File size: 58,882 Bytes
c61ccee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
from typing import List, Optional

from torch import Tensor
from .module import Module
from .utils import _single, _pair, _triple
from .. import functional as F

from ..common_types import (_size_any_t, _size_1_t, _size_2_t, _size_3_t,
                            _ratio_3_t, _ratio_2_t, _size_any_opt_t, _size_2_opt_t, _size_3_opt_t)

__all__ = ['MaxPool1d', 'MaxPool2d', 'MaxPool3d', 'MaxUnpool1d', 'MaxUnpool2d', 'MaxUnpool3d',
           'AvgPool1d', 'AvgPool2d', 'AvgPool3d', 'FractionalMaxPool2d', 'FractionalMaxPool3d', 'LPPool1d',
           'LPPool2d', 'LPPool3d', 'AdaptiveMaxPool1d', 'AdaptiveMaxPool2d', 'AdaptiveMaxPool3d',
           'AdaptiveAvgPool1d', 'AdaptiveAvgPool2d', 'AdaptiveAvgPool3d']

class _MaxPoolNd(Module):
    __constants__ = ['kernel_size', 'stride', 'padding', 'dilation',
                     'return_indices', 'ceil_mode']
    return_indices: bool
    ceil_mode: bool

    def __init__(self, kernel_size: _size_any_t, stride: Optional[_size_any_t] = None,

                 padding: _size_any_t = 0, dilation: _size_any_t = 1,

                 return_indices: bool = False, ceil_mode: bool = False) -> None:
        super().__init__()
        self.kernel_size = kernel_size
        self.stride = stride if (stride is not None) else kernel_size
        self.padding = padding
        self.dilation = dilation
        self.return_indices = return_indices
        self.ceil_mode = ceil_mode

    def extra_repr(self) -> str:
        return 'kernel_size={kernel_size}, stride={stride}, padding={padding}' \
            ', dilation={dilation}, ceil_mode={ceil_mode}'.format(**self.__dict__)


class MaxPool1d(_MaxPoolNd):
    r"""Applies a 1D max pooling over an input signal composed of several input planes.



    In the simplest case, the output value of the layer with input size :math:`(N, C, L)`

    and output :math:`(N, C, L_{out})` can be precisely described as:



    .. math::

        out(N_i, C_j, k) = \max_{m=0, \ldots, \text{kernel\_size} - 1}

                input(N_i, C_j, stride \times k + m)



    If :attr:`padding` is non-zero, then the input is implicitly padded with negative infinity on both sides

    for :attr:`padding` number of points. :attr:`dilation` is the stride between the elements within the

    sliding window. This `link`_ has a nice visualization of the pooling parameters.



    Note:

        When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding

        or the input. Sliding windows that would start in the right padded region are ignored.



    Args:

        kernel_size: The size of the sliding window, must be > 0.

        stride: The stride of the sliding window, must be > 0. Default value is :attr:`kernel_size`.

        padding: Implicit negative infinity padding to be added on both sides, must be >= 0 and <= kernel_size / 2.

        dilation: The stride between elements within a sliding window, must be > 0.

        return_indices: If ``True``, will return the argmax along with the max values.

                        Useful for :class:`torch.nn.MaxUnpool1d` later

        ceil_mode: If ``True``, will use `ceil` instead of `floor` to compute the output shape. This

                   ensures that every element in the input tensor is covered by a sliding window.



    Shape:

        - Input: :math:`(N, C, L_{in})` or :math:`(C, L_{in})`.

        - Output: :math:`(N, C, L_{out})` or :math:`(C, L_{out})`, where



          .. math::

              L_{out} = \left\lfloor \frac{L_{in} + 2 \times \text{padding} - \text{dilation}

                    \times (\text{kernel\_size} - 1) - 1}{\text{stride}} + 1\right\rfloor



    Examples::



        >>> # pool of size=3, stride=2

        >>> m = nn.MaxPool1d(3, stride=2)

        >>> input = torch.randn(20, 16, 50)

        >>> output = m(input)



    .. _link:

        https://github.com/vdumoulin/conv_arithmetic/blob/master/README.md

    """

    kernel_size: _size_1_t
    stride: _size_1_t
    padding: _size_1_t
    dilation: _size_1_t

    def forward(self, input: Tensor):
        return F.max_pool1d(input, self.kernel_size, self.stride,
                            self.padding, self.dilation, ceil_mode=self.ceil_mode,
                            return_indices=self.return_indices)


class MaxPool2d(_MaxPoolNd):
    r"""Applies a 2D max pooling over an input signal composed of several input planes.



    In the simplest case, the output value of the layer with input size :math:`(N, C, H, W)`,

    output :math:`(N, C, H_{out}, W_{out})` and :attr:`kernel_size` :math:`(kH, kW)`

    can be precisely described as:



    .. math::

        \begin{aligned}

            out(N_i, C_j, h, w) ={} & \max_{m=0, \ldots, kH-1} \max_{n=0, \ldots, kW-1} \\

                                    & \text{input}(N_i, C_j, \text{stride[0]} \times h + m,

                                                   \text{stride[1]} \times w + n)

        \end{aligned}



    If :attr:`padding` is non-zero, then the input is implicitly padded with negative infinity on both sides

    for :attr:`padding` number of points. :attr:`dilation` controls the spacing between the kernel points.

    It is harder to describe, but this `link`_ has a nice visualization of what :attr:`dilation` does.



    Note:

        When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding

        or the input. Sliding windows that would start in the right padded region are ignored.



    The parameters :attr:`kernel_size`, :attr:`stride`, :attr:`padding`, :attr:`dilation` can either be:



        - a single ``int`` -- in which case the same value is used for the height and width dimension

        - a ``tuple`` of two ints -- in which case, the first `int` is used for the height dimension,

          and the second `int` for the width dimension



    Args:

        kernel_size: the size of the window to take a max over

        stride: the stride of the window. Default value is :attr:`kernel_size`

        padding: Implicit negative infinity padding to be added on both sides

        dilation: a parameter that controls the stride of elements in the window

        return_indices: if ``True``, will return the max indices along with the outputs.

