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 pathrnnrbm.py
More file actions
301 lines (251 loc) · 11.4 KB
/
Copy pathrnnrbm.py
File metadata and controls
301 lines (251 loc) · 11.4 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
# Author: Nicolas Boulanger-Lewandowski
# University of Montreal (2012)
# RNN-RBM deep learning tutorial
# More information at http://deeplearning.net/tutorial/rnnrbm.html
from __future__ import print_function
import glob
import os
import sys
import numpy
try:
import pylab
except ImportError:
print ("pylab isn't available. If you use its functionality, it will crash.")
print("It can be installed with 'pip install -q Pillow'")
from midi.utils import midiread, midiwrite
import theano
import theano.tensor as T
from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
#Don't use a python long as this don't work on 32 bits computers.
numpy.random.seed(0xbeef)
rng = RandomStreams(seed=numpy.random.randint(1 << 30))
theano.config.warn.subtensor_merge_bug = False
def build_rbm(v, W, bv, bh, k):
'''Construct a k-step Gibbs chain starting at v for an RBM.
v : Theano vector or matrix
If a matrix, multiple chains will be run in parallel (batch).
W : Theano matrix
Weight matrix of the RBM.
bv : Theano vector
Visible bias vector of the RBM.
bh : Theano vector
Hidden bias vector of the RBM.
k : scalar or Theano scalar
Length of the Gibbs chain.
Return a (v_sample, cost, monitor, updates) tuple:
v_sample : Theano vector or matrix with the same shape as `v`
Corresponds to the generated sample(s).
cost : Theano scalar
Expression whose gradient with respect to W, bv, bh is the CD-k
approximation to the log-likelihood of `v` (training example) under the
RBM. The cost is averaged in the batch case.
monitor: Theano scalar
Pseudo log-likelihood (also averaged in the batch case).
updates: dictionary of Theano variable -> Theano variable
The `updates` object returned by scan.'''
def gibbs_step(v):
mean_h = T.nnet.sigmoid(T.dot(v, W) + bh)
h = rng.binomial(size=mean_h.shape, n=1, p=mean_h,
dtype=theano.config.floatX)
mean_v = T.nnet.sigmoid(T.dot(h, W.T) + bv)
v = rng.binomial(size=mean_v.shape, n=1, p=mean_v,
dtype=theano.config.floatX)
return mean_v, v
chain, updates = theano.scan(lambda v: gibbs_step(v)[1], outputs_info=[v],
n_steps=k)
v_sample = chain[-1]
mean_v = gibbs_step(v_sample)[0]
monitor = T.xlogx.xlogy0(v, mean_v) + T.xlogx.xlogy0(1 - v, 1 - mean_v)
monitor = monitor.sum() / v.shape[0]
def free_energy(v):
return -(v * bv).sum() - T.log(1 + T.exp(T.dot(v, W) + bh)).sum()
cost = (free_energy(v) - free_energy(v_sample)) / v.shape[0]
return v_sample, cost, monitor, updates
def shared_normal(num_rows, num_cols, scale=1):
'''Initialize a matrix shared variable with normally distributed
elements.'''
return theano.shared(numpy.random.normal(
scale=scale, size=(num_rows, num_cols)).astype(theano.config.floatX))
def shared_zeros(*shape):
'''Initialize a vector shared variable with zero elements.'''
return theano.shared(numpy.zeros(shape, dtype=theano.config.floatX))
def build_rnnrbm(n_visible, n_hidden, n_hidden_recurrent):
'''Construct a symbolic RNN-RBM and initialize parameters.
n_visible : integer
Number of visible units.
n_hidden : integer
Number of hidden units of the conditional RBMs.
n_hidden_recurrent : integer
Number of hidden units of the RNN.
Return a (v, v_sample, cost, monitor, params, updates_train, v_t,
updates_generate) tuple:
v : Theano matrix
Symbolic variable holding an input sequence (used during training)
v_sample : Theano matrix
Symbolic variable holding the negative particles for CD log-likelihood
gradient estimation (used during training)
cost : Theano scalar
Expression whose gradient (considering v_sample constant) corresponds
to the LL gradient of the RNN-RBM (used during training)
monitor : Theano scalar
Frame-level pseudo-likelihood (useful for monitoring during training)
params : tuple of Theano shared variables
The parameters of the model to be optimized during training.
updates_train : dictionary of Theano variable -> Theano variable
Update object that should be passed to theano.function when compiling
the training function.
v_t : Theano matrix
Symbolic variable holding a generated sequence (used during sampling)
updates_generate : dictionary of Theano variable -> Theano variable
Update object that should be passed to theano.function when compiling
the generation function.'''
