tensorflow学习系列二：噪声自编码器

    噪声自编码就是在自编码器的基础上对输入数据加入噪声，然后重构原始输入的干净数据，这在一定程度上使得隐含层提取的特征更具有鲁棒性。以下是基于tensorflow实现的噪声自编码器：

# -*- coding: utf-8 -*-
"""
Created on Sat Jun  9 13:28:37 2018

@author: kuangyongjian
"""
import numpy as np
import sklearn.preprocessing as prep
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#产生设定范围内的随机数用于初始化权重
def xavier_init(fan_in,fan_out,constant = 1):
    low = -constant * np.sqrt(6.0 / (fan_in + fan_out))
    high = constant * np.sqrt(6.0 / (fan_in + fan_out))
    return tf.random_uniform((fan_in,fan_out),
                             minval = low,maxval = high,
                             dtype = tf.float32)
    
#定义噪声自编码类
class AdditiveGaussianNoiseAutoencoder(object):
    #初始化定义变量以及占位符等
    def __init__(self,n_input,n_hidden,transfer_function = tf.nn.softplus,
                 optimizer = tf.train.AdamOptimizer(),scale = 0.1):
        
        self.n_input = n_input
        self.n_hidden = n_hidden
        self.transfer = transfer_function
        self.scale = tf.placeholder(tf.float32) #scale高斯噪声系数
        self.training_scale = scale
        network_weights = self._initialize_weights()
        self.weights = network_weights
        
        self.x = tf.placeholder(tf.float32,[None,self.n_input])
        self.hidden = self.transfer(tf.add(tf.matmul(self.x + scale * tf.random_normal((n_input,)),
                                                     self.weights['W1']),self.weights['b1']))
        self.reconstruction = tf.add(tf.matmul(self.hidden,self.weights['W2']),
                                     self.weights['b2'])
        #定义损失函数
        self.cost = 0.5 * tf.reduce_sum(tf.pow(tf.subtract(self.reconstruction,self.x),2.0))
        self.optimizer = optimizer.minimize(self.cost)
        init = tf.global_variables_initializer()
        self.sess = tf.Session()
        self.sess.run(init)
        
     #权重初始化   
    def _initialize_weights(self):
        
        all_weights = dict()
        all_weights['W1'] = tf.Variable(xavier_init(self.n_input,self.n_hidden))
        all_weights['b1'] = tf.Variable(tf.zeros([self.n_hidden],dtype = tf.float32))
        
        all_weights['W2'] = tf.Variable(xavier_init(self.n_hidden,self.n_input))
        all_weights['b2'] = tf.Variable(tf.zeros([self.n_input],dtype = tf.float32))
        
        return all_weights
  
    #返回代价和优化器
    def partial_fit(self,x):
        
        cost,opt = self.sess.run((self.cost,self.optimizer),feed_dict = {self.x:x,self.scale:self.training_scale})
        return cost
    
    #计算总的代价
    def calc_total_cost(self,x):
        
        return self.sess.run(self.cost,feed_dict = {self.x:x,self.scale:self.training_scale})
    
    #抽象特征
    def transform(self,x):
        
        return self.sess.run(self.hidden,feed_dict = {self.x:x,self.scale:self.training_scale})
    
    #隐含特征到重构数据
    def generate(self,hidden = None):
        
        if hidden is None:
            hidden = np.random.normal(size = self.weights['b1'])
        return self.sess.run(self.reconstruction,
                             feed_dict = {self.hidden:hidden})

    #整体一遍复现过程
    def reconstruct(self,x):
        
        return self.sess.run(self.reconstruction,feed_dict = {self.x:x,self.scale:self.training_scale})

    #获取权重w1
    def getWeights(self):
        
        return self.sess.run(self.weights['W1'])
    
    #获取biases
    def getBiases(self):
        
        return self.sess.run(self.weights['b1'])




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

#加入噪声数据
def standard_scale(x_train,x_test):
    
    preprocessor = prep.StandardScaler().fit(x_train)
    x_train = preprocessor.transform(x_train)
    x_test = preprocessor.transform(x_test)
    return x_train,x_test

#批量去数据
def get_radom_block_from_data(data,batch_size):
    
    start_index = np.random.randint(0,len(data) - batch_size)
    return data[start_index:(start_index + batch_size)]

x_train,x_test = standard_scale(mnist.train.images,mnist.test.images)    

n_samples = int(mnist.train.num_examples)
training_epochs = 20
batch_size = 128
display_step = 1

autocoder = AdditiveGaussianNoiseAutoencoder(n_input = 784,
                                             n_hidden = 200,
                                             transfer_function = tf.nn.softplus,
                                             optimizer = tf.train.AdamOptimizer(learning_rate = 0.001),
                                             scale = 0.01)

for epoch in range(training_epochs):
    avg_cost = 0
    total_batch = int(n_samples / batch_size)
    for i in range(total_batch):
        batch_xs = get_radom_block_from_data(x_train,batch_size)
        cost = autocoder.partial_fit(batch_xs)
        avg_cost += cost / n_samples * batch_size
        
    if epoch % display_step == 0:
        print('Epoch: %04d'%(epoch + 1),'cost = ","{:.9f}'.format(avg_cost))

若有不当之处请指教，谢谢!