注意：代碼源自[1][2]
# 這里以最具代表性的去噪自編碼器為例。 # 導入MNIST數據集 import numpy as np import sklearn.preprocessing as prep import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # 這里使用一種參數初始化方法xavier initialization，需要對此做好定義工作。 # Xaiver初始化器的作用就是讓權重大小正好合適。 # 這里實現的是標准均勻分布的Xaiver初始化器。 def xavier_init(fan_in, fan_out, constant=1): """ 目的是合理初始化權重。 參數： fan_in --行數； fan_out -- 列數； constant --常數權重，條件初始化范圍的倍數。 return 初始化后的權重tensor. """ 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) # 定義一個去噪的自編碼類 class AdditiveGaussianNoiseAutoencoder(object): """ __init__() :構建函數； n_input : 輸入變量數； n_hidden : 隱含層節點數； transfer_function: 隱含層激活函數，默認是softplus； optimizer : 優化器，默認是Adam; scale : 高斯噪聲系數，默認是0.1； """ 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 # 定義網絡結構，為輸入x創建一個維度為n_input的placeholder，然后 # 建立一個能提取特征的隱含層。 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']) # 首先，定義自編碼器的損失函數，在此直接使用平方誤差(SquaredError)作為cost。 # 然后，定義訓練操作作為優化器self.optimizer對損失self.cost進行優化。 # 最后，創建Session，並初始化自編碼器全部模型參數。 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}) # 定義一個transform函數，以便返回自編碼器隱含層的輸出結果，目的是提供一個接口來獲取抽象后的特征。 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): # 獲取隱含層的權重w1. return self.sess.run(self.weights['w1']) def getBiases(self): # 獲取隱含層的偏執系數b1. return self.sess.run(self.weights['b1']) # 利用TensorFlow提供的讀取示例數據的函數載入MNIST數據集。 mnist = input_data.read_data_sets('MNIST_data', one_hot=True) # 定義一個對訓練、測試數據進行標准化處理的函數。 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)) # 最后對訓練完的模型進行性能測試。 print("Total cost: " + str(autoencoder.calc_total_cost(X_test)))
[1] 黃文堅.TensorFlow實戰.北京：電子工業出版社
[2] https://blog.csdn.net/qq_37608890/article/details/79352212