Skip to content
Navigation Menu
{{ message }}
forked from MichalDanielDobrzanski/DeepLearningPython
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathnetwork3.py
More file actions
314 lines (272 loc) · 12.8 KB
/
Copy pathnetwork3.py
File metadata and controls
314 lines (272 loc) · 12.8 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
"""network3.py
~~~~~~~~~~~~~~
A Aesara-based program for training and running simple neural
networks.
Supports several layer types (fully connected, convolutional, max
pooling, softmax), and activation functions (sigmoid, tanh, and
rectified linear units, with more easily added).
When run on a CPU, this program is much faster than network.py and
network2.py. However, unlike network.py and network2.py it can also
be run on a GPU, which makes it faster still.
Because the code is based on Aesara, the code is different in many
ways from network.py and network2.py. However, where possible I have
tried to maintain consistency with the earlier programs. In
particular, the API is similar to network2.py. Note that I have
focused on making the code simple, easily readable, and easily
modifiable. It is not optimized, and omits many desirable features.
This program incorporates ideas from the Aesara documentation on
convolutional neural nets (notably,
http://deeplearning.net/tutorial/lenet.html ), from Misha Denil's
implementation of dropout (https://github.com/mdenil/dropout ), and
from Chris Olah (http://colah.github.io ).
"""
#### Libraries
# Standard library
import pickle
import gzip
# Third-party libraries
import numpy as np
import aesara
import aesara.tensor as T
from aesara.tensor.nnet import conv2d
from aesara.tensor.nnet import softmax
from aesara.tensor.random.utils import RandomStream
from aesara.tensor.signal.pool import pool_2d
# Activation functions for neurons
def linear(z): return z
from aesara.tensor.nnet import relu as ReLU
from aesara.tensor import sigmoid
from aesara.tensor import tanh
#### Constants
GPU = True
if GPU:
print("Trying to run under a GPU. If this is not desired, then modify "+\
"network3.py\nto set the GPU flag to False.")
try: aesara.config.device = 'gpu'
except: pass # it's already set
aesara.config.floatX = 'float32'
else:
print("Running with a CPU. If this is not desired, then the modify "+\
"network3.py to set\nthe GPU flag to True.")
aesara.config.gcc__cxxflags = "-Wno-c++11-narrowing" #Required for apple silicon
#### Load the MNIST data
def load_data_shared(filename="mnist.pkl.gz"):
f = gzip.open(filename, 'rb')
training_data, validation_data, test_data = pickle.load(f, encoding="latin1")
f.close()
def shared(data):
"""Place the data into shared variables. This allows Aesara to copy
the data to the GPU, if one is available.
"""
shared_x = aesara.shared(
np.asarray(data[0], dtype=aesara.config.floatX), borrow=True)
shared_y = aesara.shared(
np.asarray(data[1], dtype=aesara.config.floatX), borrow=True)
return shared_x, T.cast(shared_y, "int32")
return [shared(training_data), shared(validation_data), shared(test_data)]
#### Main class used to construct and train networks
class Network(object):
def __init__(self, layers, mini_batch_size):
"""Takes a list of `layers`, describing the network architecture, and
a value for the `mini_batch_size` to be used during training
by stochastic gradient descent.
"""
self.layers = layers
self.mini_batch_size = mini_batch_size
self.params = [param for layer in self.layers for param in layer.params]
self.x = T.matrix("x")
self.y = T.ivector("y")
init_layer = self.layers[0]
init_layer.set_inpt(self.x, self.x, self.mini_batch_size)
for j in range(1, len(self.layers)): # xrange() was renamed to range() in Python 3.
prev_layer, layer = self.layers[j-1], self.layers[j]
layer.set_inpt(
prev_layer.output, prev_layer.output_dropout, self.mini_batch_size)
self.output = self.layers[-1].output
self.output_dropout = self.layers[-1].output_dropout
def SGD(self, training_data, epochs, mini_batch_size, eta,
validation_data, test_data, lmbda=0.0):
"""Train the network using mini-batch stochastic gradient descent."""
