forked from keras-team/keras
/
convolutional.py
2718 lines (2488 loc) · 120 KB
/
convolutional.py
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
# -*- coding: utf-8 -*-
"""Convolutional layers.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from .. import backend as K
from .. import activations
from .. import initializers
from .. import regularizers
from .. import constraints
from ..engine.base_layer import Layer
from ..engine.base_layer import InputSpec
from ..utils import conv_utils
from ..legacy import interfaces
# imports for backwards namespace compatibility
from .pooling import AveragePooling1D
from .pooling import AveragePooling2D
from .pooling import AveragePooling3D
from .pooling import MaxPooling1D
from .pooling import MaxPooling2D
from .pooling import MaxPooling3D
from ..legacy.layers import AtrousConvolution1D
from ..legacy.layers import AtrousConvolution2D
class _Conv(Layer):
"""Abstract nD convolution layer (private, used as implementation base).
This layer creates a convolution kernel that is convolved
with the layer input to produce a tensor of outputs.
If `use_bias` is True, 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 output filters in the convolution).
kernel_size: An integer or tuple/list of n integers, specifying the
dimensions of the convolution window.
strides: An integer or tuple/list of n integers,
specifying the strides 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"` 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, ...)`.
It defaults to the `image_data_format` value found in your
Keras config file at `~/.keras/keras.json`.
If you never set it, then it will be "channels_last".
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 to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to the kernel matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
"""
def __init__(self, rank,
filters,
kernel_size,
strides=1,
padding='valid',
data_format=None,
dilation_rate=1,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
super(_Conv, self).__init__(**kwargs)
self.rank = rank
self.filters = filters
self.kernel_size = conv_utils.normalize_tuple(kernel_size, rank, 'kernel_size')
self.strides = conv_utils.normalize_tuple(strides, rank, 'strides')
self.padding = conv_utils.normalize_padding(padding)
self.data_format = conv_utils.normalize_data_format(data_format)
self.dilation_rate = conv_utils.normalize_tuple(dilation_rate, rank, 'dilation_rate')
self.activation = activations.get(activation)
self.use_bias = use_bias
self.kernel_initializer = initializers.get(kernel_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.bias_constraint = constraints.get(bias_constraint)
self.input_spec = InputSpec(ndim=self.rank + 2)
def build(self, input_shape):
if self.data_format == 'channels_first':
channel_axis = 1
else:
channel_axis = -1
if input_shape[channel_axis] is None:
raise ValueError('The channel dimension of the inputs '
'should be defined. Found `None`.')
input_dim = input_shape[channel_axis]
kernel_shape = self.kernel_size + (input_dim, self.filters)
self.kernel = self.add_weight(shape=kernel_shape,
initializer=self.kernel_initializer,
name='kernel',
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
if self.use_bias:
self.bias = self.add_weight(shape=(self.filters,),
initializer=self.bias_initializer,
name='bias',
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
else:
self.bias = None
# Set input spec.
self.input_spec = InputSpec(ndim=self.rank + 2,
axes={channel_axis: input_dim})
self.built = True
def call(self, inputs):
if self.rank == 1:
outputs = K.conv1d(
inputs,
self.kernel,
strides=self.strides[0],
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate[0])
if self.rank == 2:
outputs = K.conv2d(
inputs,
self.kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.rank == 3:
outputs = K.conv3d(
inputs,
self.kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(
outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def compute_output_shape(self, input_shape):
if self.data_format == 'channels_last':
space = input_shape[1:-1]
new_space = []
for i in range(len(space)):
new_dim = conv_utils.conv_output_length(
space[i],
self.kernel_size[i],
padding=self.padding,
stride=self.strides[i],
dilation=self.dilation_rate[i])
new_space.append(new_dim)
return (input_shape[0],) + tuple(new_space) + (self.filters,)
if self.data_format == 'channels_first':
space = input_shape[2:]
new_space = []
for i in range(len(space)):
new_dim = conv_utils.conv_output_length(
space[i],
self.kernel_size[i],
padding=self.padding,
stride=self.strides[i],
dilation=self.dilation_rate[i])
new_space.append(new_dim)
return (input_shape[0], self.filters) + tuple(new_space)
def get_config(self):
config = {
'rank': self.rank,
'filters': self.filters,
'kernel_size': self.kernel_size,
'strides': self.strides,
'padding': self.padding,
'data_format': self.data_format,
'dilation_rate': self.dilation_rate,
'activation': activations.serialize(self.activation),
'use_bias': self.use_bias,
'kernel_initializer': initializers.serialize(self.kernel_initializer),
'bias_initializer': initializers.serialize(self.bias_initializer),
'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
'bias_regularizer': regularizers.serialize(self.bias_regularizer),
'activity_regularizer': regularizers.serialize(self.activity_regularizer),
'kernel_constraint': constraints.serialize(self.kernel_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(_Conv, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
class Conv1D(_Conv):
"""1D convolution layer (e.g. temporal convolution).
This layer creates a convolution kernel that is convolved
with the layer input over a single spatial (or temporal) dimension
to produce a tensor of outputs.
If `use_bias` is True, a bias vector is created and added to the outputs.
Finally, if `activation` is not `None`,
it is applied to the outputs as well.
When using this layer as the first layer in a model,
provide an `input_shape` argument
(tuple of integers or `None`, e.g.
`(10, 128)` for sequences of 10 vectors of 128-dimensional vectors,
or `(None, 128)` for variable-length sequences of 128-dimensional vectors.
# Arguments
filters: Integer, the dimensionality of the output space
(i.e. the number of output 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"`, `"causal"` or `"same"` (case-insensitive).
`"valid"` means "no padding".
`"same"` results in padding the input such that
the output has the same length as the original input.
`"causal"` results in causal (dilated) convolutions, e.g. output[t]
does not depend on input[t+1:]. Useful when modeling temporal data
where the model should not violate the temporal order.
See [WaveNet: A Generative Model for Raw Audio, section 2.1](https://arxiv.org/abs/1609.03499).
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)`
(default format for temporal data in Keras)
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 to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to the kernel matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
# Input shape
3D tensor with shape: `(batch_size, steps, input_dim)`
# Output shape
3D tensor with shape: `(batch_size, new_steps, filters)`
`steps` value might have changed due to padding or strides.
"""
@interfaces.legacy_conv1d_support
def __init__(self, filters,
kernel_size,
strides=1,
padding='valid',
data_format='channels_last',
dilation_rate=1,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
if padding == 'causal':
if data_format != 'channels_last':
raise ValueError('When using causal padding in `Conv1D`, '
'`data_format` must be "channels_last" '
'(temporal data).')
super(Conv1D, 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,
kernel_constraint=kernel_constraint,
bias_constraint=bias_constraint,
**kwargs)
self.input_spec = InputSpec(ndim=3)
def get_config(self):
config = super(Conv1D, self).get_config()
config.pop('rank')
return config
class Conv2D(_Conv):
"""2D convolution layer (e.g. spatial convolution over images).
This layer creates a convolution kernel that is convolved
with the layer input to produce a tensor of
outputs. If `use_bias` is True,
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
When using this layer as the first layer in a model,
provide the keyword argument `input_shape`
(tuple of integers, does not include the sample axis),
e.g. `input_shape=(128, 128, 3)` for 128x128 RGB pictures
in `data_format="channels_last"`.
# Arguments
filters: Integer, the dimensionality of the output space
(i.e. the number of output filters in the convolution).
kernel_size: An integer or tuple/list of 2 integers, specifying the
height and width 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).
Note that `"same"` is slightly inconsistent across backends with
`strides` != 1, as described
[here](https://github.com/keras-team/keras/pull/9473#issuecomment-372166860)
data_format: A string,
one of `"channels_last"` 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)`.
