tensorflow实战（二）——自编码器

自编码器

自行百度，待补充

学习

1. one_hot 独热编码

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

可以把数据(比如5以内的数)编码成5维，数据在哪，哪个位置就是1的 [0, 0, 0, 0, 1]这种数据格式

2. 数据标准化处理

preprocessor = prep.StandardScaler().fit(X_train)
X_train = preprocessor.transform(X_train)
X_test = preprocessor.transform(X_test)

1. fit
   preprocessor里面存的是计算出来的训练数据的均值和方差
2. transform
   使用preprocessor中的均值和方差来转换数据，使数据标准化(生成0均值，标准差为1的分布)
   标准化后的数据 = (原数据 - 均值 )/标准差

3. 随机数生成

np.random.randint(a,b)

生成[a,b)的随机整数，注意：左闭右开

4. MNIST数据读取

mnist = input_data.read_data_sets('MNIST_data/', one_hot = True)
# 数据格式
print(mnist.train.images.shape, mnist.train.labels.shape)
print(mnist.test.images.shape, mnist.test.labels.shape)
print(mnist.validation.images.shape, mnist.validation.labels.shape)
# 数据大小
print(mnist.train.num_examples)
print(mnist.test.num_examples)
print(mnist.validation.num_examples)

5. feed_dict 和 sess.run()

feed_dict的作用：给使用placeholder创建出来的tensor赋值，格式为字典型

cost, opt = self.sess.run((self.cost, self.optimizer), feed_dict = {self.x: X, self.scale: self.training_scale})

run(fetches, feed_dict)
喂数据feed_dict，返回fetches的值

6. 正态分布

np.random.normal(size = self.weights["b1"])

np.random.randn(size)生成标准正态分布（μ=0,σ=1），对应于np.random.normal(loc=0, scale=1, size)

numpy.random.normal(loc=0,scale=1e-2,size=shape)

• 参数loc(float)：正态分布的均值，对应着这个分布的中心。loc=0说明这一个以Y轴为对称轴的正态分布，
• 参数scale(float)：正态分布的标准差，对应分布的宽度，scale越大，正态分布的曲线越矮胖，scale越小，曲线越高瘦。
• 参数size(int 或者整数元组)：输出的值赋在shape里，默认为None。

7. 均匀分布

tf.random_uniform((fan_in, fan_out), minval = low, maxval = high, dtype = tf.float32)

tf.random_uniform((m, n), minval, maxval, dtype)
返回m*n的矩阵，值在 [minval, maxval)范围内，数据格式为dtype的均匀分布

8. 权重初始化

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)))