001-antocoder记录

前置背景知识

1. tf.truncated_normal（shape,mean,dev）随机产生正太分布函数
2. tf.nn.softplus 激活函数log( exp( features ) + 1)
3. 优化算法总结

AntoEncoder 理论知识

 AntoEncoder其实就是编解码的一个过程，输入X与输出Y相同，通过定义loss不断训练，使得输入和输出非常相似。

用途

1. 利用中间网络节点少的特点，达到降低输入维度的作用
2. 通过训练正常用例，得到相应的loss值，可通过设定阈值的方式。当输入异常数据时，超过阈值达到异常检测的目的。

代码

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

        # model
        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'])

        # cost
        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)

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

    def reconstruct(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 = 0.001),
                                               scale = 0.01)

for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = int(n_samples / batch_size)
    # Loop over all batches
    for i in range(total_batch):
        batch_xs = get_random_block_from_data(X_train, batch_size)

        # Fit training using batch data
        cost = autoencoder.partial_fit(batch_xs)
        # Compute average loss
        avg_cost += cost / n_samples * batch_size

    # Display logs per epoch step
    if epoch % display_step == 0:
        print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(avg_cost))

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