tensorflow实现简单的自编码器

# 自编码器
#导入相关库
import numpy as np
import sklearn.preprocessing as prep
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#定义初始化函数
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)

#定义去噪自编码器类
class AdditiveGaussianNoiseAutoencoder(object):
    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)
        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'])
        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)
        
        #权重初始化函数
    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(tf.zeros([self.n_hidden,self.n_input],dtype = tf.float32))
        all_weights['b2'] = tf.Variable(tf.zeros([self.n_input],dtype = tf.float32))
        return all_weights
    
    #计算损失及执行训练的函数
    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
    
    #只求损失的函数
    def calc_total_cost(self,X):
        return self.sess.run(self.cost,feed_dict = {self.x:X,self.scale:self.training_scale})
     #返回隐藏层的输出结果
    def transform(self,X):
        return self.sess.run(self.hidden,feed_dict = {self.x:X,self.scale:self.training_scale})
        #将重建层提取到的高阶特征复原为原始函数
    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})    
        #提取高阶特征及通过高阶特征复原原始数据
    def reconstruct(self,X):
        return self.sess.run(self.reconstruction,feed_dict = {self.x:X,self.scale:self.training_scale})
    #获取隐藏层的权重
    def getWeights(self):
        return self.sess.run(self.weights['w1'])
    #获取隐藏层的偏置
    def getBiases(self):
        return self.ssess.run(self.weights['b1'])
    

#载入mnist数据集
mnist = input_data.read_data_sets('MNIST_data/',one_hot = True)

#对训练、测试进行标准化处理的函数
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


#获取随机block的函数
def get_random_block_data(data, batch_size):
    start_index = np.random.randint(0, len(data) - batch_size)
    return data[start_index:(start_index + batch_size)]


#对数据集进行标准化变换
X_train,X_test = standard_scale(mnist.train.images,mnist.test.images)

#定义常用参数
n_samples = int(mnist.train.num_examples)
training_epochs = 200
batch_size = 128
display_step = 1

#创建自编码器的一个实例
autoencoder = AdditiveGaussianNoiseAutoencoder(n_input = 784,n_hidden = 200,transfer_function = tf.nn.softplus,optimizer = tf.train.AdamOptimizer(learning_rate = 0.001),scale = 0.01)
#开始训练
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_random_block_from_data(X_train, batch_size)
        
        
        cost = autoencoder.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))
        
#性能测试
print("Total cost:" + str(autoencoder.calc_total_cost(X_test)))

参考书籍：

1.《Tensorflow实战》黄文坚  唐源 著

作者：舟华520

出处：https://www.cnblogs.com/xfzh193/

本文以学习，分享，研究交流为主，欢迎转载，请标明作者出处！