Skip to content
Navigation Menu
{{ message }}
forked from lisa-lab/DeepLearningTutorials
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathDBN.py
More file actions
384 lines (299 loc) · 15.5 KB
/
Copy pathDBN.py
File metadata and controls
384 lines (299 loc) · 15.5 KB
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
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
"""
"""
import os
import numpy, time, cPickle, gzip, os, sys
import theano
import theano.tensor as T
from theano.tensor.shared_randomstreams import RandomStreams
from logistic_sgd import LogisticRegression, load_data
from mlp import HiddenLayer
from rbm import RBM
class DBN(object):
"""Deep Belief Network
A deep belief network is obtained by stacking several RBMs on top of each
other. The hidden layer of the RBM at layer `i` becomes the input of the
RBM at layer `i+1`. The first layer RBM gets as input the input of the
network, and the hidden layer of the last RBM represents the output. When
used for classification, the DBN is treated as a MLP, by adding a logistic
regression layer on top.
"""
def __init__(self, numpy_rng, theano_rng = None, n_ins = 784,
hidden_layers_sizes = [500,500], n_outs = 10):
"""This class is made to support a variable number of layers.
:type numpy_rng: numpy.random.RandomState
:param numpy_rng: numpy random number generator used to draw initial
weights
:type theano_rng: theano.tensor.shared_randomstreams.RandomStreams
:param theano_rng: Theano random generator; if None is given one is
generated based on a seed drawn from `rng`
:type n_ins: int
:param n_ins: dimension of the input to the DBN
:type n_layers_sizes: list of ints
:param n_layers_sizes: intermediate layers size, must contain
at least one value
:type n_outs: int
:param n_outs: dimension of the output of the network
"""
self.sigmoid_layers = []
self.rbm_layers = []
self.params = []
self.n_layers = len(hidden_layers_sizes)
assert self.n_layers > 0
if not theano_rng:
theano_rng = RandomStreams(numpy_rng.randint(2**30))
# allocate symbolic variables for the data
self.x = T.matrix('x') # the data is presented as rasterized images
self.y = T.ivector('y') # the labels are presented as 1D vector of
# [int] labels
# The DBN is an MLP, for which all weights of intermediate layers are shared with a
# different RBM. We will first construct the DBN as a deep multilayer perceptron, and
# when constructing each sigmoidal layer we also construct an RBM that shares weights
# with that layer. During pretraining we will train these RBMs (which will lead
# to chainging the weights of the MLP as well) During finetuning we will finish
# training the DBN by doing stochastic gradient descent on the MLP.
for i in xrange( self.n_layers ):
# construct the sigmoidal layer
# the size of the input is either the number of hidden units of the layer below or
# the input size if we are on the first layer
if i == 0 :
input_size = n_ins
else:
input_size = hidden_layers_sizes[i-1]
# the input to this layer is either the activation of the hidden layer below or the
# input of the DBN if you are on the first layer
if i == 0 :
layer_input = self.x
else:
layer_input = self.sigmoid_layers[-1].output
sigmoid_layer = HiddenLayer(rng = numpy_rng,
input = layer_input,
n_in = input_size,
n_out = hidden_layers_sizes[i],
activation = T.nnet.sigmoid)
# add the layer to our list of layers
self.sigmoid_layers.append(sigmoid_layer)
# its arguably a philosophical question... but we are going to only declare that
# the parameters of the sigmoid_layers are parameters of the DBN. The visible
# biases in the RBM are parameters of those RBMs, but not of the DBN.
self.params.extend(sigmoid_layer.params)
# Construct an RBM that shared weights with this layer
rbm_layer = RBM(numpy_rng = numpy_rng, theano_rng = theano_rng,
input = layer_input,
n_visible = input_size,
n_hidden = hidden_layers_sizes[i],
W = sigmoid_layer.W,
hbias = sigmoid_layer.b)
self.rbm_layers.append(rbm_layer)
# We now need to add a logistic layer on top of the MLP
self.logLayer = LogisticRegression(\
input = self.sigmoid_layers[-1].output,\
n_in = hidden_layers_sizes[-1], n_out = n_outs)
self.params.extend(self.logLayer.params)
# compute the cost for second phase of training, defined as the
# negative log likelihood of the logistic regression (output) layer
self.finetune_cost = self.logLayer.negative_log_likelihood(self.y)
# compute the gradients with respect to the model parameters
# symbolic variable that points to the number of errors made on the
# minibatch given by self.x and self.y
self.errors = self.logLayer.errors(self.y)
def pretraining_functions(self, train_set_x, batch_size,k):
''' Generates a list of functions, for performing one step of gradient descent at a
given layer. The function will require as input the minibatch index, and to train an
RBM you just need to iterate, calling the corresponding function on all minibatch
indexes.