training_x, training_y = training_data
validation_x, validation_y = validation_data
test_x, test_y = test_data
# compute number of minibatches for training, validation and testing
num_training_batches = int(size(training_data)/mini_batch_size)
num_validation_batches = int(size(validation_data)/mini_batch_size)
num_test_batches = int(size(test_data)/mini_batch_size)
# define the (regularized) cost function, symbolic gradients, and updates
l2_norm_squared = sum([(layer.w**2).sum() for layer in self.layers])
cost = self.layers[-1].cost(self)+\
0.5*lmbda*l2_norm_squared/num_training_batches
grads = T.grad(cost, self.params)
updates = [(param, param-eta*grad)
for param, grad in zip(self.params, grads)]
# define functions to train a mini-batch, and to compute the
# accuracy in validation and test mini-batches.
i = T.lscalar() # mini-batch index
train_mb = aesara.function(
[i], cost, updates=updates,
givens={
self.x:
training_x[i*self.mini_batch_size: (i+1)*self.mini_batch_size],
self.y:
training_y[i*self.mini_batch_size: (i+1)*self.mini_batch_size]
})
validate_mb_accuracy = aesara.function(
[i], self.layers[-1].accuracy(self.y),
givens={
self.x:
validation_x[i*self.mini_batch_size: (i+1)*self.mini_batch_size],
self.y:
validation_y[i*self.mini_batch_size: (i+1)*self.mini_batch_size]
})
test_mb_accuracy = aesara.function(
[i], self.layers[-1].accuracy(self.y),
givens={
self.x:
test_x[i*self.mini_batch_size: (i+1)*self.mini_batch_size],
self.y:
test_y[i*self.mini_batch_size: (i+1)*self.mini_batch_size]
})
self.test_mb_predictions = aesara.function(
[i], self.layers[-1].y_out,
givens={
self.x:
test_x[i*self.mini_batch_size: (i+1)*self.mini_batch_size]
})
# Do the actual training
best_validation_accuracy = 0.0
for epoch in range(epochs):
for minibatch_index in range(num_training_batches):
iteration = num_training_batches*epoch+minibatch_index
if iteration % 1000 == 0:
print("Training mini-batch number {0}".format(iteration))
cost_ij = train_mb(minibatch_index)
if (iteration+1) % num_training_batches == 0:
validation_accuracy = np.mean(
[validate_mb_accuracy(j) for j in range(num_validation_batches)])
print("Epoch {0}: validation accuracy {1:.2%}".format(
epoch, validation_accuracy))
if validation_accuracy >= best_validation_accuracy:
print("This is the best validation accuracy to date.")
best_validation_accuracy = validation_accuracy
best_iteration = iteration
if test_data:
test_accuracy = np.mean(
[test_mb_accuracy(j) for j in range(num_test_batches)])
print('The corresponding test accuracy is {0:.2%}'.format(
test_accuracy))
print("Finished training network.")
print("Best validation accuracy of {0:.2%} obtained at iteration {1}".format(
best_validation_accuracy, best_iteration))
print("Corresponding test accuracy of {0:.2%}".format(test_accuracy))
#### Define layer types
class ConvPoolLayer(object):
"""Used to create a combination of a convolutional and a max-pooling
layer. A more sophisticated implementation would separate the
two, but for our purposes we'll always use them together, and it
simplifies the code, so it makes sense to combine them.
"""
def __init__(self, filter_shape, image_shape, poolsize=(2, 2),
activation_fn=sigmoid):
"""`filter_shape` is a tuple of length 4, whose entries are the number
of filters, the number of input feature maps, the filter height, and the
filter width.
`image_shape` is a tuple of length 4, whose entries are the
mini-batch size, the number of input feature maps, the image
height, and the image width.
`poolsize` is a tuple of length 2, whose entries are the y and
x pooling sizes.
