CNN的demo_cnn demo

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)

#定义计算准确率的函数
def compute_accuracy(v_xs,v_ys):
    global prediction
    y_pre = sess.run(prediction,feed_dict={xs:v_xs,ys:v_ys,keep_prob:1})
    correct_prediction = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    result = sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys,keep_prob:1})
    return result

def weight_variable(shape):
    initial = tf.truncated_normal(shape=shape,stddev=0.1)
    #生成一个形状为shape,标准差为0.1的tensor
    return tf.Variable(initial)

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

def conv2d(x,W):
    #stride[1,x_movement,y_movement,1]
    #must have stride[0]=stride[3]=1
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

def max_pool_2d(x):
    #ksize is same as strides
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')

#define placeholder for inputs to network
xs = tf.placeholder(tf.float32,[None,784])#28*28
ys = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs,[-1,28,28,1])#这里的-1表示数量未知
#print(x_image.shape) the result will be [n_samples,28,28,1]


#conv1 layer
W_conv1 = weight_variable([5,5,1,32])#patch 5*5,in size 1,out size 32,过滤器大小为5*5,高度与图片一样是1,共32个过滤器
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)#output size 28*28*32
h_pool1 = max_pool_2d(h_conv1)#output size 14*14*32

#conv2 layer
W_conv2 = weight_variable([5,5,32,64])#patch 5*5,in size 32,out size 64,过滤器大小为5*5,高度与图片一样是32,共64个过滤器
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)#output size 14*14*64
h_pool2 = max_pool_2d(h_conv2)#output size 7*7*64

#func1 layer
W_fc1 =weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])

#[n,sample,7,7,64]->>[n_samples,7*7*64]
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])#这里的-1是什么意思？-1是指先不管有多少个sample
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)#这里使用随机失活用来防止过拟合

#func2 layer
W_fc2 =weight_variable([1024,10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)

#train the neural network
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(0.0001).minimize(cross_entropy)

sess = tf.Session()
sess.run(tf.initialize_all_variables())

for i in range(1000):
    batch_xs,batch_ys = mnist.train.next_batch(100)
    sess.run(train_step,feed_dict={xs:batch_xs,ys:batch_ys,keep_prob:0.5})
    if i%50 == 0:
        print(compute_accuracy(mnist.test.images,mnist.test.labels))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78