:type train_set_x: theano.tensor.TensorType
:param train_set_x: Shared var. that contains all datapoints used for training the RBM
:type batch_size: int
:param batch_size: size of a [mini]batch
:param k: number of Gibbs steps to do in CD-k / PCD-k
'''
# index to a [mini]batch
index = T.lscalar('index') # index to a minibatch
learning_rate = T.scalar('lr') # learning rate to use
# number of batches
n_batches = train_set_x.value.shape[0] / batch_size
# begining of a batch, given `index`
batch_begin = index * batch_size
# ending of a batch given `index`
batch_end = batch_begin+batch_size
pretrain_fns = []
for rbm in self.rbm_layers:
# get the cost and the updates list
# using CD-k here (persisent=None) for training each RBM.
# TODO: change cost function to reconstruction error
cost,updates = rbm.get_cost_updates(learning_rate, persistent=None, k =k)
# compile the theano function
fn = theano.function(inputs = [index,
theano.Param(learning_rate, default = 0.1)],
outputs = cost,
updates = updates,
givens = {self.x :train_set_x[batch_begin:batch_end]})
# append `fn` to the list of functions
pretrain_fns.append(fn)
return pretrain_fns
def build_finetune_functions(self, datasets, batch_size, learning_rate):
'''Generates a function `train` that implements one step of finetuning, a function
`validate` that computes the error on a batch from the validation set, and a function
`test` that computes the error on a batch from the testing set
:type datasets: list of pairs of theano.tensor.TensorType
:param datasets: It is a list that contain all the datasets; the has to contain three
pairs, `train`, `valid`, `test` in this order, where each pair is formed of two Theano
variables, one for the datapoints, the other for the labels
:type batch_size: int
:param batch_size: size of a minibatch
:type learning_rate: float
:param learning_rate: learning rate used during finetune stage
'''
(train_set_x, train_set_y) = datasets[0]
(valid_set_x, valid_set_y) = datasets[1]
(test_set_x , test_set_y ) = datasets[2]
# compute number of minibatches for training, validation and testing
n_valid_batches = valid_set_x.value.shape[0] / batch_size
n_test_batches = test_set_x.value.shape[0] / batch_size
index = T.lscalar('index') # index to a [mini]batch
# compute the gradients with respect to the model parameters
gparams = T.grad(self.finetune_cost, self.params)
# compute list of fine-tuning updates
updates = {}
for param, gparam in zip(self.params, gparams):
updates[param] = param - gparam*learning_rate
train_fn = theano.function(inputs = [index],
outputs = self.finetune_cost,
updates = updates,
givens = {
self.x : train_set_x[index*batch_size:(index+1)*batch_size],
self.y : train_set_y[index*batch_size:(index+1)*batch_size]})
test_score_i = theano.function([index], self.errors,
givens = {
self.x: test_set_x[index*batch_size:(index+1)*batch_size],
self.y: test_set_y[index*batch_size:(index+1)*batch_size]})
valid_score_i = theano.function([index], self.errors,
givens = {
self.x: valid_set_x[index*batch_size:(index+1)*batch_size],
self.y: valid_set_y[index*batch_size:(index+1)*batch_size]})
# Create a function that scans the entire validation set
def valid_score():
return [valid_score_i(i) for i in xrange(n_valid_batches)]
# Create a function that scans the entire test set
def test_score():
return [test_score_i(i) for i in xrange(n_test_batches)]
return train_fn, valid_score, test_score
def test_DBN( finetune_lr = 0.1, pretraining_epochs = 100, \
pretrain_lr = 0.01, k = 1, training_epochs = 1000, \
dataset='../data/mnist.pkl.gz', batch_size = 10):
"""
Demonstrates how to train and test a Deep Belief Network.
This is demonstrated on MNIST.
