TensorFlow实战（二）自编码器

自编码器就是对数据进行高维处理：

（1） 如果限制中间隐含层节点的数量， 比如让中间隐含层节点的数量小于输入／输出节点的数量，就相当于一个降维的过程。此时已经不可能出现复制所有节点的情况， 因为 中间节点数小于输入节点数，那只能学习数据中最重要的特征复原，将可能不太相关的内容去除。此时 ， 如果再给中间隐含层的权重加一个LI的正则， 则可以根据惩罚系数控制隐含节点的稀疏程度，惩罚系数越大，学到的特征组合越稀疏， 实际使用（非零权重）的特征数量越少。

（2）如果给数据加入噪声，那么就是 Denoising AutoEncoder （去噪自编码器），我们将从l噪声中学习出数据的特征。同样， 我们也不可能完全复制节点，完全复制并不能去除 我们添加的噪声，无法完全复原数据。所以唯有学习数据频繁出现的模式和结构，将无规律的噪声略去， 才可以复原数据。

import numpy as np
import sklearn.preprocessing as prep
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#xavier_init是对学习模型的权重就行初始化。
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)
#定义一个类
class AdditiveGaussianNoiseAutoencoder(object):

#定义一个构造函数
    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)
#神经网络各层的权重初始化
    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(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)))
print(autoencoder. getWeights())

MLP是多层感知机：用到了

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()

in_units = 784
h1_units = 300
W1 = tf.Variable(tf.truncated_normal([in_units, h1_units], stddev=0.1))
b1 = tf.Variable(tf.zeros([h1_units]))
W2 = tf.Variable(tf.zeros([h1_units, 10]))
b2 = tf.Variable(tf.zeros([10]))

x = tf.placeholder(tf.float32, [None, in_units])
keep_prob = tf.placeholder(tf.float32)
#隐藏层用了relu激活函数
hidden1 = tf.nn.relu(tf.matmul(x, W1) + b1)
#随机丢失参数
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)
y = tf.nn.softmax(tf.matmul(hidden1_drop, W2) + b2)

# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)

# Train
tf.global_variables_initializer().run()
for i in range(3000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  train_step.run({x: batch_xs, y_: batch_ys, keep_prob: 0.75})

# Test trained model
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval({x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))