forked from tensorflow/tensorflow
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathconvolutional.py
More file actions
1465 lines (1359 loc) · 60.1 KB
/
convolutional.py
File metadata and controls
1465 lines (1359 loc) · 60.1 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
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Copyright 2015 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.
# =============================================================================
# pylint: disable=unused-import,g-bad-import-order
"""Contains the convolutional layer classes and their functional aliases.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import six
from six.moves import xrange # pylint: disable=redefined-builtin
import numpy as np
from tensorflow.python.framework import ops
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import control_flow_ops
from tensorflow.python.ops import nn
from tensorflow.python.ops import math_ops
from tensorflow.python.ops import init_ops
from tensorflow.python.ops import standard_ops
from tensorflow.python.ops import variable_scope as vs
from tensorflow.python.layers import base
from tensorflow.python.layers import utils
class _Conv(base.Layer):
"""Abstract nD convolution layer (private, used as implementation base).
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
rank: An integer, the rank of the convolution, e.g. "2" for 2D convolution.
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of n integers, specifying the
length of the convolution window.
strides: An integer or tuple/list of n integers,
specifying the stride length of the convolution.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, ..., channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, ...)`.
dilation_rate: An integer or tuple/list of n integers, specifying
the dilation rate to use for dilated convolution.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any `strides` value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
"""
def __init__(self, rank,
filters,
kernel_size,
strides=1,
padding='valid',
data_format='channels_last',
dilation_rate=1,
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
**kwargs):
super(_Conv, self).__init__(trainable=trainable,
name=name, **kwargs)
self.rank = rank
self.filters = filters
self.kernel_size = utils.normalize_tuple(kernel_size, rank, 'kernel_size')
self.strides = utils.normalize_tuple(strides, rank, 'strides')
self.padding = utils.normalize_padding(padding)
self.data_format = utils.normalize_data_format(data_format)
self.dilation_rate = utils.normalize_tuple(
dilation_rate, rank, 'dilation_rate')
self.activation = activation
self.use_bias = use_bias
self.kernel_initializer = kernel_initializer
self.bias_initializer = bias_initializer
self.kernel_regularizer = kernel_regularizer
self.bias_regularizer = bias_regularizer
self.activity_regularizer = activity_regularizer
def build(self, input_shape):
if len(input_shape) != self.rank + 2:
raise ValueError('Inputs should have rank ' +
str(self.rank + 2) +
'. Received input shape: ' + str(input_shape))
if self.data_format == 'channels_first':
channel_axis = 1
else:
channel_axis = -1
if input_shape[channel_axis].value is None:
raise ValueError('The channel dimension of the inputs '
'should be defined. Found `None`.')
input_dim = input_shape[channel_axis].value
kernel_shape = self.kernel_size + (input_dim, self.filters)
self.kernel = self.add_variable(name='kernel',
shape=kernel_shape,
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
trainable=True,
dtype=self.dtype)
if self.use_bias:
self.bias = self.add_variable(name='bias',
shape=(self.filters,),
initializer=self.bias_initializer,
regularizer=self.bias_regularizer,
trainable=True,
dtype=self.dtype)
else:
self.bias = None
self.built = True
def call(self, inputs):
outputs = nn.convolution(
input=inputs,
filter=self.kernel,
dilation_rate=self.dilation_rate,
strides=self.strides,
padding=self.padding.upper(),
data_format=utils.convert_data_format(self.data_format, self.rank + 2))
if self.bias is not None:
if self.rank != 2 and self.data_format == 'channels_first':
# bias_add does not support channels_first for non-4D inputs.
if self.rank == 1:
bias = array_ops.reshape(self.bias, (1, self.filters, 1))
outputs += bias
elif self.rank == 3:
# As of Mar 2017, direct addition is significantly slower than
# bias_add when computing gradients. To use bias_add, we collapse Z
# and Y into a single dimension to obtain a 4D input tensor.
outputs_shape = outputs.shape.as_list()
outputs_4d = array_ops.reshape(outputs,
[outputs_shape[0], outputs_shape[1],
outputs_shape[2] * outputs_shape[3],
outputs_shape[4]])
outputs_4d = nn.bias_add(
outputs_4d,
self.bias,
data_format=utils.convert_data_format(self.data_format, 4))
outputs = array_ops.reshape(outputs_4d, outputs_shape)
else:
outputs = nn.bias_add(
outputs,
self.bias,
data_format=utils.convert_data_format(self.data_format, 4))
# Note that we passed rank=4 because bias_add will only accept
# NHWC and NCWH even if the rank of the inputs is 3 or 5.
if self.activation is not None:
return self.activation(outputs)
return outputs
class Conv1D(_Conv):
"""1D convolution layer (e.g. temporal convolution).
