簡介

• 自編碼器是利用神經網路提取出影象中的高階特徵，同時可以利用高階特徵重構自己
• 如果向原圖中新增噪聲，則可以通過高階特徵的提取，對原始影象進行去噪
• tensorflow實戰第四章內容

程式碼

import numpy as np
import sklearn.preprocessing as prep
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

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 )

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 ) )
        self.optimizer = optimizer.minimize( self.cost )
        init = tf.global_variables_initializer()
        self.sess = tf.Session()
        self.sess.run( init )
        print "begin to run session..."
    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

    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

    def calc_total_cost( self, X ):
        return self.sess.run( self.cost, feed_dict = { self.x : X, self.scale : self.training_scale } )

    def transform( self, X ):
        return self.sess.run( self.hidden, feed_dict = { self.x : X, self.scale : self.training_scale } )

    def generate( self, hidden = None ):
        if hidden == None:
            hidden = np.random.normal( size = self.weights['b1'] )
        return self.sess.run( self.reconstruction, feed_dict = { self.hidden : hidden } )

    def reconstruction( self, X ):
        return self.sess.run( self.reconstruction, feed_dict = { self.x : X, self.scale : self.training_scale } )

    def getWeights( self ):
        return self.sess.run( self.weights['w1'] )

    def getBiases( self ):
        return self.sess.run( self.weights['b1'] )


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

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

def get_random_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

autoencoder = AdditiveGaussianNoiseAutoencoder( n_input = 784,
                                                                                    n_hidden = 200, 
                                                                                    transfer_function = tf.nn.softplus,
                                                                                    optimizer = tf.train.AdamOptimizer( learning_rate = 0.0001 ),
                                                                                    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_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, cost = %.9f" % ( epoch+1, avg_cost ) )

print( "Total cost : ",  str( autoencoder.calc_total_cost(X_test) 
 

說明

• 檔案中mnist初始化時需要設定資料集的位置
• 隱藏層的節點數越大，訓練後得到的誤差越小，200個節點時，測試誤差為60萬左右，400個節點時，測試誤差為20萬左右
• 自己又加了一個隱藏層，但是效果好像不明顯，隨著訓練次數的變化，訓練誤差呈現出發散的狀態