TensorFlow学习（四）

TensorFlow学习（四）

CNN

• 传统的神经网络权值太多，计算量太大，需要大量样本进行训练。
  
  卷积神经网络，通过感受野和权值共享减少了神经网络需要训练的参数个数。
  
• 卷积
  
  对于不同的卷积核：
  
• 代码使用卷积神经网络进行数字识别：

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


mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
batch_size = 100
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
   return tf.Variable(initial)
#初始化偏置
def bias_variable(shape):
   initial = tf.constant(0.1,shape=shape)
   return tf.Variable(initial)
#卷积层
def conv2d(x,W):
   return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
#池化层
def max_pool_2x2(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])
x_image = tf.reshape(x,[-1,28,28,1])

###   神经网络
W_conv1 = weight_variable([5,5,1,32])#5*5的采样窗口，32个卷积核从1个平面抽取特征
b_conv1 = bias_variable([32])#每一个卷积核一个偏置值
conv2d_1 = conv2d(x_image,W_conv1) + b_conv1
h_conv1 = tf.nn.relu(conv2d_1)
h_pool1 = max_pool_2x2(h_conv1)#进行max-pooling


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值
conv2d_2 = conv2d(h_pool1,W_conv2) + b_conv2
h_conv2 = tf.nn.relu(conv2d_2)
h_pool2 = max_pool_2x2(h_conv2)#进行max-pooling

#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，第二次池化后变为了7*7
#进过上面操作后得到64张7*7的平面

#全连接层
#参数
W_fc1 = weight_variable([7*7*64,1024])#上一场有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
#把池化层2的输出扁平化为1维
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
wx_plus_b1 = tf.matmul(h_pool2_flat,W_fc1) + b_fc1
h_fc1 = tf.nn.relu(wx_plus_b1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
#第二个全连接层
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
wx_plus_b2 = tf.matmul(h_fc1_drop,W_fc2) + b_fc2
#计算输出
prediction = tf.nn.softmax(wx_plus_b2)


#交叉熵代价函数，使用AdamOptimizer进行优化
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))  
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#求准确率
#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的值所在的位置
#求准确率
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(10):
       for batch in range(n_batch):
       #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:0.7})
       
      
       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))

结果：