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of a single integer, specifying the
length of the 1D convolution window.
strides: An integer or tuple/list of a single integer,
specifying the stride length of the convolution.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, length, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, length)`.
dilation_rate: An integer or tuple/list of a single integer, specifying
the dilation rate to use for dilated convolution.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any `strides` value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
"""
def __init__(self, filters,
kernel_size,
strides=1,
padding='valid',
data_format='channels_last',
dilation_rate=1,
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
**kwargs):
super(Convolution1D, self).__init__(
rank=1,
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name, **kwargs)
def conv1d(inputs,
filters,
kernel_size,
strides=1,
padding='valid',
data_format='channels_last',
dilation_rate=1,
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
reuse=None):
"""Functional interface for 1D convolution layer (e.g. temporal convolution).
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
inputs: Tensor input.
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of a single integer, specifying the
length of the 1D convolution window.
strides: An integer or tuple/list of a single integer,
specifying the stride length of the convolution.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, length, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, length)`.
dilation_rate: An integer or tuple/list of a single integer, specifying
the dilation rate to use for dilated convolution.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any `strides` value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns:
Output tensor.
"""
layer = Conv1D(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name,
_reuse=reuse,
_scope=name)
return layer.apply(inputs)
class Conv2D(_Conv):
"""2D convolution layer (e.g. spatial convolution over images).
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of 2 integers, specifying the
width and height of the 2D convolution window.
Can be a single integer to specify the same value for
all spatial dimensions.
strides: An integer or tuple/list of 2 integers,
specifying the strides of the convolution along the height and width.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, height, width, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, height, width)`.
dilation_rate: An integer or tuple/list of 2 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
"""
def __init__(self, filters,
kernel_size,
strides=(1, 1),
padding='valid',
data_format='channels_last',
dilation_rate=(1, 1),
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
**kwargs):
super(Conv2D, self).__init__(
rank=2,
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name, **kwargs)
def conv2d(inputs,
filters,
kernel_size,
strides=(1, 1),
padding='valid',
data_format='channels_last',
dilation_rate=(1, 1),
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
reuse=None):
"""Functional interface for the 2D convolution layer.
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
inputs: Tensor input.
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of 2 integers, specifying the
width and height of the 2D convolution window.
Can be a single integer to specify the same value for
all spatial dimensions.
strides: An integer or tuple/list of 2 integers,
specifying the strides of the convolution along the height and width.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, height, width, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, height, width)`.
dilation_rate: An integer or tuple/list of 2 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns:
Output tensor.
"""
layer = Conv2D(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name,
_reuse=reuse,
_scope=name)
return layer.apply(inputs)
class Conv3D(_Conv):
"""3D convolution layer (e.g. spatial convolution over volumes).
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of 3 integers, specifying the
depth, height and width of the 3D convolution window.
Can be a single integer to specify the same value for
all spatial dimensions.
strides: An integer or tuple/list of 3 integers,
specifying the strides of the convolution along the depth,
height and width.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, depth, height, width, channels)` while `channels_first`
corresponds to inputs with shape
`(batch, channels, depth, height, width)`.
dilation_rate: An integer or tuple/list of 3 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
"""
def __init__(self, filters,
kernel_size,
strides=(1, 1, 1),
padding='valid',
data_format='channels_last',
dilation_rate=(1, 1, 1),
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
**kwargs):
super(Conv3D, self).__init__(
rank=3,
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name, **kwargs)
def conv3d(inputs,
filters,
kernel_size,
strides=(1, 1, 1),
padding='valid',
data_format='channels_last',
dilation_rate=(1, 1, 1),
activation=None,
use_bias=True,
kernel_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
reuse=None):
"""Functional interface for the 3D convolution layer.