"""
self.filter_shape = filter_shape
self.image_shape = image_shape
self.poolsize = poolsize
self.activation_fn=activation_fn
# initialize weights and biases
n_out = (filter_shape[0]*np.prod(filter_shape[2:])/np.prod(poolsize))
self.w = aesara.shared(
np.asarray(
np.random.normal(loc=0, scale=np.sqrt(1.0/n_out), size=filter_shape),
dtype=aesara.config.floatX),
borrow=True)
self.b = aesara.shared(
np.asarray(
np.random.normal(loc=0, scale=1.0, size=(filter_shape[0],)),
dtype=aesara.config.floatX),
borrow=True)
self.params = [self.w, self.b]
def set_inpt(self, inpt, inpt_dropout, mini_batch_size):
self.inpt = inpt.reshape(self.image_shape)
conv_out = conv2d(
input=self.inpt, filters=self.w, filter_shape=self.filter_shape,
input_shape=self.image_shape)
pooled_out = pool_2d(
input=conv_out, ws=self.poolsize, ignore_border=True)
self.output = self.activation_fn(
pooled_out + self.b.dimshuffle('x', 0, 'x', 'x'))
self.output_dropout = self.output # no dropout in the convolutional layers
class FullyConnectedLayer(object):
def __init__(self, n_in, n_out, activation_fn=sigmoid, p_dropout=0.0):
self.n_in = n_in
self.n_out = n_out
self.activation_fn = activation_fn
self.p_dropout = p_dropout
# Initialize weights and biases
self.w = aesara.shared(
np.asarray(
np.random.normal(
loc=0.0, scale=np.sqrt(1.0/n_out), size=(n_in, n_out)),
dtype=aesara.config.floatX),
name='w', borrow=True)
self.b = aesara.shared(
np.asarray(np.random.normal(loc=0.0, scale=1.0, size=(n_out,)),
dtype=aesara.config.floatX),
name='b', borrow=True)
self.params = [self.w, self.b]
def set_inpt(self, inpt, inpt_dropout, mini_batch_size):
self.inpt = inpt.reshape((mini_batch_size, self.n_in))
self.output = self.activation_fn(
(1-self.p_dropout)*T.dot(self.inpt, self.w) + self.b)
self.y_out = T.argmax(self.output, axis=1)
self.inpt_dropout = dropout_layer(
inpt_dropout.reshape((mini_batch_size, self.n_in)), self.p_dropout)
self.output_dropout = self.activation_fn(
T.dot(self.inpt_dropout, self.w) + self.b)
def accuracy(self, y):
"Return the accuracy for the mini-batch."
return T.mean(T.eq(y, self.y_out))
class SoftmaxLayer(object):
def __init__(self, n_in, n_out, p_dropout=0.0):
self.n_in = n_in
self.n_out = n_out
self.p_dropout = p_dropout
# Initialize weights and biases
self.w = aesara.shared(
np.zeros((n_in, n_out), dtype=aesara.config.floatX),
name='w', borrow=True)
self.b = aesara.shared(
np.zeros((n_out,), dtype=aesara.config.floatX),
name='b', borrow=True)
self.params = [self.w, self.b]
def set_inpt(self, inpt, inpt_dropout, mini_batch_size):
self.inpt = inpt.reshape((mini_batch_size, self.n_in))
self.output = softmax((1-self.p_dropout)*T.dot(self.inpt, self.w) + self.b, axis=-1)
self.y_out = T.argmax(self.output, axis=1)
self.inpt_dropout = dropout_layer(
inpt_dropout.reshape((mini_batch_size, self.n_in)), self.p_dropout)
self.output_dropout = softmax(T.dot(self.inpt_dropout, self.w) + self.b, axis=-1)
def cost(self, net):
"Return the log-likelihood cost."
return -T.mean(T.log(self.output_dropout)[T.arange(net.y.shape[0]), net.y])
def accuracy(self, y):
"Return the accuracy for the mini-batch."
return T.mean(T.eq(y, self.y_out))
#### Miscellanea
def size(data):
"Return the size of the dataset `data`."
return data[0].get_value(borrow=True).shape[0]
def dropout_layer(layer, p_dropout):
srng = RandomStream(
np.random.RandomState(0).randint(999999))
mask = srng.binomial(1, 1-p_dropout, size=layer.shape)
return layer*T.cast(mask, aesara.config.floatX)
You can’t perform that action at this time.