用CNN做简单的MNIST手写数字分类

用CNN做简单的MNIST手写数字分类

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

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

#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

#初始化权值
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1) #生成一个截断的正态分布,标准差为0.1
    return tf.Variable(initial)

#初始化偏置值
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

#卷积层
def conv2d(x,W):
    #x input tensor of shape `[batch, in_height, in_width, in_channels]--[每一个批次大小，输入的长，输入的宽，输入图片的通道(1 or 3)]
    #W filter/kernel tensor of shape `[filter_height, filter_width, in_channels, out_channels]
    #`strides[0] = strides[3] = 1`. strides[1]代表x方向的步长，strides[3]代表y方向的步长
    #padding: A `string `from: `"SAME","VALID"`
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')

#池化层
def max_pool_2x2(x):
    #ksize[1,x,y,1] 池化的窗口尺寸为 x,y
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

#定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784]) #28*28
y = tf.placeholder(tf.float32, [None, 10])

#改变x的格式转化为4维向量表示[batch, in_height, in_width, in_channels]
x_image = tf.reshape(x, [-1,28,28,1]) #batch=-1默认为前面设置的batch_size，因为图片是黑白的，所以in_channels=1；

#初始化第一个卷积层的权值和偏置
W_conv1 = weight_variable([5,5,1,32]) #5*5的采样窗口，32个卷积从1个平面抽取特征；采样完后会得到32个特征平面
b_conv1 = bias_variable([32]) #每一个卷积和一个偏置值

#把x_image和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1) #进行max_pooling

#初始化第二个卷积层的权重和偏置
W_conv2 = weight_variable([5,5,32,64]) #5*5的采样窗口，64个卷积核从32个平面抽取特征
b_conv2 = bias_variable([64]) #每一个卷积核一个偏置

#把h_pool1和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#28*28的图片第一次卷积后还是28*28，第一次池化后变为14*14
#第二次卷积后为14*14，第二次池化后变为7*7
#通过上面操作后得到64张7*7的平面

#吧池化层2的输出扁平化为1维
h_pool2_flat = tf.reshape(h_pool2, [-1,7*7*64]) #-1表示一个批次100

#初始化第一个全连接层的权值
W_fc1 = weight_variable([7*7*64,1024]) #上一层有7*7*64个神经元，全连接层有1024个神经元
b_fc1 = bias_variable([1024]) #1024个节点
#求第一个全连接层的输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#keep_prob用来表示神经元dropout概率
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#初始化第二个全连接层
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])

#计算输出
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))

#使用AdamOptimizer进行优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#结果存放在一个布尔列表中
correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1)) #argmax返回一维张量中最大值所在位置

#求准确度
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(21):
        for bath 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) + ', Testing Accuracy = ' + str(acc))
#    acc_test = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0})
#    print('Testing Accuracy = ' + str(acc_test))    
#        
        

用tensorboard可视化CNN网络

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

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

#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

#参数概要
def variable_summaries(var):
    with tf.name_scope('summaries'):
        mean = tf.reduce_mena(var)
        tf.summary.scalar('mean',mean) #平均值
        with tf.name_scope('stddev'):
            stddev = tf.sqrt(tf.reduce_mean(tf.square(var-mean)))
        tf.summary.scalar('stddev', stddev) #标准差
        tf.summary.scalar('max', tf.reduce_max(var)) #最大值
        tf.summary.saclar('min', tf.reduce_min(var)) #最小值
        tf.summary.histogram('histogram', var) #直方图

#初始化权值
def weight_variable(shape, name):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial, name=name)

#初始化偏置值
def bias_variable(shape, name):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial, name=name)

#卷积层
def conv2d(x, W):
    #x input tensor of shape `[batch, in_height, in_width, in_channels]--[每一个批次大小，输入的长，输入的宽，输入图片的通道(1 or 3)]
    #W filter/kernel tensor of shape `[filter_height, filter_width, in_channels, out_channels]
    #`strides[0] = strides[3] = 1`. strides[1]代表x方向的步长，strides[3]代表y方向的步长
    #padding: A `string `from: `"SAME","VALID"`
    return  tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')

#磁化层
def max_pool_2x2(x):
    #ksize [1,x,y,1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