                        Useful for :class:`torch.nn.MaxUnpool2d` later

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape



    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`

        - Output: :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`, where



          .. math::

              H_{out} = \left\lfloor\frac{H_{in} + 2 * \text{padding[0]} - \text{dilation[0]}

                    \times (\text{kernel\_size[0]} - 1) - 1}{\text{stride[0]}} + 1\right\rfloor



          .. math::

              W_{out} = \left\lfloor\frac{W_{in} + 2 * \text{padding[1]} - \text{dilation[1]}

                    \times (\text{kernel\_size[1]} - 1) - 1}{\text{stride[1]}} + 1\right\rfloor



    Examples::



        >>> # pool of square window of size=3, stride=2

        >>> m = nn.MaxPool2d(3, stride=2)

        >>> # pool of non-square window

        >>> m = nn.MaxPool2d((3, 2), stride=(2, 1))

        >>> input = torch.randn(20, 16, 50, 32)

        >>> output = m(input)



    .. _link:

        https://github.com/vdumoulin/conv_arithmetic/blob/master/README.md

    """

    kernel_size: _size_2_t
    stride: _size_2_t
    padding: _size_2_t
    dilation: _size_2_t

    def forward(self, input: Tensor):
        return F.max_pool2d(input, self.kernel_size, self.stride,
                            self.padding, self.dilation, ceil_mode=self.ceil_mode,
                            return_indices=self.return_indices)


class MaxPool3d(_MaxPoolNd):
    r"""Applies a 3D max pooling over an input signal composed of several input planes.



    In the simplest case, the output value of the layer with input size :math:`(N, C, D, H, W)`,

    output :math:`(N, C, D_{out}, H_{out}, W_{out})` and :attr:`kernel_size` :math:`(kD, kH, kW)`

    can be precisely described as:



    .. math::

        \begin{aligned}

            \text{out}(N_i, C_j, d, h, w) ={} & \max_{k=0, \ldots, kD-1} \max_{m=0, \ldots, kH-1} \max_{n=0, \ldots, kW-1} \\

                                              & \text{input}(N_i, C_j, \text{stride[0]} \times d + k,

                                                             \text{stride[1]} \times h + m, \text{stride[2]} \times w + n)

        \end{aligned}



    If :attr:`padding` is non-zero, then the input is implicitly padded with negative infinity on both sides

    for :attr:`padding` number of points. :attr:`dilation` controls the spacing between the kernel points.

    It is harder to describe, but this `link`_ has a nice visualization of what :attr:`dilation` does.



    Note:

        When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding

        or the input. Sliding windows that would start in the right padded region are ignored.



    The parameters :attr:`kernel_size`, :attr:`stride`, :attr:`padding`, :attr:`dilation` can either be:



        - a single ``int`` -- in which case the same value is used for the depth, height and width dimension

        - a ``tuple`` of three ints -- in which case, the first `int` is used for the depth dimension,

          the second `int` for the height dimension and the third `int` for the width dimension



    Args:

        kernel_size: the size of the window to take a max over

        stride: the stride of the window. Default value is :attr:`kernel_size`

        padding: Implicit negative infinity padding to be added on all three sides

        dilation: a parameter that controls the stride of elements in the window

        return_indices: if ``True``, will return the max indices along with the outputs.

                        Useful for :class:`torch.nn.MaxUnpool3d` later

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape



    Shape:

        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` or :math:`(C, D_{out}, H_{out}, W_{out})`, where



          .. math::

              D_{out} = \left\lfloor\frac{D_{in} + 2 \times \text{padding}[0] - \text{dilation}[0] \times

                (\text{kernel\_size}[0] - 1) - 1}{\text{stride}[0]} + 1\right\rfloor



          .. math::

              H_{out} = \left\lfloor\frac{H_{in} + 2 \times \text{padding}[1] - \text{dilation}[1] \times

                (\text{kernel\_size}[1] - 1) - 1}{\text{stride}[1]} + 1\right\rfloor



          .. math::

              W_{out} = \left\lfloor\frac{W_{in} + 2 \times \text{padding}[2] - \text{dilation}[2] \times

                (\text{kernel\_size}[2] - 1) - 1}{\text{stride}[2]} + 1\right\rfloor



    Examples::



        >>> # pool of square window of size=3, stride=2

        >>> m = nn.MaxPool3d(3, stride=2)

        >>> # pool of non-square window

        >>> m = nn.MaxPool3d((3, 2, 2), stride=(2, 1, 2))

        >>> input = torch.randn(20, 16, 50, 44, 31)

        >>> output = m(input)



    .. _link:

        https://github.com/vdumoulin/conv_arithmetic/blob/master/README.md

    """  # noqa: E501

    kernel_size: _size_3_t
    stride: _size_3_t
    padding: _size_3_t
    dilation: _size_3_t

    def forward(self, input: Tensor):
        return F.max_pool3d(input, self.kernel_size, self.stride,
                            self.padding, self.dilation, ceil_mode=self.ceil_mode,
                            return_indices=self.return_indices)


class _MaxUnpoolNd(Module):

    def extra_repr(self) -> str:
        return f'kernel_size={self.kernel_size}, stride={self.stride}, padding={self.padding}'


class MaxUnpool1d(_MaxUnpoolNd):
    r"""Computes a partial inverse of :class:`MaxPool1d`.



    :class:`MaxPool1d` is not fully invertible, since the non-maximal values are lost.



    :class:`MaxUnpool1d` takes in as input the output of :class:`MaxPool1d`

    including the indices of the maximal values and computes a partial inverse

    in which all non-maximal values are set to zero.



    Note:

        This operation may behave nondeterministically when the input indices has repeat values.

        See https://github.com/pytorch/pytorch/issues/80827 and :doc:`/notes/randomness` for more information.



    .. note:: :class:`MaxPool1d` can map several input sizes to the same output

              sizes. Hence, the inversion process can get ambiguous.

              To accommodate this, you can provide the needed output size

              as an additional argument :attr:`output_size` in the forward call.

              See the Inputs and Example below.



    Args:

        kernel_size (int or tuple): Size of the max pooling window.

        stride (int or tuple): Stride of the max pooling window.

            It is set to :attr:`kernel_size` by default.

        padding (int or tuple): Padding that was added to the input



    Inputs:

        - `input`: the input Tensor to invert

        - `indices`: the indices given out by :class:`~torch.nn.MaxPool1d`

        - `output_size` (optional): the targeted output size



    Shape:

        - Input: :math:`(N, C, H_{in})` or :math:`(C, H_{in})`.

        - Output: :math:`(N, C, H_{out})` or :math:`(C, H_{out})`, where



          .. math::

              H_{out} = (H_{in} - 1) \times \text{stride}[0] - 2 \times \text{padding}[0] + \text{kernel\_size}[0]



          or as given by :attr:`output_size` in the call operator



    Example::



        >>> # xdoctest: +IGNORE_WANT("do other tests modify the global state?")

        >>> pool = nn.MaxPool1d(2, stride=2, return_indices=True)

        >>> unpool = nn.MaxUnpool1d(2, stride=2)

        >>> input = torch.tensor([[[1., 2, 3, 4, 5, 6, 7, 8]]])

        >>> output, indices = pool(input)

        >>> unpool(output, indices)

        tensor([[[ 0.,  2.,  0.,  4.,  0.,  6.,  0., 8.]]])



