tensorflow study4 cnn

In [1]:

#构建简单的卷积神经网络
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist=input_data.read_data_sets('MNIST_data/',one_hot=True)
sess=tf.InteractiveSession()

Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

In [5]:

#定义w\b的初始化
def weight_variable(shape):
    initial=tf.truncated_normal(shape,stddev=0.1)#增加正态分布的噪声
    return tf.Variable(initial)
def bias_variable(shape):
    initial=tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

#定义卷积层和池化
def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],
                         padding='SAME')

In [6]:

x=tf.placeholder(tf.float32,[None,784])
y_=tf.placeholder(tf.float32,[None,10])
x_image=tf.reshape(x,[-1,28,28,1])#卷积之前需要MNIST转化为图像大小

In [8]:

W_conv1=weight_variable([5,5,1,32])#第一个卷积层
b_conv1=bias_variable([32])
h_conv1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1=max_pool_2x2(h_conv1)

In [9]:

W_conv2=weight_variable([5,5,32,64])#第二个卷积层
b_conv2=bias_variable([64])
h_conv2=tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2=max_pool_2x2(h_conv2)

import tensorflow as tf

a=tf.constant([
[[1.0,2.0,3.0,4.0],
[5.0,6.0,7.0,8.0],
[8.0,7.0,6.0,5.0],
[4.0,3.0,2.0,1.0]],
[[4.0,3.0,2.0,1.0],
[8.0,7.0,6.0,5.0],
[1.0,2.0,3.0,4.0],
[5.0,6.0,7.0,8.0]]
])

a=tf.reshape(a,[1,4,4,2])

pooling=tf.nn.max_pool(a,[1,2,2,1],[1,1,1,1],padding='VALID')
with tf.Session() as sess:
print("image:")
image=sess.run(a)
print (image)
print("reslut:")
result=sess.run(pooling)
print (result)

In [16]:

W_fc1=weight_variable([7*7*64,1024])
b_fc1=bias_variable([1024])
h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])#拉平
h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)#第一个全连接层输出

In [22]:

keep_prob=tf.placeholder(tf.float32)#保留的概率
h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)#添加dropout层防止过拟合

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)

#定义损失函数
cross_entropy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y_conv)))
train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

In [23]:

#定义准确率
correct_prediction=tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))#cast将数据转化成bool型，然后统计均值

In [ ]:

#开始训练
tf.global_variables_initializer().run()
for i in range(2000):
    batch=mnist.train.next_batch(50)
    if i%100==0:
        train_accuracy=accuracy.eval(feed_dict={x:batch[0],y_:batch[1],
                                               keep_prob:1})
        print("setp %d,training accuracy %g"%(i,train_accuracy))
    train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})

In [26]:

print("test accuracy %g"%accuracy.eval(feed_dict={
    x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))#eval只是用来测试不影响训练

test accuracy 0.9756