This layer creates a convolution kernel that is convolved
(actually cross-correlated) with the layer input to produce a tensor of
outputs. If `use_bias` is True (and a `bias_initializer` is provided),
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
Arguments:
inputs: Tensor input.
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: An integer or tuple/list of 3 integers, specifying the
depth, height and width of the 3D convolution window.
Can be a single integer to specify the same value for
all spatial dimensions.
strides: An integer or tuple/list of 3 integers,
specifying the strides of the convolution along the depth,
height and width.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, depth, height, width, channels)` while `channels_first`
corresponds to inputs with shape
`(batch, channels, depth, height, width)`.
dilation_rate: An integer or tuple/list of 3 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
kernel_initializer: An initializer for the convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
kernel_regularizer: Optional regularizer for the convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns:
Output tensor.
"""
layer = Conv3D(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name,
_reuse=reuse,
_scope=name)
return layer.apply(inputs)
class SeparableConv2D(Conv2D):
"""Depthwise separable 2D convolution.
This layer performs a depthwise convolution that acts separately on
channels, followed by a pointwise convolution that mixes channels.
If `use_bias` is True and a bias initializer is provided,
it adds a bias vector to the output.
It then optionally applies an activation function to produce the final output.
Arguments:
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: A tuple or list of 2 integers specifying the spatial
dimensions of of the filters. Can be a single integer to specify the same
value for all spatial dimensions.
strides: A tuple or list of 2 positive integers specifying the strides
of the convolution. Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any `stride` value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, height, width, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, height, width)`.
dilation_rate: An integer or tuple/list of 2 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
depth_multiplier: The number of depthwise convolution output channels for
each input channel. The total number of depthwise convolution output
channels will be equal to `num_filters_in * depth_multiplier`.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
depthwise_initializer: An initializer for the depthwise convolution kernel.
pointwise_initializer: An initializer for the pointwise convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
depthwise_regularizer: Optional regularizer for the depthwise
convolution kernel.
pointwise_regularizer: Optional regularizer for the pointwise
convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
"""
def __init__(self, filters,
kernel_size,
strides=(1, 1),
padding='valid',
data_format='channels_last',
dilation_rate=(1, 1),
depth_multiplier=1,
activation=None,
use_bias=True,
depthwise_initializer=None,
pointwise_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
depthwise_regularizer=None,
pointwise_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
**kwargs):
super(SeparableConv2D, self).__init__(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name,
**kwargs)
self.depth_multiplier = depth_multiplier
self.depthwise_initializer = depthwise_initializer
self.pointwise_initializer = pointwise_initializer
self.depthwise_regularizer = depthwise_regularizer
self.pointwise_regularizer = pointwise_regularizer
def build(self, input_shape):
if len(input_shape) < 4:
raise ValueError('Inputs to `SeparableConv2D` should have rank 4. '
'Received input shape:', str(input_shape))
if self.data_format == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
if input_shape[channel_axis] is None:
raise ValueError('The channel dimension of the inputs to '
'`SeparableConv2D` '
'should be defined. Found `None`.')
input_dim = int(input_shape[channel_axis])
depthwise_kernel_shape = (self.kernel_size[0],
self.kernel_size[1],
input_dim,
self.depth_multiplier)
pointwise_kernel_shape = (1, 1,
self.depth_multiplier * input_dim,
self.filters)
self.depthwise_kernel = self.add_variable(
name='depthwise_kernel',
shape=depthwise_kernel_shape,
initializer=self.depthwise_initializer,
regularizer=self.depthwise_regularizer,
trainable=True,
dtype=self.dtype)
self.pointwise_kernel = self.add_variable(
name='pointwise_kernel',
shape=pointwise_kernel_shape,
initializer=self.pointwise_initializer,
regularizer=self.pointwise_regularizer,
trainable=True,
dtype=self.dtype)
if self.use_bias:
self.bias = self.add_variable(name='bias',
shape=(self.filters,),
initializer=self.bias_initializer,
regularizer=self.bias_regularizer,
trainable=True,
dtype=self.dtype)
else:
self.bias = None
self.built = True
def call(self, inputs):
if self.data_format == 'channels_first':
# Reshape to channels last
inputs = array_ops.transpose(inputs, (0, 2, 3, 1))
