×64
h_pool2 = max_pool_2x2(h_conv2) #得到7×7×64
#密集连接层
#现在，图片尺寸减小到7x7，我们加入一个有1024个神经元的全连接层，用于处理整个图片
#我们把池化层输出的张量reshape成一些向量，乘上权重矩阵，加上偏置，然后对其使用ReLU
W_fc1 = weight_variable([7 * 7 * 64, 512])
b_fc1 = bias_variable([512])
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)
#Dropout
#减少过拟合，dropout可以屏蔽神经元的输出和某些突触
keep_prob = tf.placeholder("float")
#keep_prob=tf.Variable(tf.constant(0.5))
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#输出层 最后，我们添加一个softmax层，就像前面的单层softmax regression一样
W_fc2 = weight_variable([512, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
#训练和评估模型
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv)) #交叉熵
optimizer = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
predict_op = tf.argmax(y_conv, 1) #放回py_x序列中最大值的index，概率最大的那>个，即类别（0--9）
merged = tf.summary.merge_all() ##定义合并变量操作，一次性生成所有摘要数据i
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))#accuracy分类正确率
with tf.device("/cpu:0"):
saver = tf.train.Saver(tf.global_variables(), max_to_keep=2)
with tf.Session(graph=graph) as sess: #启动模型
train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph) #定义写入摘要数据到事件日志的操作
tf.global_variables_initializer().run() #将所有的变量初始化
for i in range(20000): #20000
batch = mnist.train.next_batch(50)
if i%100 == 0: #每100次训练计算一次训练集正确率
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)
print "test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
optimizer.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
saver.save(sess, 'run/checkpoint', global_step=global_step) #使用tf.save.Saver保存整个模型后,让TensorBoard自动对模型中所有二维的Variable进行可视化
8240
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
