Fork me on GitHub

使用Autoencoder自编码进行Classfication

发表于 | 分类于
字数统计: 625 | 阅读时长 ≈ 3

使用Autoencoder进行Classfication

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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
#author:victor
#use encoder_decoder classfication

#import module
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np

#import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets('MNIST_data',one_hot=False)

#Visualize decoder setting
#Parameters
learning_rate=0.001
training_epochs=20
batch_size=256
display_step=1


#Network Parameters
n_input=784#MNIST data input(img shape:28*28),也即是784个features

#tf.Graph input(only pictures)
X=tf.placeholder('float',[None,n_input])

#hidden layer settings
n_hidden_1=128#first num features，先经过一个隐藏层压缩成128个features
n_hidden_2=64#second num features，在经过一个隐藏层压缩成64个features
n_hidden_3=10#third num features，先经过一个隐藏层压缩成10个features
n_hidden_4=2#fourth num features，在经过一个隐藏层压缩成2个features
#define the weights
weights={
         'encoder_h1':tf.Variable(tf.random_normal([n_input,n_hidden_1])),
         'encoder_h2':tf.Variable(tf.random_normal([n_hidden_1,n_hidden_2])),
         'encoder_h3':tf.Variable(tf.random_normal([n_hidden_2,n_hidden_3])),
         'encoder_h4':tf.Variable(tf.random_normal([n_hidden_3,n_hidden_4])),

         'decoder_h1':tf.Variable(tf.random_normal([n_hidden_4,n_hidden_3])),     
         'decoder_h2':tf.Variable(tf.random_normal([n_hidden_3,n_hidden_2])),
         'decoder_h3':tf.Variable(tf.random_normal([n_hidden_2,n_hidden_1])),
         'decoder_h4':tf.Variable(tf.random_normal([n_hidden_1,n_input])),
         }
#define the biases
biases={
        'encoder_b1':tf.Variable(tf.random_normal([n_hidden_1])),
        'encoder_b2':tf.Variable(tf.random_normal([n_hidden_2])),
        'encoder_b3':tf.Variable(tf.random_normal([n_hidden_3])),
        'encoder_b4':tf.Variable(tf.random_normal([n_hidden_4])),
        
        'decoder_b1':tf.Variable(tf.random_normal([n_hidden_3])),
        'decoder_b2':tf.Variable(tf.random_normal([n_hidden_2])),
        'decoder_b3':tf.Variable(tf.random_normal([n_hidden_1])),
        'decoder_b4':tf.Variable(tf.random_normal([n_input])),
        }

#building the encoder
def encoder(x):
    layer_1=tf.nn.sigmoid(tf.add(tf.matmul(x,weights['encoder_h1']),
                           biases['encoder_b1'] ))
    #Decoder hidden layer with sigmoid activation function
    layer_2=tf.nn.sigmoid(tf.add(tf.matmul(layer_1,weights['encoder_h2']),
                          biases['encoder_b2']))
    layer_3=tf.nn.sigmoid(tf.add(tf.matmul(layer_2,weights['encoder_h3']),
                           biases['encoder_b3'] ))
    #no use activation function
    layer_4=tf.add(tf.matmul(layer_3,weights['encoder_h4']),
                          biases['encoder_b4'])
    return layer_4
    
#building the decoder
def decoder(x):
    #Encoder hidden layer with sigmoid activation
    layer_1=tf.nn.sigmoid(tf.add(tf.matmul(x,weights['decoder_h1']),
                           biases['decoder_b1'] ))
    #Decoder hidden layer with sigmoid activation function
    layer_2=tf.nn.sigmoid(tf.add(tf.matmul(layer_1,weights['decoder_h2']),
                          biases['decoder_b2']))
     #Encoder hidden layer with sigmoid activation
    layer_3=tf.nn.sigmoid(tf.add(tf.matmul(layer_2,weights['decoder_h3']),
                           biases['decoder_b3'] ))
    #Decoder hidden layer with sigmoid activation function
    layer_4=tf.nn.sigmoid(tf.add(tf.matmul(layer_3,weights['decoder_h4']),
                          biases['decoder_b4']))
    return layer_4
    
#Construct model
encoder_op=encoder(X)
decoder_op=decoder(encoder_op)    

#Prediction
y_pred=decoder_op
#Targets(Labels) are the input data
y_true=X

#Define loss and optimizer,minimize the squre error
cost=tf.reduce_mean(tf.pow(y_true-y_pred,2))
optimizer=tf.train.AdamOptimizer(learning_rate).minimize(cost)    

#Initializing the variables
init=tf.initialize_all_variables()

#Launch the graph
with tf.Session() as sess:
    sess.run(init)
    total_batch=int(mnist.train.num_examples/batch_size)
    #Train cycle
    for epoch in range(training_epochs):
        #Loop overall batches
        for i in range(total_batch):
            batch_xs,batch_ys=mnist.train.next_batch(batch_size)#max(x)=1,min(x)=0,batch_xs已经被normalize正规化过了，最大值是1
            #Run optimization op (backprop) and cost op (to get loss value)
            _,c=sess.run([optimizer,cost],feed_dict={X:batch_xs})
            #Display logs per epoch step
            if epoch% display_step==0:
                print("Epoch",'%04d'%(epoch+1),
                      "cost=","{:9f}".format(c))
                
    print("Optimization Finished!")
            
    encoder_result=sess.run(encoder_op,feed_dict={X:mnist.test.images})
    plt.scatter(encoder_result[:,0],encoder_result[:,1],c=mnist.test.labels)
    plt.show()

运行结果：

classfication

总结：等运行结束后，以散点图scatter的形式展现出来，不同颜色表示MNIST data里的不同的数字lable，发现Classfication的效果还是不错