It defaults to the `image_data_format` value found in your
Keras config file at `~/.keras/keras.json`.
If you never set it, then it will be "channels_last".
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 to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to the kernel matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
# Input shape
4D tensor with shape:
`(samples, channels, rows, cols)`
if `data_format` is `"channels_first"`
or 4D tensor with shape:
`(samples, rows, cols, channels)`
if `data_format` is `"channels_last"`.
# Output shape
4D tensor with shape:
`(samples, filters, new_rows, new_cols)`
if `data_format` is `"channels_first"`
or 4D tensor with shape:
`(samples, new_rows, new_cols, filters)`
if `data_format` is `"channels_last"`.
`rows` and `cols` values might have changed due to padding.
"""
@interfaces.legacy_conv2d_support
def __init__(self, filters,
kernel_size,
strides=(1, 1),
padding='valid',
data_format=None,
dilation_rate=(1, 1),
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=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,
kernel_constraint=kernel_constraint,
bias_constraint=bias_constraint,
**kwargs)
self.input_spec = InputSpec(ndim=4)
def get_config(self):
config = super(Conv2D, self).get_config()
config.pop('rank')
return config
class Conv3D(_Conv):
"""3D convolution layer (e.g. spatial convolution over volumes).
This layer creates a convolution kernel that is convolved
with the layer input to produce a tensor of
outputs. If `use_bias` is True,
a bias vector is created and added to the outputs. Finally, if
`activation` is not `None`, it is applied to the outputs as well.
When using this layer as the first layer in a model,
provide the keyword argument `input_shape`
(tuple of integers, does not include the sample axis),
e.g. `input_shape=(128, 128, 128, 1)` for 128x128x128 volumes
with a single channel,
in `data_format="channels_last"`.
# Arguments
filters: Integer, the dimensionality of the output space
(i.e. the number of output 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 each spatial dimension.
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"` or `"channels_first"`.
The ordering of the dimensions in the inputs.
`"channels_last"` corresponds to inputs with shape
`(batch, spatial_dim1, spatial_dim2, spatial_dim3, channels)`
while `"channels_first"` corresponds to inputs with shape
`(batch, channels, spatial_dim1, spatial_dim2, spatial_dim3)`.
It defaults to the `image_data_format` value found in your
Keras config file at `~/.keras/keras.json`.
If you never set it, then it will be "channels_last".
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 to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to the kernel matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
# Input shape
5D tensor with shape:
`(samples, channels, conv_dim1, conv_dim2, conv_dim3)`
if `data_format` is `"channels_first"`
or 5D tensor with shape:
`(samples, conv_dim1, conv_dim2, conv_dim3, channels)`
if `data_format` is `"channels_last"`.
# Output shape
5D tensor with shape:
`(samples, filters, new_conv_dim1, new_conv_dim2, new_conv_dim3)`
if `data_format` is `"channels_first"`
or 5D tensor with shape:
`(samples, new_conv_dim1, new_conv_dim2, new_conv_dim3, filters)`
if `data_format` is `"channels_last"`.
`new_conv_dim1`, `new_conv_dim2` and `new_conv_dim3` values might have changed due to padding.
"""
@interfaces.legacy_conv3d_support
def __init__(self, filters,
kernel_size,
strides=(1, 1, 1),
padding='valid',
data_format=None,
dilation_rate=(1, 1, 1),
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=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,
kernel_constraint=kernel_constraint,
bias_constraint=bias_constraint,
**kwargs)
self.input_spec = InputSpec(ndim=5)
def get_config(self):
config = super(Conv3D, self).get_config()
config.pop('rank')
return config
class Conv2DTranspose(Conv2D):
"""Transposed convolution layer (sometimes called 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.
