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
|
from __future__ import print_function
import numpy as np
import pytest
import string
from keras.utils.test_utils import get_test_data
from keras.utils.np_utils import to_categorical
from keras.models import Sequential
from keras import layers, optimizers
import keras.backend as K
import keras
def test_temporal_classification():
'''
Classify temporal sequences of float numbers
of length 3 into 2 classes using
single layer of GRU units and softmax applied
to the last activations of the units
'''
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = get_test_data(num_train=200,
num_test=20,
input_shape=(3, 4),
classification=True,
num_classes=2)
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
model = Sequential()
model.add(layers.GRU(8,
input_shape=(x_train.shape[1], x_train.shape[2])))
model.add(layers.Dense(y_train.shape[-1], activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.summary()
history = model.fit(x_train, y_train, epochs=5, batch_size=10,
validation_data=(x_test, y_test),
verbose=0)
assert(history.history['accuracy'][-1] >= 0.8)
config = model.get_config()
model = Sequential.from_config(config)
def test_temporal_classification_functional():
'''
Classify temporal sequences of float numbers
of length 3 into 2 classes using
single layer of GRU units and softmax applied
to the last activations of the units
'''
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = get_test_data(num_train=200,
num_test=20,
input_shape=(3, 4),
classification=True,
num_classes=2)
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
inputs = layers.Input(shape=(x_train.shape[1], x_train.shape[2]))
x = layers.SimpleRNN(8)(inputs)
outputs = layers.Dense(y_train.shape[-1], activation='softmax')(x)
model = keras.models.Model(inputs, outputs)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs=5, batch_size=10,
validation_data=(x_test, y_test),
verbose=0)
assert(history.history['accuracy'][-1] >= 0.75)
def test_temporal_regression():
'''
Predict float numbers (regression) based on sequences
of float numbers of length 3 using a single layer of GRU units
'''
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = get_test_data(num_train=200,
num_test=20,
input_shape=(3, 5),
output_shape=(2,),
classification=False)
model = Sequential()
model.add(layers.LSTM(y_train.shape[-1],
input_shape=(x_train.shape[1], x_train.shape[2])))
model.compile(loss='hinge', optimizer='adam')
history = model.fit(x_train, y_train, epochs=5, batch_size=16,
validation_data=(x_test, y_test), verbose=0)
assert(history.history['loss'][-1] < 1.)
def test_3d_to_3d():
'''
Apply a same Dense layer for each element of time dimension of the input
and make predictions of the output sequence elements.
This does not make use of the temporal structure of the sequence
(see TimeDistributedDense for more details)
'''
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = get_test_data(num_train=100,
num_test=20,
input_shape=(3, 5),
output_shape=(3, 5),
classification=False)
model = Sequential()
model.add(layers.TimeDistributed(
layers.Dense(y_train.shape[-1]), input_shape=x_train.shape[1:3]))
model.compile(loss='hinge', optimizer='rmsprop')
history = model.fit(x_train, y_train, epochs=20, batch_size=16,
validation_data=(x_test, y_test), verbose=0)
assert(history.history['loss'][-1] < 1.)
def test_stacked_lstm_char_prediction():
'''
Learn alphabetical char sequence with stacked LSTM.
Predict the whole alphabet based on the first two letters ('ab' -> 'ab...z')
See non-toy example in examples/lstm_text_generation.py
'''
# generate alphabet:
# http://stackoverflow.com/questions/16060899/alphabet-range-python
alphabet = string.ascii_lowercase
number_of_chars = len(alphabet)
# generate char sequences of length 'sequence_length' out of alphabet and
# store the next char as label (e.g. 'ab'->'c')
sequence_length = 2
sentences = [alphabet[i: i + sequence_length]
for i in range(len(alphabet) - sequence_length)]
next_chars = [alphabet[i + sequence_length]
for i in range(len(alphabet) - sequence_length)]
# Transform sequences and labels into 'one-hot' encoding
x = np.zeros((len(sentences), sequence_length, number_of_chars), dtype=np.bool)
y = np.zeros((len(sentences), number_of_chars), dtype=np.bool)
for i, sentence in enumerate(sentences):
for t, char in enumerate(sentence):
x[i, t, ord(char) - ord('a')] = 1
y[i, ord(next_chars[i]) - ord('a')] = 1
# learn the alphabet with stacked LSTM
model = Sequential([
layers.LSTM(16, return_sequences=True,
input_shape=(sequence_length, number_of_chars)),
layers.LSTM(16, return_sequences=False),
layers.Dense(number_of_chars, activation='softmax')
])
model.compile(loss='categorical_crossentropy', optimizer='adam')
model.fit(x, y, batch_size=1, epochs=60, verbose=1)
# prime the model with 'ab' sequence and let it generate the learned alphabet
sentence = alphabet[:sequence_length]
generated = sentence
for iteration in range(number_of_chars - sequence_length):
x = np.zeros((1, sequence_length, number_of_chars))
for t, char in enumerate(sentence):
x[0, t, ord(char) - ord('a')] = 1.
preds = model.predict(x, verbose=0)[0]
next_char = chr(np.argmax(preds) + ord('a'))
generated += next_char
sentence = sentence[1:] + next_char
# check that it did generate the alphabet correctly
assert(generated == alphabet)
@pytest.mark.skipif(K.backend() != 'tensorflow', reason='Requires TF backend')
def test_embedding_with_clipnorm():
model = Sequential()
model.add(layers.Embedding(input_dim=1, output_dim=1))
model.compile(optimizer=optimizers.SGD(clipnorm=0.1), loss='mse')
model.fit(np.array([[0]]), np.array([[[0.5]]]), epochs=1)
if __name__ == '__main__':
pytest.main([__file__])
|