:type learning_rate: float
:param learning_rate: learning rate used in the finetune stage
:type pretraining_epochs: int
:param pretraining_epochs: number of epoch to do pretraining
:type pretrain_lr: float
:param pretrain_lr: learning rate to be used during pre-training
:type k: int
:param k: number of Gibbs steps in CD/PCD
:type training_epochs: int
:param training_epochs: maximal number of iterations ot run the optimizer
:type dataset: string
:param dataset: path the the pickled dataset
:type batch_size: int
:param batch_size: the size of a minibatch
"""
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
valid_set_x, valid_set_y = datasets[1]
test_set_x , test_set_y = datasets[2]
# compute number of minibatches for training, validation and testing
n_train_batches = train_set_x.value.shape[0] / batch_size
# numpy random generator
numpy_rng = numpy.random.RandomState(123)
print '... building the model'
# construct the Deep Belief Network
dbn = DBN(numpy_rng = numpy_rng, n_ins = 28*28,
hidden_layers_sizes = [1000,1000,1000],
n_outs = 10)
#########################
# PRETRAINING THE MODEL #
#########################
print '... getting the pretraining functions'
pretraining_fns = dbn.pretraining_functions(
train_set_x = train_set_x,
batch_size = batch_size,
k = k)
print '... pre-training the model'
start_time = time.clock()
## Pre-train layer-wise
for i in xrange(dbn.n_layers):
# go through pretraining epochs
for epoch in xrange(pretraining_epochs):
# go through the training set
c = []
for batch_index in xrange(n_train_batches):
c.append(pretraining_fns[i](index = batch_index,
lr = pretrain_lr ) )
print 'Pre-training layer %i, epoch %d, cost '%(i,epoch),numpy.mean(c)
end_time = time.clock()
print >> sys.stderr, ('The pretraining code for file '+os.path.split(__file__)[1]+' ran for %.2fm' % ((end_time-start_time)/60.))
########################
# FINETUNING THE MODEL #
########################
# get the training, validation and testing function for the model
print '... getting the finetuning functions'
train_fn, validate_model, test_model = dbn.build_finetune_functions (
datasets = datasets, batch_size = batch_size,
learning_rate = finetune_lr)
print '... finetunning the model'
# early-stopping parameters
patience = 4*n_train_batches # look as this many examples regardless
patience_increase = 2. # wait this much longer when a new best is
# found
improvement_threshold = 0.995 # a relative improvement of this much is
# considered significant
validation_frequency = min(n_train_batches, patience/2)
# go through this many
# minibatche before checking the network
# on the validation set; in this case we
# check every epoch
best_params = None
best_validation_loss = float('inf')
test_score = 0.
start_time = time.clock()
done_looping = False
epoch = 0
while (epoch < training_epochs) and (not done_looping):
epoch = epoch + 1
for minibatch_index in xrange(n_train_batches):
minibatch_avg_cost = train_fn(minibatch_index)
iter = epoch * n_train_batches + minibatch_index
if (iter+1) % validation_frequency == 0:
validation_losses = validate_model()
this_validation_loss = numpy.mean(validation_losses)
print('epoch %i, minibatch %i/%i, validation error %f %%' % \
(epoch, minibatch_index+1, n_train_batches, \
this_validation_loss*100.))
# if we got the best validation score until now
if this_validation_loss < best_validation_loss:
#improve patience if loss improvement is good enough
if this_validation_loss < best_validation_loss * \
improvement_threshold :
patience = max(patience, iter * patience_increase)
# save best validation score and iteration number
best_validation_loss = this_validation_loss
best_iter = iter
# test it on the test set
test_losses = test_model()
test_score = numpy.mean(test_losses)
print((' epoch %i, minibatch %i/%i, test error of best '
'model %f %%') %
(epoch, minibatch_index+1, n_train_batches,
test_score*100.))
if patience <= iter :
done_looping = True
break
end_time = time.clock()
print(('Optimization complete with best validation score of %f %%,'
'with test performance %f %%') %
(best_validation_loss * 100., test_score*100.))
print >> sys.stderr, ('The fine tuning code for file '+os.path.split(__file__)[1]+' ran for %.2fm' % ((end_time-start_time)/60.))
if __name__ == '__main__':
test_DBN()
You can’t perform that action at this time.