        >>> # Example showcasing the use of output_size

        >>> input = torch.tensor([[[1., 2, 3, 4, 5, 6, 7, 8, 9]]])

        >>> output, indices = pool(input)

        >>> unpool(output, indices, output_size=input.size())

        tensor([[[ 0.,  2.,  0.,  4.,  0.,  6.,  0., 8.,  0.]]])



        >>> unpool(output, indices)

        tensor([[[ 0.,  2.,  0.,  4.,  0.,  6.,  0., 8.]]])

    """

    kernel_size: _size_1_t
    stride: _size_1_t
    padding: _size_1_t

    def __init__(self, kernel_size: _size_1_t, stride: Optional[_size_1_t] = None, padding: _size_1_t = 0) -> None:
        super().__init__()
        self.kernel_size = _single(kernel_size)
        self.stride = _single(stride if (stride is not None) else kernel_size)
        self.padding = _single(padding)

    def forward(self, input: Tensor, indices: Tensor, output_size: Optional[List[int]] = None) -> Tensor:
        return F.max_unpool1d(input, indices, self.kernel_size, self.stride,
                              self.padding, output_size)


class MaxUnpool2d(_MaxUnpoolNd):
    r"""Computes a partial inverse of :class:`MaxPool2d`.



    :class:`MaxPool2d` is not fully invertible, since the non-maximal values are lost.



    :class:`MaxUnpool2d` takes in as input the output of :class:`MaxPool2d`

    including the indices of the maximal values and computes a partial inverse

    in which all non-maximal values are set to zero.



    Note:

        This operation may behave nondeterministically when the input indices has repeat values.

        See https://github.com/pytorch/pytorch/issues/80827 and :doc:`/notes/randomness` for more information.



    .. note:: :class:`MaxPool2d` can map several input sizes to the same output

              sizes. Hence, the inversion process can get ambiguous.

              To accommodate this, you can provide the needed output size

              as an additional argument :attr:`output_size` in the forward call.

              See the Inputs and Example below.



    Args:

        kernel_size (int or tuple): Size of the max pooling window.

        stride (int or tuple): Stride of the max pooling window.

            It is set to :attr:`kernel_size` by default.

        padding (int or tuple): Padding that was added to the input



    Inputs:

        - `input`: the input Tensor to invert

        - `indices`: the indices given out by :class:`~torch.nn.MaxPool2d`

        - `output_size` (optional): the targeted output size



    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`.

        - Output: :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`, where



          .. math::

            H_{out} = (H_{in} - 1) \times \text{stride[0]} - 2 \times \text{padding[0]} + \text{kernel\_size[0]}



          .. math::

            W_{out} = (W_{in} - 1) \times \text{stride[1]} - 2 \times \text{padding[1]} + \text{kernel\_size[1]}



          or as given by :attr:`output_size` in the call operator



    Example::



        >>> pool = nn.MaxPool2d(2, stride=2, return_indices=True)

        >>> unpool = nn.MaxUnpool2d(2, stride=2)

        >>> input = torch.tensor([[[[ 1.,  2.,  3.,  4.],

                                    [ 5.,  6.,  7.,  8.],

                                    [ 9., 10., 11., 12.],

                                    [13., 14., 15., 16.]]]])

        >>> output, indices = pool(input)

        >>> unpool(output, indices)

        tensor([[[[  0.,   0.,   0.,   0.],

                  [  0.,   6.,   0.,   8.],

                  [  0.,   0.,   0.,   0.],

                  [  0.,  14.,   0.,  16.]]]])

        >>> # Now using output_size to resolve an ambiguous size for the inverse

        >>> input = torch.torch.tensor([[[[ 1.,  2.,  3., 4., 5.],

                                          [ 6.,  7.,  8., 9., 10.],

                                          [11., 12., 13., 14., 15.],

                                          [16., 17., 18., 19., 20.]]]])

        >>> output, indices = pool(input)

        >>> # This call will not work without specifying output_size

        >>> unpool(output, indices, output_size=input.size())

        tensor([[[[ 0.,  0.,  0.,  0.,  0.],

                  [ 0.,  7.,  0.,  9.,  0.],

                  [ 0.,  0.,  0.,  0.,  0.],

                  [ 0., 17.,  0., 19.,  0.]]]])





    """

    kernel_size: _size_2_t
    stride: _size_2_t
    padding: _size_2_t

    def __init__(self, kernel_size: _size_2_t, stride: Optional[_size_2_t] = None, padding: _size_2_t = 0) -> None:
        super().__init__()
        self.kernel_size = _pair(kernel_size)
        self.stride = _pair(stride if (stride is not None) else kernel_size)
        self.padding = _pair(padding)

    def forward(self, input: Tensor, indices: Tensor, output_size: Optional[List[int]] = None) -> Tensor:
        return F.max_unpool2d(input, indices, self.kernel_size, self.stride,
                              self.padding, output_size)


class MaxUnpool3d(_MaxUnpoolNd):
    r"""Computes a partial inverse of :class:`MaxPool3d`.



    :class:`MaxPool3d` is not fully invertible, since the non-maximal values are lost.

    :class:`MaxUnpool3d` takes in as input the output of :class:`MaxPool3d`

    including the indices of the maximal values and computes a partial inverse

    in which all non-maximal values are set to zero.



    Note:

        This operation may behave nondeterministically when the input indices has repeat values.

        See https://github.com/pytorch/pytorch/issues/80827 and :doc:`/notes/randomness` for more information.



    .. note:: :class:`MaxPool3d` can map several input sizes to the same output

              sizes. Hence, the inversion process can get ambiguous.

              To accommodate this, you can provide the needed output size

              as an additional argument :attr:`output_size` in the forward call.

              See the Inputs section below.



    Args:

        kernel_size (int or tuple): Size of the max pooling window.

        stride (int or tuple): Stride of the max pooling window.

