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
|
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Tests for convolutional recurrent layers."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
from tensorflow.python import keras
from tensorflow.python.keras import testing_utils
from tensorflow.python.platform import test
class ConvLSTMTest(test.TestCase):
def test_conv_lstm(self):
num_row = 3
num_col = 3
filters = 2
num_samples = 1
input_channel = 2
input_num_row = 5
input_num_col = 5
sequence_len = 2
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, sequence_len,
input_channel,
input_num_row, input_num_col)
else:
inputs = np.random.rand(num_samples, sequence_len,
input_num_row, input_num_col,
input_channel)
for return_sequences in [True, False]:
with self.cached_session():
# test for return state:
x = keras.Input(batch_shape=inputs.shape)
kwargs = {'data_format': data_format,
'return_sequences': return_sequences,
'return_state': True,
'stateful': True,
'filters': filters,
'kernel_size': (num_row, num_col),
'padding': 'valid'}
layer = keras.layers.ConvLSTM2D(**kwargs)
layer.build(inputs.shape)
outputs = layer(x)
_, states = outputs[0], outputs[1:]
self.assertEqual(len(states), 2)
model = keras.models.Model(x, states[0])
state = model.predict(inputs)
self.assertAllClose(
keras.backend.eval(layer.states[0]), state, atol=1e-4)
# test for output shape:
testing_utils.layer_test(
keras.layers.ConvLSTM2D,
kwargs={'data_format': data_format,
'return_sequences': return_sequences,
'filters': filters,
'kernel_size': (num_row, num_col),
'padding': 'valid'},
input_shape=inputs.shape)
def test_conv_lstm_statefulness(self):
# Tests for statefulness
num_row = 3
num_col = 3
filters = 2
num_samples = 1
input_channel = 2
input_num_row = 5
input_num_col = 5
sequence_len = 2
inputs = np.random.rand(num_samples, sequence_len,
input_num_row, input_num_col,
input_channel)
with self.cached_session():
model = keras.models.Sequential()
kwargs = {'data_format': 'channels_last',
'return_sequences': False,
'filters': filters,
'kernel_size': (num_row, num_col),
'stateful': True,
'batch_input_shape': inputs.shape,
'padding': 'same'}
layer = keras.layers.ConvLSTM2D(**kwargs)
model.add(layer)
model.compile(optimizer='sgd', loss='mse')
out1 = model.predict(np.ones_like(inputs))
# train once so that the states change
model.train_on_batch(np.ones_like(inputs),
np.random.random(out1.shape))
out2 = model.predict(np.ones_like(inputs))
# if the state is not reset, output should be different
self.assertNotEqual(out1.max(), out2.max())
# check that output changes after states are reset
# (even though the model itself didn't change)
layer.reset_states()
out3 = model.predict(np.ones_like(inputs))
self.assertNotEqual(out3.max(), out2.max())
# check that container-level reset_states() works
model.reset_states()
out4 = model.predict(np.ones_like(inputs))
self.assertAllClose(out3, out4, atol=1e-5)
# check that the call to `predict` updated the states
out5 = model.predict(np.ones_like(inputs))
self.assertNotEqual(out4.max(), out5.max())
def test_conv_lstm_regularizers(self):
# check regularizers
num_row = 3
num_col = 3
filters = 2
num_samples = 1
input_channel = 2
input_num_row = 5
input_num_col = 5
sequence_len = 2
inputs = np.random.rand(num_samples, sequence_len,
input_num_row, input_num_col,
input_channel)
with self.cached_session():
kwargs = {'data_format': 'channels_last',
'return_sequences': False,
'kernel_size': (num_row, num_col),
'stateful': True,
'filters': filters,
'batch_input_shape': inputs.shape,
'kernel_regularizer': keras.regularizers.L1L2(l1=0.01),
'recurrent_regularizer': keras.regularizers.L1L2(l1=0.01),
'activity_regularizer': 'l2',
'bias_regularizer': 'l2',
'kernel_constraint': 'max_norm',
'recurrent_constraint': 'max_norm',
'bias_constraint': 'max_norm',
'padding': 'same'}
layer = keras.layers.ConvLSTM2D(**kwargs)
layer.build(inputs.shape)
self.assertEqual(len(layer.losses), 3)
layer(keras.backend.variable(np.ones(inputs.shape)))
self.assertEqual(len(layer.losses), 4)
def test_conv_lstm_dropout(self):
# check dropout
with self.cached_session():
testing_utils.layer_test(
keras.layers.ConvLSTM2D,
kwargs={'data_format': 'channels_last',
'return_sequences': False,
'filters': 2,
'kernel_size': (3, 3),
'padding': 'same',
'dropout': 0.1,
'recurrent_dropout': 0.1},
input_shape=(1, 2, 5, 5, 2))
def test_conv_lstm_cloning(self):
with self.cached_session():
model = keras.models.Sequential()
model.add(keras.layers.ConvLSTM2D(5, 3, input_shape=(None, 5, 5, 3)))
test_inputs = np.random.random((2, 4, 5, 5, 3))
reference_outputs = model.predict(test_inputs)
weights = model.get_weights()
# Use a new graph to clone the model
with self.cached_session():
clone = keras.models.clone_model(model)
clone.set_weights(weights)
outputs = clone.predict(test_inputs)
self.assertAllClose(reference_outputs, outputs, atol=1e-5)
if __name__ == '__main__':
test.main()
|