W = shared_normal(n_visible, n_hidden, 0.01)
bv = shared_zeros(n_visible)
bh = shared_zeros(n_hidden)
Wuh = shared_normal(n_hidden_recurrent, n_hidden, 0.0001)
Wuv = shared_normal(n_hidden_recurrent, n_visible, 0.0001)
Wvu = shared_normal(n_visible, n_hidden_recurrent, 0.0001)
Wuu = shared_normal(n_hidden_recurrent, n_hidden_recurrent, 0.0001)
bu = shared_zeros(n_hidden_recurrent)
params = W, bv, bh, Wuh, Wuv, Wvu, Wuu, bu # learned parameters as shared
# variables
v = T.matrix() # a training sequence
u0 = T.zeros((n_hidden_recurrent,)) # initial value for the RNN hidden
# units
# If `v_t` is given, deterministic recurrence to compute the variable
# biases bv_t, bh_t at each time step. If `v_t` is None, same recurrence
# but with a separate Gibbs chain at each time step to sample (generate)
# from the RNN-RBM. The resulting sample v_t is returned in order to be
# passed down to the sequence history.
def recurrence(v_t, u_tm1):
bv_t = bv + T.dot(u_tm1, Wuv)
bh_t = bh + T.dot(u_tm1, Wuh)
generate = v_t is None
if generate:
v_t, _, _, updates = build_rbm(T.zeros((n_visible,)), W, bv_t,
bh_t, k=25)
u_t = T.tanh(bu + T.dot(v_t, Wvu) + T.dot(u_tm1, Wuu))
return ([v_t, u_t], updates) if generate else [u_t, bv_t, bh_t]
# For training, the deterministic recurrence is used to compute all the
# {bv_t, bh_t, 1 <= t <= T} given v. Conditional RBMs can then be trained
# in batches using those parameters.
(u_t, bv_t, bh_t), updates_train = theano.scan(
lambda v_t, u_tm1, *_: recurrence(v_t, u_tm1),
sequences=v, outputs_info=[u0, None, None], non_sequences=params)
v_sample, cost, monitor, updates_rbm = build_rbm(v, W, bv_t[:], bh_t[:],
k=15)
updates_train.update(updates_rbm)
# symbolic loop for sequence generation
(v_t, u_t), updates_generate = theano.scan(
lambda u_tm1, *_: recurrence(None, u_tm1),
outputs_info=[None, u0], non_sequences=params, n_steps=200)
return (v, v_sample, cost, monitor, params, updates_train, v_t,
updates_generate)
class RnnRbm:
'''Simple class to train an RNN-RBM from MIDI files and to generate sample
sequences.'''
def __init__(
self,
n_hidden=150,
n_hidden_recurrent=100,
lr=0.001,
r=(21, 109),
dt=0.3
):
'''Constructs and compiles Theano functions for training and sequence
generation.
n_hidden : integer
Number of hidden units of the conditional RBMs.
n_hidden_recurrent : integer
Number of hidden units of the RNN.
lr : float
Learning rate
r : (integer, integer) tuple
Specifies the pitch range of the piano-roll in MIDI note numbers,
including r[0] but not r[1], such that r[1]-r[0] is the number of
visible units of the RBM at a given time step. The default (21,
109) corresponds to the full range of piano (88 notes).
dt : float
Sampling period when converting the MIDI files into piano-rolls, or
equivalently the time difference between consecutive time steps.'''
self.r = r
self.dt = dt
(v, v_sample, cost, monitor, params, updates_train, v_t,
updates_generate) = build_rnnrbm(
r[1] - r[0],
n_hidden,
n_hidden_recurrent
)
gradient = T.grad(cost, params, consider_constant=[v_sample])
updates_train.update(
((p, p - lr * g) for p, g in zip(params, gradient))
)
self.train_function = theano.function(
[v],
monitor,
updates=updates_train
)
self.generate_function = theano.function(
[],
v_t,
updates=updates_generate
)
def train(self, files, batch_size=100, num_epochs=200):
'''Train the RNN-RBM via stochastic gradient descent (SGD) using MIDI
files converted to piano-rolls.
files : list of strings
List of MIDI files that will be loaded as piano-rolls for training.
batch_size : integer
Training sequences will be split into subsequences of at most this
size before applying the SGD updates.
num_epochs : integer
Number of epochs (pass over the training set) performed. The user
can safely interrupt training with Ctrl+C at any time.'''
assert len(files) > 0, 'Training set is empty!' \
' (did you download the data files?)'
dataset = [midiread(f, self.r,
self.dt).piano_roll.astype(theano.config.floatX)
for f in files]
try:
for epoch in range(num_epochs):
numpy.random.shuffle(dataset)
costs = []
for s, sequence in enumerate(dataset):
for i in range(0, len(sequence), batch_size):
cost = self.train_function(sequence[i:i + batch_size])
costs.append(cost)
print('Epoch %i/%i' % (epoch + 1, num_epochs))
print(numpy.mean(costs))
sys.stdout.flush()
except KeyboardInterrupt:
print('Interrupted by user.')
def generate(self, filename, show=True):
'''Generate a sample sequence, plot the resulting piano-roll and save
it as a MIDI file.
filename : string
A MIDI file will be created at this location.
show : boolean
If True, a piano-roll of the generated sequence will be shown.'''
piano_roll = self.generate_function()
midiwrite(filename, piano_roll, self.r, self.dt)
if show:
extent = (0, self.dt * len(piano_roll)) + self.r
pylab.figure()
pylab.imshow(piano_roll.T, origin='lower', aspect='auto',
interpolation='nearest', cmap=pylab.cm.gray_r,
extent=extent)
pylab.xlabel('time (s)')
pylab.ylabel('MIDI note number')
pylab.title('generated piano-roll')
def test_rnnrbm(batch_size=100, num_epochs=200):
model = RnnRbm()
re = os.path.join(os.path.split(os.path.dirname(__file__))[0],
'data', 'Nottingham', 'train', '*.mid')
model.train(glob.glob(re),
batch_size=batch_size, num_epochs=num_epochs)
return model
if __name__ == '__main__':
model = test_rnnrbm()
model.generate('sample1.mid')
model.generate('sample2.mid')
pylab.show()
You can’t perform that action at this time.