            It is set to :attr:`kernel_size` by default.

        padding (int or tuple): Padding that was added to the input



    Inputs:

        - `input`: the input Tensor to invert

        - `indices`: the indices given out by :class:`~torch.nn.MaxPool3d`

        - `output_size` (optional): the targeted output size



    Shape:

        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` or :math:`(C, D_{out}, H_{out}, W_{out})`, where



          .. math::

              D_{out} = (D_{in} - 1) \times \text{stride[0]} - 2 \times \text{padding[0]} + \text{kernel\_size[0]}



          .. math::

              H_{out} = (H_{in} - 1) \times \text{stride[1]} - 2 \times \text{padding[1]} + \text{kernel\_size[1]}



          .. math::

              W_{out} = (W_{in} - 1) \times \text{stride[2]} - 2 \times \text{padding[2]} + \text{kernel\_size[2]}



          or as given by :attr:`output_size` in the call operator



    Example::



        >>> # pool of square window of size=3, stride=2

        >>> pool = nn.MaxPool3d(3, stride=2, return_indices=True)

        >>> unpool = nn.MaxUnpool3d(3, stride=2)

        >>> output, indices = pool(torch.randn(20, 16, 51, 33, 15))

        >>> unpooled_output = unpool(output, indices)

        >>> unpooled_output.size()

        torch.Size([20, 16, 51, 33, 15])

    """

    kernel_size: _size_3_t
    stride: _size_3_t
    padding: _size_3_t

    def __init__(self, kernel_size: _size_3_t, stride: Optional[_size_3_t] = None, padding: _size_3_t = 0) -> None:
        super().__init__()
        self.kernel_size = _triple(kernel_size)
        self.stride = _triple(stride if (stride is not None) else kernel_size)
        self.padding = _triple(padding)

    def forward(self, input: Tensor, indices: Tensor, output_size: Optional[List[int]] = None) -> Tensor:
        return F.max_unpool3d(input, indices, self.kernel_size, self.stride,
                              self.padding, output_size)


class _AvgPoolNd(Module):
    __constants__ = ['kernel_size', 'stride', 'padding', 'ceil_mode', 'count_include_pad']

    def extra_repr(self) -> str:
        return f'kernel_size={self.kernel_size}, stride={self.stride}, padding={self.padding}'


class AvgPool1d(_AvgPoolNd):
    r"""Applies a 1D average pooling over an input signal composed of several input planes.



    In the simplest case, the output value of the layer with input size :math:`(N, C, L)`,

    output :math:`(N, C, L_{out})` and :attr:`kernel_size` :math:`k`

    can be precisely described as:



    .. math::



        \text{out}(N_i, C_j, l) = \frac{1}{k} \sum_{m=0}^{k-1}

                               \text{input}(N_i, C_j, \text{stride} \times l + m)



    If :attr:`padding` is non-zero, then the input is implicitly zero-padded on both sides

    for :attr:`padding` number of points.



    Note:

        When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding

        or the input. Sliding windows that would start in the right padded region are ignored.



    The parameters :attr:`kernel_size`, :attr:`stride`, :attr:`padding` can each be

    an ``int`` or a one-element tuple.



    Args:

        kernel_size: the size of the window

        stride: the stride of the window. Default value is :attr:`kernel_size`

        padding: implicit zero padding to be added on both sides

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape

        count_include_pad: when True, will include the zero-padding in the averaging calculation



    Shape:

        - Input: :math:`(N, C, L_{in})` or :math:`(C, L_{in})`.

        - Output: :math:`(N, C, L_{out})` or :math:`(C, L_{out})`, where



          .. math::

              L_{out} = \left\lfloor \frac{L_{in} +

              2 \times \text{padding} - \text{kernel\_size}}{\text{stride}} + 1\right\rfloor



          Per the note above, if ``ceil_mode`` is True and :math:`(L_{out} - 1) \times \text{stride} \geq L_{in}

          + \text{padding}`, we skip the last window as it would start in the right padded region, resulting in

          :math:`L_{out}` being reduced by one.



    Examples::



        >>> # pool with window of size=3, stride=2

        >>> m = nn.AvgPool1d(3, stride=2)

        >>> m(torch.tensor([[[1., 2, 3, 4, 5, 6, 7]]]))

        tensor([[[2., 4., 6.]]])

    """

    kernel_size: _size_1_t
    stride: _size_1_t
    padding: _size_1_t
    ceil_mode: bool
    count_include_pad: bool

    def __init__(self, kernel_size: _size_1_t, stride: _size_1_t = None, padding: _size_1_t = 0, ceil_mode: bool = False,

                 count_include_pad: bool = True) -> None:
        super().__init__()
        self.kernel_size = _single(kernel_size)
        self.stride = _single(stride if stride is not None else kernel_size)
        self.padding = _single(padding)
        self.ceil_mode = ceil_mode
        self.count_include_pad = count_include_pad

    def forward(self, input: Tensor) -> Tensor:
        return F.avg_pool1d(
            input, self.kernel_size, self.stride, self.padding, self.ceil_mode,
            self.count_include_pad)


class AvgPool2d(_AvgPoolNd):
    r"""Applies a 2D average pooling over an input signal composed of several input planes.



    In the simplest case, the output value of the layer with input size :math:`(N, C, H, W)`,

    output :math:`(N, C, H_{out}, W_{out})` and :attr:`kernel_size` :math:`(kH, kW)`

    can be precisely described as:



    .. math::



        out(N_i, C_j, h, w)  = \frac{1}{kH * kW} \sum_{m=0}^{kH-1} \sum_{n=0}^{kW-1}

                               input(N_i, C_j, stride[0] \times h + m, stride[1] \times w + n)



    If :attr:`padding` is non-zero, then the input is implicitly zero-padded on both sides

    for :attr:`padding` number of points.



    Note:

        When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding

        or the input. Sliding windows that would start in the right padded region are ignored.



    The parameters :attr:`kernel_size`, :attr:`stride`, :attr:`padding` can either be:



        - a single ``int`` -- in which case the same value is used for the height and width dimension

        - a ``tuple`` of two ints -- in which case, the first `int` is used for the height dimension,

          and the second `int` for the width dimension



    Args:

        kernel_size: the size of the window

        stride: the stride of the window. Default value is :attr:`kernel_size`

        padding: implicit zero padding to be added on both sides

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape

        count_include_pad: when True, will include the zero-padding in the averaging calculation

        divisor_override: if specified, it will be used as divisor, otherwise size of the pooling region will be used.





    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`.

        - Output: :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`, where



          .. math::

              H_{out} = \left\lfloor\frac{H_{in}  + 2 \times \text{padding}[0] -

                \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor



          .. math::

              W_{out} = \left\lfloor\frac{W_{in}  + 2 \times \text{padding}[1] -

                \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor



          Per the note above, if ``ceil_mode`` is True and :math:`(H_{out} - 1)\times \text{stride}[0]\geq H_{in}

          + \text{padding}[0]`, we skip the last window as it would start in the bottom padded region,

          resulting in :math:`H_{out}` being reduced by one.



          The same applies for :math:`W_{out}`.



    Examples::



        >>> # pool of square window of size=3, stride=2

        >>> m = nn.AvgPool2d(3, stride=2)

        >>> # pool of non-square window

        >>> m = nn.AvgPool2d((3, 2), stride=(2, 1))

        >>> input = torch.randn(20, 16, 50, 32)

        >>> output = m(input)

    """

    __constants__ = ['kernel_size', 'stride', 'padding', 'ceil_mode', 'count_include_pad', 'divisor_override']

    kernel_size: _size_2_t
    stride: _size_2_t
    padding: _size_2_t
    ceil_mode: bool
    count_include_pad: bool

    def __init__(self, kernel_size: _size_2_t, stride: Optional[_size_2_t] = None, padding: _size_2_t = 0,

                 ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: Optional[int] = None) -> None:
        super().__init__()
        self.kernel_size = kernel_size
        self.stride = stride if (stride is not None) else kernel_size
        self.padding = padding
        self.ceil_mode = ceil_mode
        self.count_include_pad = count_include_pad
        self.divisor_override = divisor_override

    def forward(self, input: Tensor) -> Tensor:
        return F.avg_pool2d(input, self.kernel_size, self.stride,
                            self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override)


class AvgPool3d(_AvgPoolNd):
    r"""Applies a 3D average pooling over an input signal composed of several input planes.