When using this layer as the first layer in a model,
provide the keyword argument `input_shape`
(tuple of integers, does not include the sample axis),
e.g. `input_shape=(128, 128, 3)` for 128x128 RGB pictures
in `data_format="channels_last"`.
# Arguments
filters: Integer, the dimensionality of the output space
(i.e. the number of output filters in the convolution).
kernel_size: An integer or tuple/list of 2 integers, specifying the
height and width 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).
output_padding: An integer or tuple/list of 2 integers,
specifying the amount of padding along the height and width
of the output tensor.
Can be a single integer to specify the same value for all
spatial dimensions.
The amount of output padding along a givern dimension must be
lower than the stride along that same dimension.
If set to `None`, defaults to 1 if padding is `"same"` and to
0 if padding is '"valid"'.
data_format: A string,
one of `"channels_last"` 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)`.
It defaults to the `image_data_format` value found in your
Keras config file at `~/.keras/keras.json`.
If you never set it, then it will be "channels_last".
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 to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to the kernel matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
# Input shape
4D tensor with shape:
`(batch, channels, rows, cols)`
if `data_format` is `"channels_first"`
or 4D tensor with shape:
`(batch, rows, cols, channels)`
if `data_format` is `"channels_last"`.
# Output shape
4D tensor with shape:
`(batch, filters, new_rows, new_cols)`
if `data_format` is `"channels_first"`
or 4D tensor with shape:
`(batch, new_rows, new_cols, filters)`
if `data_format` is `"channels_last"`.
`rows` and `cols` values might have changed due to padding.
# References
- [A guide to convolution arithmetic for deep learning](https://arxiv.org/abs/1603.07285v1)
- [Deconvolutional Networks](http://www.matthewzeiler.com/pubs/cvpr2010/cvpr2010.pdf)
"""
@interfaces.legacy_deconv2d_support
def __init__(self, filters,
kernel_size,
strides=(1, 1),
padding='valid',
output_padding=None,
data_format=None,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
super(Conv2DTranspose, self).__init__(
filters,
kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
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,
kernel_constraint=kernel_constraint,
bias_constraint=bias_constraint,
**kwargs)
self.input_spec = InputSpec(ndim=4)
self.output_padding = output_padding
if self.output_padding is not None:
self.output_padding = conv_utils.normalize_tuple(self.output_padding, 2, 'output_padding')
for stride, out_pad in zip(self.strides, self.output_padding):
if out_pad >= stride:
raise ValueError('Stride ' + str(self.strides) + ' must be ' +
'greater than output padding ' +
str(self.output_padding))
def build(self, input_shape):
if len(input_shape) != 4:
raise ValueError('Inputs should have rank ' +
str(4) +
'; Received input shape:', str(input_shape))
if self.data_format == 'channels_first':
channel_axis = 1
else:
channel_axis = -1
if input_shape[channel_axis] is None:
raise ValueError('The channel dimension of the inputs '
'should be defined. Found `None`.')
input_dim = input_shape[channel_axis]
kernel_shape = self.kernel_size + (self.filters, input_dim)
self.kernel = self.add_weight(shape=kernel_shape,
initializer=self.kernel_initializer,
name='kernel',
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
if self.use_bias:
self.bias = self.add_weight(shape=(self.filters,),
initializer=self.bias_initializer,
name='bias',
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
else:
