-
Notifications
You must be signed in to change notification settings - Fork 0
/
test2.py
243 lines (203 loc) · 10.5 KB
/
test2.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
import numpy as np
import matplotlib.pylab as plt
import gzip
import cPickle
import tensorflow as tf
import input_data
def xavier_init(fan_in, fan_out, constant=1):
""" Xavier initialization of network weights"""
# https://stackoverflow.com/questions/33640581/how-to-do-xavier-initialization-on-tensorflow
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 VariationalAutoencoder(object):
""" Variation Autoencoder (VAE) with an sklearn-like interface implemented using TensorFlow.
This implementation uses probabilistic encoders and decoders using Gaussian
distributions and realized by multi-layer perceptrons. The VAE can be learned
end-to-end.
See "Auto-Encoding Variational Bayes" by Kingma and Welling for more details.
"""
def __init__(self, network_architecture, transfer_fct=tf.nn.softplus,
learning_rate=0.001, batch_size=100):
self.network_architecture = network_architecture
self.transfer_fct = transfer_fct
self.learning_rate = learning_rate
self.batch_size = batch_size
# tf Graph input
self.x = tf.placeholder(tf.float32, [None, network_architecture["n_input"]])
# Create autoencoder network
self._create_network()
# Define loss function based variational upper-bound and
# corresponding optimizer
self._create_loss_optimizer()
# Initializing the tensor flow variables
init = tf.initialize_all_variables()
# Launch the session
self.sess = tf.InteractiveSession()
self.sess.run(init)
def _create_network(self):
# Initialize autoencode network weights and biases
network_weights = self._initialize_weights(**self.network_architecture)
# Use recognition network to determine mean and
# (log) variance of Gaussian distribution in latent
# space
self.z_mean, self.z_log_sigma_sq = \
self._recognition_network(network_weights["weights_recog"],
network_weights["biases_recog"])
# Draw one sample z from Gaussian distribution
n_z = self.network_architecture["n_z"]
eps = tf.random_normal((self.batch_size, n_z), 0, 1,
dtype=tf.float32)
# z = mu + sigma*epsilon
self.z = tf.add(self.z_mean,
tf.mul(tf.sqrt(tf.exp(self.z_log_sigma_sq)), eps))
# Use generator to determine mean of
# Bernoulli distribution of reconstructed input
self.x_reconstr_mean = \
self._generator_network(network_weights["weights_gener"],
network_weights["biases_gener"])
def _initialize_weights(self, n_hidden_recog_1, n_hidden_recog_2,
n_hidden_gener_1, n_hidden_gener_2,
n_input, n_z):
all_weights = dict()
all_weights['weights_recog'] = {
'h1': tf.Variable(xavier_init(n_input, n_hidden_recog_1)),
'h2': tf.Variable(xavier_init(n_hidden_recog_1, n_hidden_recog_2)),
'out_mean': tf.Variable(xavier_init(n_hidden_recog_2, n_z)),
'out_log_sigma': tf.Variable(xavier_init(n_hidden_recog_2, n_z))}
all_weights['biases_recog'] = {
'b1': tf.Variable(tf.zeros([n_hidden_recog_1], dtype=tf.float32)),
'b2': tf.Variable(tf.zeros([n_hidden_recog_2], dtype=tf.float32)),
'out_mean': tf.Variable(tf.zeros([n_z], dtype=tf.float32)),
'out_log_sigma': tf.Variable(tf.zeros([n_z], dtype=tf.float32))}
all_weights['weights_gener'] = {
'h1': tf.Variable(xavier_init(n_z, n_hidden_gener_1)),
'h2': tf.Variable(xavier_init(n_hidden_gener_1, n_hidden_gener_2)),
'out_mean': tf.Variable(xavier_init(n_hidden_gener_2, n_input)),
'out_log_sigma': tf.Variable(xavier_init(n_hidden_gener_2, n_input))}
all_weights['biases_gener'] = {
'b1': tf.Variable(tf.zeros([n_hidden_gener_1], dtype=tf.float32)),
'b2': tf.Variable(tf.zeros([n_hidden_gener_2], dtype=tf.float32)),
'out_mean': tf.Variable(tf.zeros([n_input], dtype=tf.float32)),
'out_log_sigma': tf.Variable(tf.zeros([n_input], dtype=tf.float32))}
return all_weights
def _recognition_network(self, weights, biases):