    In the simplest case, the output value of the layer with input size :math:`(N, C, D, H, W)`,

    output :math:`(N, C, D_{out}, H_{out}, W_{out})` and :attr:`kernel_size` :math:`(kD, kH, kW)`

    can be precisely described as:



    .. math::

        \begin{aligned}

            \text{out}(N_i, C_j, d, h, w) ={} & \sum_{k=0}^{kD-1} \sum_{m=0}^{kH-1} \sum_{n=0}^{kW-1} \\

                                              & \frac{\text{input}(N_i, C_j, \text{stride}[0] \times d + k,

                                                      \text{stride}[1] \times h + m, \text{stride}[2] \times w + n)}

                                                     {kD \times kH \times kW}

        \end{aligned}



    If :attr:`padding` is non-zero, then the input is implicitly zero-padded on all three sides

    for :attr:`padding` number of points.



    Note:

        When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding

        or the input. Sliding windows that would start in the right padded region are ignored.



    The parameters :attr:`kernel_size`, :attr:`stride` can either be:



        - a single ``int`` -- in which case the same value is used for the depth, height and width dimension

        - a ``tuple`` of three ints -- in which case, the first `int` is used for the depth dimension,

          the second `int` for the height dimension and the third `int` for the width dimension



    Args:

        kernel_size: the size of the window

        stride: the stride of the window. Default value is :attr:`kernel_size`

        padding: implicit zero padding to be added on all three sides

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape

        count_include_pad: when True, will include the zero-padding in the averaging calculation

        divisor_override: if specified, it will be used as divisor, otherwise :attr:`kernel_size` will be used



    Shape:

        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` or

          :math:`(C, D_{out}, H_{out}, W_{out})`, where



          .. math::

              D_{out} = \left\lfloor\frac{D_{in} + 2 \times \text{padding}[0] -

                    \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor



          .. math::

              H_{out} = \left\lfloor\frac{H_{in} + 2 \times \text{padding}[1] -

                    \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor



          .. math::

              W_{out} = \left\lfloor\frac{W_{in} + 2 \times \text{padding}[2] -

                    \text{kernel\_size}[2]}{\text{stride}[2]} + 1\right\rfloor



          Per the note above, if ``ceil_mode`` is True and :math:`(D_{out} - 1)\times \text{stride}[0]\geq D_{in}

          + \text{padding}[0]`, we skip the last window as it would start in the padded region,

          resulting in :math:`D_{out}` being reduced by one.



          The same applies for :math:`W_{out}` and :math:`H_{out}`.



    Examples::



        >>> # pool of square window of size=3, stride=2

        >>> m = nn.AvgPool3d(3, stride=2)

        >>> # pool of non-square window

        >>> m = nn.AvgPool3d((3, 2, 2), stride=(2, 1, 2))

        >>> input = torch.randn(20, 16, 50, 44, 31)

        >>> output = m(input)

    """

    __constants__ = ['kernel_size', 'stride', 'padding', 'ceil_mode', 'count_include_pad', 'divisor_override']

    kernel_size: _size_3_t
    stride: _size_3_t
    padding: _size_3_t
    ceil_mode: bool
    count_include_pad: bool

    def __init__(self, kernel_size: _size_3_t, stride: Optional[_size_3_t] = None, padding: _size_3_t = 0,

                 ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: Optional[int] = None) -> None:
        super().__init__()
        self.kernel_size = kernel_size
        self.stride = stride if (stride is not None) else kernel_size
        self.padding = padding
        self.ceil_mode = ceil_mode
        self.count_include_pad = count_include_pad
        self.divisor_override = divisor_override

    def forward(self, input: Tensor) -> Tensor:
        return F.avg_pool3d(input, self.kernel_size, self.stride,
                            self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override)

    def __setstate__(self, d):
        super().__setstate__(d)
        self.__dict__.setdefault('padding', 0)
        self.__dict__.setdefault('ceil_mode', False)
        self.__dict__.setdefault('count_include_pad', True)


class FractionalMaxPool2d(Module):
    r"""Applies a 2D fractional max pooling over an input signal composed of several input planes.



    Fractional MaxPooling is described in detail in the paper `Fractional MaxPooling`_ by Ben Graham



    The max-pooling operation is applied in :math:`kH \times kW` regions by a stochastic

    step size determined by the target output size.

    The number of output features is equal to the number of input planes.



    .. note:: Exactly one of ``output_size`` or ``output_ratio`` must be defined.



    Args:

        kernel_size: the size of the window to take a max over.

                     Can be a single number k (for a square kernel of k x k) or a tuple `(kh, kw)`

        output_size: the target output size of the image of the form `oH x oW`.

                     Can be a tuple `(oH, oW)` or a single number oH for a square image `oH x oH`.

                     Note that we must have :math:`kH + oH - 1 <= H_{in}` and :math:`kW + oW - 1 <= W_{in}`

        output_ratio: If one wants to have an output size as a ratio of the input size, this option can be given.

                      This has to be a number or tuple in the range (0, 1).

                      Note that we must have :math:`kH + (output\_ratio\_H * H_{in}) - 1 <= H_{in}`

                      and :math:`kW + (output\_ratio\_W * W_{in}) - 1 <= W_{in}`

        return_indices: if ``True``, will return the indices along with the outputs.

                        Useful to pass to :meth:`nn.MaxUnpool2d`. Default: ``False``



    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`.

        - Output: :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`, where

          :math:`(H_{out}, W_{out})=\text{output\_size}` or

          :math:`(H_{out}, W_{out})=\text{output\_ratio} \times (H_{in}, W_{in})`.



