Tensorflow实现自编码器

#encoding: utf-8'''AutoEncoder:使用自身的高阶编码器来提取特征，自编码器其实也是一种神经网络，它的输入和输出是一致的它借助稀疏编码的思想，目标是使用稀疏的一些高阶特征重新组合来重构自己。特点：①期望输入/输出一致；②用高阶特征来重构自己，不是复制像素点'''import numpy as np import sklearn.preprocessing as prep import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data# 载入MNIST数据mnist = input_data.read_data_sets('MNIST_data', one_hot=True)# 标准的均匀分布的Xavier初始化器 fan_in:输入节点的数量 fan_out:输出节点的数量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 #输入变量数self.n_hidden = n_hidden #隐含层结点数self.transfer = transfer_function #隐含层激活函数 默认为softplusself.scale = tf.placeholder(tf.float32) self.training_scale = scale #高斯噪声系数network_weights = self._initialize_weights() #参数初始化self.weights = network_weights# 定义网络结构self.x = tf.placeholder(tf.float32, [None, self.n_input])# 将输入x加入噪声# 将加了噪声的输入与隐含层的权重w1相乘 再加上隐含层的偏置b1# 激活函数处理self.hidden = self.transfer(tf.add(tf.matmul(self.x + scale*tf.random_normal((n_input,)),self.weights['w1']) , self.weights['b1']))# 经过隐含层在输出层进行数据复原、重建self.reconstruction = tf.add(tf.matmul(self.hidden, self.weights['w2']), self.weights['b2'])# 定义自编码函数的损失函数self.cost = 0.5*tf.reduce_sum(tf.pow(tf.subtract(self.reconstruction, self.x), 2.0))# 定义优化器self.optimizer = optimizer.minimize(self.cost)init = tf.global_variables_initializer()self.sess = tf.Session()self.sess.run(init)# 参数初始化函数def _initialize_weights(self):all_weights = {}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# 定义训练函数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# 求损失函数的函数 在训练完成后在测试集上你你你你你你你你你对模型性能进行评测def calc_total_cost(self, X):return self.sess.run(self.cost, feed_dict = {self.x:X, self.scale:self.training_scale})# transform函数 返回隐含层的输出结果 学习出的数据中的高阶特征def transform(self, X):return self.sess.run(self.hidden, feed_dict = {self.x:X, self.scale:self.training_scale})# 将隐含层的输出结果作为输入 通过之后重建层将高阶特征复原为原始数据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})# reconstruct函数 整体运行一遍复原过程 包括提取高阶特征和通过高阶特征复原数据def reconstruct(self, X):return self.sess.run(self.reconstruction, feed_dict = {self.x:X, self.scale:self.training_scale})# 获取权重w1def getWeights(self):return self.sess.run(self.weights['w1'])def getBiases(self):return self.sess.run(self.weights['b1'])# 对训练、测试数据进行标准化处理 让数据变成0均值 标准差为1的分布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数据 不放回抽样 取一个0--len(data)-batch_size之间的整数作为block的起始位置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)]# 数据标准化处理X_train, X_test = standard_scale(mnist.train.images, mnist.test.images)n_samples = int(mnist.train.num_examples)training_epochs = 20batch_size = 128display_step = 1autoencoder = 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)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_sizeif epoch%display_step == 0:print('Epoch:', '%04d' % (epoch+1), 'cost=','{:.9f}'.format(avg_cost))print('Total cost: ' + str(autoencoder.calc_total_cost(X_test)))

自编码器是一种无监督学习的方法，目的在于提取数据中最有用、最频繁出现的高阶特征，根据这些特征重构数据

内容源自《Tensorflow实战》