Autoencoders

.gitignore

@@ -0,0 +1,2 @@
+autoencoder/MNIST_data/*
+*.pyc

README

@@ -0,0 +1 @@
+Very simple implementations of some autoencoder variations

autoencoder/AdditiveGaussianNoiseAutoencoderRunner.py

@@ -0,0 +1,51 @@
+import numpy as np
+
+import sklearn.preprocessing as prep
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+
+from autoencoder.autoencoder_models.DenoisingAutoencoder import AdditiveGaussianNoiseAutoencoder
+
+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))

autoencoder/AutoencoderRunner.py

@@ -0,0 +1,50 @@
+import numpy as np
+
+import sklearn.preprocessing as prep
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+
+from autoencoder.autoencoder_models.Autoencoder import Autoencoder
+
+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 = Autoencoder(n_input = 784,
+                          n_hidden = 200,
+                          transfer_function = tf.nn.softplus,
+                          optimizer = tf.train.AdamOptimizer(learning_rate = 0.001))
+
+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))

autoencoder/MaskingNoiseAutoencoderRunner.py

@@ -0,0 +1,49 @@
+import numpy as np
+
+import sklearn.preprocessing as prep
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+
+from autoencoder.autoencoder_models.DenoisingAutoencoder import MaskingNoiseAutoencoder
+
+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 = 100
+batch_size = 128
+display_step = 1
+
+autoencoder = MaskingNoiseAutoencoder(n_input = 784,
+                                      n_hidden = 200,
+                                      transfer_function = tf.nn.softplus,
+                                      optimizer = tf.train.AdamOptimizer(learning_rate = 0.001),
+                                      dropout_probability = 0.95)
+
+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_size
+
+    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))

autoencoder/Utils.py

@@ -0,0 +1,9 @@
+import numpy as np
+import tensorflow as tf
+
+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)

autoencoder/VariationalAutoencoderRunner.py

@@ -0,0 +1,53 @@
+import numpy as np
+
+import sklearn.preprocessing as prep
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+
+from autoencoder.autoencoder_models.VariationalAutoencoder import VariationalAutoencoder
+
+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 = VariationalAutoencoder(n_input = 784,
+                                     n_hidden = 200,
+                                     optimizer = tf.train.AdamOptimizer(learning_rate = 0.001),
+                                     gaussian_sample_size = 128)
+
+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))

autoencoder/autoencoder_models/Autoencoder.py

@@ -0,0 +1,60 @@
+import tensorflow as tf
+import numpy as np
+import autoencoder.Utils
+
+class Autoencoder(object):
+
+    def __init__(self, n_input, n_hidden, transfer_function=tf.nn.softplus, optimizer = tf.train.AdamOptimizer()):
+        self.n_input = n_input
+        self.n_hidden = n_hidden
+        self.transfer = transfer_function
+
+        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, 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.sub(self.reconstruction, self.x), 2.0))
+        self.optimizer = optimizer.minimize(self.cost)
+
+        init = tf.initialize_all_variables()
+        self.sess = tf.Session()
+        self.sess.run(init)
+
+
+    def _initialize_weights(self):
+        all_weights = dict()
+        all_weights['w1'] = tf.Variable(autoencoder.Utils.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})
+        return cost
+
+    def calc_total_cost(self, X):
+        return self.sess.run(self.cost, feed_dict = {self.x: X})
+
+    def transform(self, X):
+        return self.sess.run(self.hidden, feed_dict={self.x: X})
+
+    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})
+
+    def getWeights(self):
+        return self.sess.run(self.weights['w1'])
+
+    def getBiases(self):
+        return self.sess.run(self.weights['b1'])
+