    Examples:

        >>> # pool of square window of size=3, and target output size 13x12

        >>> m = nn.FractionalMaxPool2d(3, output_size=(13, 12))

        >>> # pool of square window and target output size being half of input image size

        >>> m = nn.FractionalMaxPool2d(3, output_ratio=(0.5, 0.5))

        >>> input = torch.randn(20, 16, 50, 32)

        >>> output = m(input)



    .. _Fractional MaxPooling:

        https://arxiv.org/abs/1412.6071

    """

    __constants__ = ['kernel_size', 'return_indices', 'output_size',
                     'output_ratio']

    kernel_size: _size_2_t
    return_indices: bool
    output_size: _size_2_t
    output_ratio: _ratio_2_t

    def __init__(self, kernel_size: _size_2_t, output_size: Optional[_size_2_t] = None,

                 output_ratio: Optional[_ratio_2_t] = None,

                 return_indices: bool = False, _random_samples=None) -> None:
        super().__init__()
        self.kernel_size = _pair(kernel_size)
        self.return_indices = return_indices
        self.register_buffer('_random_samples', _random_samples)
        self.output_size = _pair(output_size) if output_size is not None else None
        self.output_ratio = _pair(output_ratio) if output_ratio is not None else None
        if output_size is None and output_ratio is None:
            raise ValueError("FractionalMaxPool2d requires specifying either "
                             "an output size, or a pooling ratio")
        if output_size is not None and output_ratio is not None:
            raise ValueError("only one of output_size and output_ratio may be specified")
        if self.output_ratio is not None:
            if not (0 < self.output_ratio[0] < 1 and 0 < self.output_ratio[1] < 1):
                raise ValueError(f"output_ratio must be between 0 and 1 (got {output_ratio})")

    def forward(self, input: Tensor):
        return F.fractional_max_pool2d(
            input, self.kernel_size, self.output_size, self.output_ratio,
            self.return_indices,
            _random_samples=self._random_samples)


class FractionalMaxPool3d(Module):
    r"""Applies a 3D fractional max pooling over an input signal composed of several input planes.



    Fractional MaxPooling is described in detail in the paper `Fractional MaxPooling`_ by Ben Graham



    The max-pooling operation is applied in :math:`kT \times kH \times kW` regions by a stochastic

    step size determined by the target output size.

    The number of output features is equal to the number of input planes.



    .. note:: Exactly one of ``output_size`` or ``output_ratio`` must be defined.



    Args:

        kernel_size: the size of the window to take a max over.

                     Can be a single number k (for a square kernel of k x k x k) or a tuple `(kt x kh x kw)`

        output_size: the target output size of the image of the form `oT x oH x oW`.

                     Can be a tuple `(oT, oH, oW)` or a single number oH for a square image `oH x oH x oH`

        output_ratio: If one wants to have an output size as a ratio of the input size, this option can be given.

                      This has to be a number or tuple in the range (0, 1)

        return_indices: if ``True``, will return the indices along with the outputs.

                        Useful to pass to :meth:`nn.MaxUnpool3d`. Default: ``False``



    Shape:

        - Input: :math:`(N, C, T_{in}, H_{in}, W_{in})` or :math:`(C, T_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, T_{out}, H_{out}, W_{out})` or :math:`(C, T_{out}, H_{out}, W_{out})`, where

          :math:`(T_{out}, H_{out}, W_{out})=\text{output\_size}` or

          :math:`(T_{out}, H_{out}, W_{out})=\text{output\_ratio} \times (T_{in}, H_{in}, W_{in})`



    Examples:

        >>> # pool of cubic window of size=3, and target output size 13x12x11

        >>> m = nn.FractionalMaxPool3d(3, output_size=(13, 12, 11))

        >>> # pool of cubic window and target output size being half of input size

        >>> m = nn.FractionalMaxPool3d(3, output_ratio=(0.5, 0.5, 0.5))

        >>> input = torch.randn(20, 16, 50, 32, 16)

        >>> output = m(input)



    .. _Fractional MaxPooling:

        https://arxiv.org/abs/1412.6071

    """

    __constants__ = ['kernel_size', 'return_indices', 'output_size',
                     'output_ratio']
    kernel_size: _size_3_t
    return_indices: bool
    output_size: _size_3_t
    output_ratio: _ratio_3_t

    def __init__(self, kernel_size: _size_3_t, output_size: Optional[_size_3_t] = None,

                 output_ratio: Optional[_ratio_3_t] = None,

                 return_indices: bool = False, _random_samples=None) -> None:
        super().__init__()
        self.kernel_size = _triple(kernel_size)
        self.return_indices = return_indices
        self.register_buffer('_random_samples', _random_samples)
        self.output_size = _triple(output_size) if output_size is not None else None
        self.output_ratio = _triple(output_ratio) if output_ratio is not None else None
        if output_size is None and output_ratio is None:
            raise ValueError("FractionalMaxPool3d requires specifying either "
                             "an output size, or a pooling ratio")
        if output_size is not None and output_ratio is not None:
            raise ValueError("only one of output_size and output_ratio may be specified")
        if self.output_ratio is not None:
            if not (0 < self.output_ratio[0] < 1 and 0 < self.output_ratio[1] < 1 and 0 < self.output_ratio[2] < 1):
                raise ValueError(f"output_ratio must be between 0 and 1 (got {output_ratio})")

    def forward(self, input: Tensor):
        return F.fractional_max_pool3d(
            input, self.kernel_size, self.output_size, self.output_ratio,
            self.return_indices,
            _random_samples=self._random_samples)


class _LPPoolNd(Module):
    __constants__ = ['norm_type', 'kernel_size', 'stride', 'ceil_mode']

    norm_type: float
    ceil_mode: bool

    def __init__(self, norm_type: float, kernel_size: _size_any_t, stride: Optional[_size_any_t] = None,

                 ceil_mode: bool = False) -> None:
        super().__init__()
        self.norm_type = norm_type
        self.kernel_size = kernel_size
        self.stride = stride
        self.ceil_mode = ceil_mode

    def extra_repr(self) -> str:
        return 'norm_type={norm_type}, kernel_size={kernel_size}, stride={stride}, ' \
            'ceil_mode={ceil_mode}'.format(**self.__dict__)


class LPPool1d(_LPPoolNd):
    r"""Applies a 1D power-average pooling over an input signal composed of several input planes.



    On each window, the function computed is:



    .. math::

        f(X) = \sqrt[p]{\sum_{x \in X} x^{p}}



    - At p = :math:`\infty`, one gets Max Pooling

    - At p = 1, one gets Sum Pooling (which is proportional to Average Pooling)



    .. note:: If the sum to the power of `p` is zero, the gradient of this function is

              not defined. This implementation will set the gradient to zero in this case.



    Args:

        kernel_size: a single int, the size of the window

        stride: a single int, the stride of the window. Default value is :attr:`kernel_size`

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape



    Shape:

        - Input: :math:`(N, C, L_{in})` or :math:`(C, L_{in})`.

        - Output: :math:`(N, C, L_{out})` or :math:`(C, L_{out})`, where



          .. math::

              L_{out} = \left\lfloor\frac{L_{in} - \text{kernel\_size}}{\text{stride}} + 1\right\rfloor



    Examples::

        >>> # power-2 pool of window of length 3, with stride 2.