self.bias = None
# Set input spec.
self.input_spec = InputSpec(ndim=4, axes={channel_axis: input_dim})
self.built = True
def call(self, inputs):
input_shape = K.shape(inputs)
batch_size = input_shape[0]
if self.data_format == 'channels_first':
h_axis, w_axis = 2, 3
else:
h_axis, w_axis = 1, 2
height, width = input_shape[h_axis], input_shape[w_axis]
kernel_h, kernel_w = self.kernel_size
stride_h, stride_w = self.strides
if self.output_padding is None:
out_pad_h = out_pad_w = None
else:
out_pad_h, out_pad_w = self.output_padding
# Infer the dynamic output shape:
out_height = conv_utils.deconv_length(height,
stride_h, kernel_h,
self.padding,
out_pad_h)
out_width = conv_utils.deconv_length(width,
stride_w, kernel_w,
self.padding,
out_pad_w)
if self.data_format == 'channels_first':
output_shape = (batch_size, self.filters, out_height, out_width)
else:
output_shape = (batch_size, out_height, out_width, self.filters)
outputs = K.conv2d_transpose(
inputs,
self.kernel,
output_shape,
self.strides,
padding=self.padding,
data_format=self.data_format)
if self.bias:
outputs = K.bias_add(
outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def compute_output_shape(self, input_shape):
output_shape = list(input_shape)
if self.data_format == 'channels_first':
c_axis, h_axis, w_axis = 1, 2, 3
else:
c_axis, h_axis, w_axis = 3, 1, 2
kernel_h, kernel_w = self.kernel_size
stride_h, stride_w = self.strides
if self.output_padding is None:
out_pad_h = out_pad_w = None
else:
out_pad_h, out_pad_w = self.output_padding
output_shape[c_axis] = self.filters
output_shape[h_axis] = conv_utils.deconv_length(output_shape[h_axis],
stride_h,
kernel_h,
self.padding,
out_pad_h)
output_shape[w_axis] = conv_utils.deconv_length(output_shape[w_axis],
stride_w,
kernel_w,
self.padding,
out_pad_w)
return tuple(output_shape)
def get_config(self):
config = super(Conv2DTranspose, self).get_config()
config.pop('dilation_rate')
config['output_padding'] = self.output_padding
return config
class Conv3DTranspose(Conv3D):
"""Transposed convolution layer (sometimes called 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.
When using this layer as the first layer in a model,
provide the keyword argument `input_shape`
(tuple of integers, does not include the sample axis),
e.g. `input_shape=(128, 128, 128, 3)` for a 128x128x128 volume with 3 channels
if `data_format="channels_last"`.
# Arguments
filters: Integer, the dimensionality of the output space
(i.e. the number of output filters in the convolution).
kernel_size: An integer or tuple/list of 3 integers, specifying the
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 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).
output_padding: An integer or tuple/list of 3 integers,
specifying the amount of padding along the depth, height, and
width.
Can be a single integer to specify the same value for all
spatial dimensions.
The amount of output padding along a givern dimension must be
lower than the stride along that same dimension.
If set to `None`, defaults to 1 if padding is `"same"` and to
0 if padding is '"valid"'.
data_format: A string,
one of `"channels_last"` 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)`.
It defaults to the `image_data_format` value found in your
Keras config file at `~/.keras/keras.json`.
If you never set it, then it will be "channels_last".
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 to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to the kernel matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
# Input shape
5D tensor with shape:
`(batch, channels, depth, rows, cols)`
if `data_format` is `"channels_first"`
or 5D tensor with shape:
`(batch, depth, rows, cols, channels)`
if `data_format` is `"channels_last"`.
# Output shape
5D tensor with shape:
`(batch, filters, new_depth, new_rows, new_cols)`
if `data_format` is `"channels_first"`
or 5D tensor with shape:
`(batch, new_depth, new_rows, new_cols, filters)`
if `data_format` is `"channels_last"`.
`depth` and `rows` and `cols` values might have changed due to padding.
# References
- [A guide to convolution arithmetic for deep learning](https://arxiv.org/abs/1603.07285v1)
- [Deconvolutional Networks](http://www.matthewzeiler.com/pubs/cvpr2010/cvpr2010.pdf)
"""
def __init__(self, filters,
kernel_size,
strides=(1, 1, 1),
padding='valid',
output_padding=None,
data_format=None,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
super(Conv3DTranspose, self).__init__(
filters,
kernel_size,
strides=strides,
padding=padding,
data_format=data_format,