#命名空间
with tf.name_scope('input'):
    #定义两个placeholder
    x = tf.placeholder(tf.float32, [None,784],name='x-input')
    y = tf.placeholder(tf.float32, [None,10],name='y-input')
    with tf.name_scope('x_image'):
        x_image = tf.reshape(x, [-1,28,28,1], name='x_image')

with tf.name_scope('Conv1'):
    #初始化第一个卷积层的权值和偏置
    with tf.name_scope('W_conv1'):
        W_conv1 = weight_variable([5,5,1,32], name='W_Conv1')
    with tf.name_scope('b_conv1'):
        b_conv1 = bias_variable([32], name='b_conv1')
    
    #把x_image和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
    with tf.name_scope('conv2d_1'):
        conv2d_1 = conv2d(x_image, W_conv1) + b_conv1
    with tf.name_scope('relu'):
        h_conv1 = tf.nn.relu(conv2d_1)
    with tf.name_scope('h_pool1'):
        h_pool1 = max_pool_2x2(h_conv1) #进行max_pooling

with tf.name_scope('Conv2'):
    #初始化第二个卷积层的权值和偏置
    with tf.name_scope('W_conv2'):
        W_conv2 = weight_variable([5,5,32,64],name='W_conv2')
    with tf.name_scope('b_conv2'):
        b_conv2 = bias_variable([64],name='b_conv2')
    with tf.name_scope('conv2d_2'):
        conv2d_2 = conv2d(h_pool1, W_conv2) + b_conv2
    with tf.name_scope('relu'):
        h_conv2 = tf.nn.relu(conv2d_2)
    with tf.name_scope('h_pool1'):
        h_pool2 = max_pool_2x2(h_conv2) #进行max_pooling

with tf.name_scope('fc1'):
    with tf.name_scope('W_fc1'):
        W_fc1 = weight_variable([7*7*64,1024],name='W_fc1')
    with tf.name_scope('b_fc1'):
        b_fc1 = bias_variable([1024],name='b_fc1')
        
    #将池化层2的输出扁平化为1维
    with tf.name_scope('h_pool2_flat'):
        h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64],name='h_pool2_flat')
    #求以第一个全连接层的输出
    with tf.name_scope('wx_plus_b1'):
        wx_plus_b1 = tf.matmul(h_pool2_flat,W_fc1) + b_fc1
    with tf.name_scope('relu'):
        h_fc1 = tf.nn.relu(wx_plus_b1)
    
    #keep_prob用来表示神经网络的输出概率
    with tf.name_scope('keep_prob'):
        keep_prob = tf.placeholder(tf.float32, name='keep_prob')
    with tf.name_scope('h_fc1_drop'):
        h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob,name='h_fc1_drop')

with tf.name_scope('fc2'):
    #初始化第二个全连接层
    with tf.name_scope('W_fc2'):
        W_fc2 = weight_variable([1024,10],name='W_fc2')
    with tf.name_scope('b_fc2'):
        b_fc2 = bias_variable([10],name='b_fc2')
        
    #求以第一个全连接层的输出
    with tf.name_scope('wx_plus_b2'):
        wx_plus_b2 = tf.matmul(h_fc1_drop,W_fc2) + b_fc2
    with tf.name_scope('softmax'):
        prediction = tf.nn.softmax(wx_plus_b2)

#交叉熵代价函数
with tf.name_scope('cross_entropy'):
    cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction),name='cross_entropy')
    tf.summary.scalar('cross_entropy',cross_entropy)
    
#使用AdamOptimizer进行优化
with tf.name_scope('train'):
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
    
#求准确率
with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
        #结果存放在一个布尔列表中
        correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
    with tf.name_scope('accuracy'):
        #求准确率
        accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
        tf.summary.scalar('accuracy',accuracy)
        
#合并所有的summary
merged = tf.summary.merge_all()

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    train_writer = tf.summary.FileWriter('logs/train',sess.graph)
    test_writer = tf.summary.FileWriter('logs/test',sess.graph)
    for i in range(1001):
        #训练模型
        batch_xs,batch_ys = mnist.train.next_batch(batch_size)
        sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.5})
        #记录训练集计算的参数
        summary = sess.run(merged, feed_dict={x:batch_xs,y:batch_ys,keep_prob:1.0})
        train_writer.add_summary(summary,i)
        
        #记录测试集计算的参数
        batch_xs,batch_ys = mnist.test.next_batch(batch_size)
        summary = sess.run(merged, feed_dict={x:batch_xs,y:batch_ys,keep_prob:1})
        test_writer.add_summary(summary,i)
        
        if i%100 == 0:
            test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
            train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images[:10000],y:mnist.train.labels[:10000],keep_prob:1.0})
            print('Iter' + str(i) + ', Testing Accuracy = ' + str(test_acc) + ', Training Accuracy = ' + str(train_acc))