        >>> m = nn.LPPool1d(2, 3, stride=2)

        >>> input = torch.randn(20, 16, 50)

        >>> output = m(input)

    """

    kernel_size: _size_1_t
    stride: _size_1_t

    def forward(self, input: Tensor) -> Tensor:
        return F.lp_pool1d(input, float(self.norm_type), self.kernel_size,
                           self.stride, self.ceil_mode)


class LPPool2d(_LPPoolNd):
    r"""Applies a 2D power-average pooling over an input signal composed of several input planes.



    On each window, the function computed is:



    .. math::

        f(X) = \sqrt[p]{\sum_{x \in X} x^{p}}



    - At p = :math:`\infty`, one gets Max Pooling

    - At p = 1, one gets Sum Pooling (which is proportional to average pooling)



    The parameters :attr:`kernel_size`, :attr:`stride` can either be:



        - a single ``int`` -- in which case the same value is used for the height and width dimension

        - a ``tuple`` of two ints -- in which case, the first `int` is used for the height dimension,

          and the second `int` for the width dimension



    .. note:: If the sum to the power of `p` is zero, the gradient of this function is

              not defined. This implementation will set the gradient to zero in this case.



    Args:

        kernel_size: the size of the window

        stride: the stride of the window. Default value is :attr:`kernel_size`

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape



    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`.

        - Output: :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`, where



          .. math::

              H_{out} = \left\lfloor\frac{H_{in} - \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor



          .. math::

              W_{out} = \left\lfloor\frac{W_{in} - \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor



    Examples::



        >>> # power-2 pool of square window of size=3, stride=2

        >>> m = nn.LPPool2d(2, 3, stride=2)

        >>> # pool of non-square window of power 1.2

        >>> m = nn.LPPool2d(1.2, (3, 2), stride=(2, 1))

        >>> input = torch.randn(20, 16, 50, 32)

        >>> output = m(input)



    """

    kernel_size: _size_2_t
    stride: _size_2_t

    def forward(self, input: Tensor) -> Tensor:
        return F.lp_pool2d(input, float(self.norm_type), self.kernel_size,
                           self.stride, self.ceil_mode)


class LPPool3d(_LPPoolNd):
    r"""Applies a 3D power-average pooling over an input signal composed of several input planes.



    On each window, the function computed is:



    .. math::

        f(X) = \sqrt[p]{\sum_{x \in X} x^{p}}



    - At p = :math:`\infty`, one gets Max Pooling

    - At p = 1, one gets Sum Pooling (which is proportional to average pooling)



    The parameters :attr:`kernel_size`, :attr:`stride` can either be:



        - a single ``int`` -- in which case the same value is used for the height, width and depth dimension

        - a ``tuple`` of three ints -- in which case, the first `int` is used for the depth dimension,

          the second `int` for the height dimension and the third `int` for the width dimension



    .. note:: If the sum to the power of `p` is zero, the gradient of this function is

              not defined. This implementation will set the gradient to zero in this case.



    Args:

        kernel_size: the size of the window

        stride: the stride of the window. Default value is :attr:`kernel_size`

        ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape



    Shape:

        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` or

          :math:`(C, D_{out}, H_{out}, W_{out})`, where



          .. math::

              D_{out} = \left\lfloor\frac{D_{in} - \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor



          .. math::

              H_{out} = \left\lfloor\frac{H_{in} - \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor



          .. math::

              W_{out} = \left\lfloor\frac{W_{in} - \text{kernel\_size}[2]}{\text{stride}[2]} + 1\right\rfloor



    Examples::



        >>> # power-2 pool of square window of size=3, stride=2

        >>> m = nn.LPPool3d(2, 3, stride=2)

        >>> # pool of non-square window of power 1.2

        >>> m = nn.LPPool3d(1.2, (3, 2, 2), stride=(2, 1, 2))

        >>> input = torch.randn(20, 16, 50, 44, 31)

        >>> output = m(input)



    """

    kernel_size: _size_3_t
    stride: _size_3_t

    def forward(self, input: Tensor) -> Tensor:
        return F.lp_pool3d(input, float(self.norm_type), self.kernel_size,
                           self.stride, self.ceil_mode)


class _AdaptiveMaxPoolNd(Module):
    __constants__ = ['output_size', 'return_indices']
    return_indices: bool

    def __init__(self, output_size: _size_any_opt_t, return_indices: bool = False) -> None:
        super().__init__()
        self.output_size = output_size
        self.return_indices = return_indices

    def extra_repr(self) -> str:
        return f'output_size={self.output_size}'

# FIXME (by @ssnl): Improve adaptive pooling docs: specify what the input and
#   output shapes are, and how the operation computes output.


class AdaptiveMaxPool1d(_AdaptiveMaxPoolNd):
    r"""Applies a 1D adaptive max pooling over an input signal composed of several input planes.



    The output size is :math:`L_{out}`, for any input size.

    The number of output features is equal to the number of input planes.



    Args:

        output_size: the target output size :math:`L_{out}`.

        return_indices: if ``True``, will return the indices along with the outputs.

                        Useful to pass to nn.MaxUnpool1d. Default: ``False``



    Shape:

        - Input: :math:`(N, C, L_{in})` or :math:`(C, L_{in})`.

        - Output: :math:`(N, C, L_{out})` or :math:`(C, L_{out})`, where

          :math:`L_{out}=\text{output\_size}`.



    Examples:

        >>> # target output size of 5

        >>> m = nn.AdaptiveMaxPool1d(5)

        >>> input = torch.randn(1, 64, 8)

        >>> output = m(input)



    """

    output_size: _size_1_t

    def forward(self, input: Tensor):
        return F.adaptive_max_pool1d(input, self.output_size, self.return_indices)


class AdaptiveMaxPool2d(_AdaptiveMaxPoolNd):
    r"""Applies a 2D adaptive max pooling over an input signal composed of several input planes.



    The output is of size :math:`H_{out} \times W_{out}`, for any input size.

    The number of output features is equal to the number of input planes.



    Args:

        output_size: the target output size of the image of the form :math:`H_{out} \times W_{out}`.

                     Can be a tuple :math:`(H_{out}, W_{out})` or a single :math:`H_{out}` for a

                     square image :math:`H_{out} \times H_{out}`. :math:`H_{out}` and :math:`W_{out}`

                     can be either a ``int``, or ``None`` which means the size will be the same as that

                     of the input.

        return_indices: if ``True``, will return the indices along with the outputs.

                        Useful to pass to nn.MaxUnpool2d. Default: ``False``



    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`.

        - Output: :math:`(N, C, H_{out}, W_{out})` or :math:`(C, H_{out}, W_{out})`, where

          :math:`(H_{out}, W_{out})=\text{output\_size}`.