# Apply the actual ops.
outputs = nn.separable_conv2d(
inputs,
self.depthwise_kernel,
self.pointwise_kernel,
strides=(1,) + self.strides + (1,),
padding=self.padding.upper(),
rate=self.dilation_rate)
if self.data_format == 'channels_first':
# Reshape to channels first
outputs = array_ops.transpose(outputs, (0, 3, 1, 2))
if self.bias is not None:
outputs = nn.bias_add(
outputs,
self.bias,
data_format=utils.convert_data_format(self.data_format, ndim=4))
if self.activation is not None:
return self.activation(outputs)
return outputs
def separable_conv2d(inputs,
filters,
kernel_size,
strides=(1, 1),
padding='valid',
data_format='channels_last',
dilation_rate=(1, 1),
depth_multiplier=1,
activation=None,
use_bias=True,
depthwise_initializer=None,
pointwise_initializer=None,
bias_initializer=init_ops.zeros_initializer(),
depthwise_regularizer=None,
pointwise_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
trainable=True,
name=None,
reuse=None):
"""Functional interface for the depthwise separable 2D convolution layer.
This layer performs a depthwise convolution that acts separately on
channels, followed by a pointwise convolution that mixes channels.
If `use_bias` is True and a bias initializer is provided,
it adds a bias vector to the output.
It then optionally applies an activation function to produce the final output.
Arguments:
inputs: Input tensor.
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: A tuple or list of 2 integers specifying the spatial
dimensions of of the filters. Can be a single integer to specify the same
value for all spatial dimensions.
strides: A tuple or list of 2 positive integers specifying the strides
of the convolution. Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any `stride` value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: One of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, height, width, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, height, width)`.
dilation_rate: An integer or tuple/list of 2 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
depth_multiplier: The number of depthwise convolution output channels for
each input channel. The total number of depthwise convolution output
channels will be equal to `num_filters_in * depth_multiplier`.
activation: Activation function. Set it to None to maintain a
linear activation.
use_bias: Boolean, whether the layer uses a bias.
depthwise_initializer: An initializer for the depthwise convolution kernel.
pointwise_initializer: An initializer for the pointwise convolution kernel.
bias_initializer: An initializer for the bias vector. If None, no bias will
be applied.
depthwise_regularizer: Optional regularizer for the depthwise
convolution kernel.
pointwise_regularizer: Optional regularizer for the pointwise
convolution kernel.
bias_regularizer: Optional regularizer for the bias vector.
activity_regularizer: Regularizer function for the output.
trainable: Boolean, if `True` also add variables to the graph collection
`GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`).
name: A string, the name of the layer.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns:
Output tensor.
"""
layer = SeparableConv2D(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
depth_multiplier=depth_multiplier,
activation=activation,
use_bias=use_bias,
depthwise_initializer=depthwise_initializer,
pointwise_initializer=pointwise_initializer,
bias_initializer=bias_initializer,
depthwise_regularizer=depthwise_regularizer,
pointwise_regularizer=pointwise_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
trainable=trainable,
name=name,
_reuse=reuse,
_scope=name)
return layer.apply(inputs)
class Conv2DTranspose(Conv2D):
"""Transposed 2D convolution layer (sometimes called 2D Deconvolution).
The need for transposed convolutions generally arises
from the desire to use a transformation going in the opposite direction
of a normal convolution, i.e., from something that has the shape of the
output of some convolution to something that has the shape of its input
while maintaining a connectivity pattern that is compatible with
said convolution.
Arguments:
filters: Integer, the dimensionality of the output space (i.e. the number
of filters in the convolution).
kernel_size: A tuple or list of 2 positive integers specifying the spatial
dimensions of of the filters. Can be a single integer to specify the same
value for all spatial dimensions.
strides: A tuple or list of 2 positive integers specifying the strides
of the convolution. Can be a single integer to specify the same value for
all spatial dimensions.
padding: one of `"valid"` or `"same"` (case-insensitive).
data_format: A string, one of `channels_last` (default) or `channels_first`.
The ordering of the dimensions in the inputs.
`channels_last` corresponds to inputs with shape
`(batch, height, width, channels)` while `channels_first` corresponds to
inputs with shape `(batch, channels, height, width)`.
activation: Activation function. Set it to None to maintain a
linear activation.