# Generate probabilistic encoder (recognition network), which
# maps inputs onto a normal distribution in latent space.
# The transformation is parametrized and can be learned.
layer_1 = self.transfer_fct(tf.add(tf.matmul(self.x, weights['h1']),
biases['b1']))
layer_2 = self.transfer_fct(tf.add(tf.matmul(layer_1, weights['h2']),
biases['b2']))
z_mean = tf.add(tf.matmul(layer_2, weights['out_mean']),
biases['out_mean'])
z_log_sigma_sq = \
tf.add(tf.matmul(layer_2, weights['out_log_sigma']),
biases['out_log_sigma'])
return (z_mean, z_log_sigma_sq)
def _generator_network(self, weights, biases):
# Generate probabilistic decoder (decoder network), which
# maps points in latent space onto a Bernoulli distribution in data space.
# The transformation is parametrized and can be learned.
layer_1 = self.transfer_fct(tf.add(tf.matmul(self.z, weights['h1']),
biases['b1']))
layer_2 = self.transfer_fct(tf.add(tf.matmul(layer_1, weights['h2']),
biases['b2']))
x_reconstr_mean = \
tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['out_mean']),
biases['out_mean']))
return x_reconstr_mean
def _create_loss_optimizer(self):
# The loss is composed of two terms:
# 1.) The reconstruction loss (the negative log probability
# of the input under the reconstructed Bernoulli distribution
# induced by the decoder in the data space).
# This can be interpreted as the number of "nats" required
# for reconstructing the input when the activation in latent
# is given.
# Adding 1e-10 to avoid evaluatio of log(0.0)
reconstr_loss = \
-tf.reduce_sum(self.x * tf.log(1e-10 + self.x_reconstr_mean)
+ (1-self.x) * tf.log(1e-10 + 1 - self.x_reconstr_mean),
1)
# 2.) The latent loss, which is defined as the Kullback Leibler divergence
## between the distribution in latent space induced by the encoder on
# the data and some prior. This acts as a kind of regularizer.
# This can be interpreted as the number of "nats" required
# for transmitting the the latent space distribution given
# the prior.
latent_loss = -0.5 * tf.reduce_sum(1 + self.z_log_sigma_sq
- tf.square(self.z_mean)
- tf.exp(self.z_log_sigma_sq), 1)
self.cost = tf.reduce_mean(reconstr_loss + latent_loss) # average over batch
# Use ADAM optimizer
self.optimizer = \
tf.train.AdamOptimizer(learning_rate=self.learning_rate).minimize(self.cost)
def partial_fit(self, X):
"""Train model based on mini-batch of input data.
Return cost of mini-batch.
"""
opt, cost = self.sess.run((self.optimizer, self.cost),
feed_dict={self.x: X})
return cost
def transform(self, X):
"""Transform data by mapping it into the latent space."""
# Note: This maps to mean of distribution, we could alternatively
# sample from Gaussian distribution
return self.sess.run(self.z_mean, feed_dict={self.x: X})
def generate(self, z_mu=None):
""" Generate data by sampling from latent space.
If z_mu is not None, data for this point in latent space is
generated. Otherwise, z_mu is drawn from prior in latent
space.
"""
if z_mu is None:
z_mu = np.random.normal(size=self.network_architecture["n_z"])
# Note: This maps to mean of distribution, we could alternatively
# sample from Gaussian distribution
return self.sess.run(self.x_reconstr_mean,
feed_dict={self.z: z_mu})
def reconstruct(self, X):
""" Use VAE to reconstruct given data. """
return self.sess.run(self.x_reconstr_mean,
feed_dict={self.x: X})
def train(network_architecture, learning_rate=0.001,
batch_size=100, training_epochs=10, display_step=5):
vae = VariationalAutoencoder(network_architecture,
learning_rate=learning_rate,
batch_size=batch_size)
# Training cycle
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, _ = mnist.train.next_batch(batch_size)
# Fit training using batch data
cost = vae.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)
return vae
#f = gzip.open('mnist.pkl.gz', 'rb')
#train_set, valid_set, test_set = cPickle.load(f)
#f.close()
#data = train_set[0]
#labels = train_set[1]
#n_samples = data.shape[0]
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
n_samples = mnist.train.num_examples
network_architecture = \
dict(n_hidden_recog_1=50, # 1st layer encoder neurons
n_hidden_recog_2=50, # 2nd layer encoder neurons
n_hidden_gener_1=50, # 1st layer decoder neurons
n_hidden_gener_2=50, # 2nd layer decoder neurons
n_input=784, # MNIST data input (img shape: 28*28)
n_z=20) # dimensionality of latent space
vae = train(network_architecture, training_epochs=0)
saver = tf.train.Saver()
#saver.restore(vae.sess, 'ae.ae')
#print("Model restored.")