    Examples:

        >>> # target output size of 5x7

        >>> m = nn.AdaptiveMaxPool2d((5, 7))

        >>> input = torch.randn(1, 64, 8, 9)

        >>> output = m(input)

        >>> # target output size of 7x7 (square)

        >>> m = nn.AdaptiveMaxPool2d(7)

        >>> input = torch.randn(1, 64, 10, 9)

        >>> output = m(input)

        >>> # target output size of 10x7

        >>> m = nn.AdaptiveMaxPool2d((None, 7))

        >>> input = torch.randn(1, 64, 10, 9)

        >>> output = m(input)



    """

    output_size: _size_2_opt_t

    def forward(self, input: Tensor):
        return F.adaptive_max_pool2d(input, self.output_size, self.return_indices)


class AdaptiveMaxPool3d(_AdaptiveMaxPoolNd):
    r"""Applies a 3D adaptive max pooling over an input signal composed of several input planes.



    The output is of size :math:`D_{out} \times H_{out} \times W_{out}`, for any input size.

    The number of output features is equal to the number of input planes.



    Args:

        output_size: the target output size of the image of the form :math:`D_{out} \times H_{out} \times W_{out}`.

                     Can be a tuple :math:`(D_{out}, H_{out}, W_{out})` or a single

                     :math:`D_{out}` for a cube :math:`D_{out} \times D_{out} \times D_{out}`.

                     :math:`D_{out}`, :math:`H_{out}` and :math:`W_{out}` can be either a

                     ``int``, or ``None`` which means the size will be the same as that of the input.



        return_indices: if ``True``, will return the indices along with the outputs.

                        Useful to pass to nn.MaxUnpool3d. Default: ``False``



    Shape:

        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` or :math:`(C, D_{out}, H_{out}, W_{out})`,

          where :math:`(D_{out}, H_{out}, W_{out})=\text{output\_size}`.



    Examples:

        >>> # target output size of 5x7x9

        >>> m = nn.AdaptiveMaxPool3d((5, 7, 9))

        >>> input = torch.randn(1, 64, 8, 9, 10)

        >>> output = m(input)

        >>> # target output size of 7x7x7 (cube)

        >>> m = nn.AdaptiveMaxPool3d(7)

        >>> input = torch.randn(1, 64, 10, 9, 8)

        >>> output = m(input)

        >>> # target output size of 7x9x8

        >>> m = nn.AdaptiveMaxPool3d((7, None, None))

        >>> input = torch.randn(1, 64, 10, 9, 8)

        >>> output = m(input)



    """

    output_size: _size_3_opt_t

    def forward(self, input: Tensor):
        return F.adaptive_max_pool3d(input, self.output_size, self.return_indices)


class _AdaptiveAvgPoolNd(Module):
    __constants__ = ['output_size']

    def __init__(self, output_size: _size_any_opt_t) -> None:
        super().__init__()
        self.output_size = output_size

    def extra_repr(self) -> str:
        return f'output_size={self.output_size}'


class AdaptiveAvgPool1d(_AdaptiveAvgPoolNd):
    r"""Applies a 1D adaptive average pooling over an input signal composed of several input planes.



    The output size is :math:`L_{out}`, for any input size.

    The number of output features is equal to the number of input planes.



    Args:

        output_size: the target output size :math:`L_{out}`.



    Shape:

        - Input: :math:`(N, C, L_{in})` or :math:`(C, L_{in})`.

        - Output: :math:`(N, C, L_{out})` or :math:`(C, L_{out})`, where

          :math:`L_{out}=\text{output\_size}`.



    Examples:

        >>> # target output size of 5

        >>> m = nn.AdaptiveAvgPool1d(5)

        >>> input = torch.randn(1, 64, 8)

        >>> output = m(input)



    """

    output_size: _size_1_t

    def forward(self, input: Tensor) -> Tensor:
        return F.adaptive_avg_pool1d(input, self.output_size)


class AdaptiveAvgPool2d(_AdaptiveAvgPoolNd):
    r"""Applies a 2D adaptive average pooling over an input signal composed of several input planes.



    The output is of size H x W, for any input size.

    The number of output features is equal to the number of input planes.



    Args:

        output_size: the target output size of the image of the form H x W.

                     Can be a tuple (H, W) or a single H for a square image H x H.

                     H and W can be either a ``int``, or ``None`` which means the size will

                     be the same as that of the input.



    Shape:

        - Input: :math:`(N, C, H_{in}, W_{in})` or :math:`(C, H_{in}, W_{in})`.

        - Output: :math:`(N, C, S_{0}, S_{1})` or :math:`(C, S_{0}, S_{1})`, where

          :math:`S=\text{output\_size}`.



    Examples:

        >>> # target output size of 5x7

        >>> m = nn.AdaptiveAvgPool2d((5, 7))

        >>> input = torch.randn(1, 64, 8, 9)

        >>> output = m(input)

        >>> # target output size of 7x7 (square)

        >>> m = nn.AdaptiveAvgPool2d(7)

        >>> input = torch.randn(1, 64, 10, 9)

        >>> output = m(input)

        >>> # target output size of 10x7

        >>> m = nn.AdaptiveAvgPool2d((None, 7))

        >>> input = torch.randn(1, 64, 10, 9)

        >>> output = m(input)



    """

    output_size: _size_2_opt_t

    def forward(self, input: Tensor) -> Tensor:
        return F.adaptive_avg_pool2d(input, self.output_size)


class AdaptiveAvgPool3d(_AdaptiveAvgPoolNd):
    r"""Applies a 3D adaptive average pooling over an input signal composed of several input planes.



    The output is of size D x H x W, for any input size.

    The number of output features is equal to the number of input planes.



    Args:

        output_size: the target output size of the form D x H x W.

                     Can be a tuple (D, H, W) or a single number D for a cube D x D x D.

                     D, H and W can be either a ``int``, or ``None`` which means the size will

                     be the same as that of the input.



    Shape:

        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})` or :math:`(C, D_{in}, H_{in}, W_{in})`.

        - Output: :math:`(N, C, S_{0}, S_{1}, S_{2})` or :math:`(C, S_{0}, S_{1}, S_{2})`,

          where :math:`S=\text{output\_size}`.



    Examples:

        >>> # target output size of 5x7x9

        >>> m = nn.AdaptiveAvgPool3d((5, 7, 9))

        >>> input = torch.randn(1, 64, 8, 9, 10)

        >>> output = m(input)

        >>> # target output size of 7x7x7 (cube)

        >>> m = nn.AdaptiveAvgPool3d(7)

        >>> input = torch.randn(1, 64, 10, 9, 8)

        >>> output = m(input)

        >>> # target output size of 7x9x8

        >>> m = nn.AdaptiveAvgPool3d((7, None, None))

        >>> input = torch.randn(1, 64, 10, 9, 8)

        >>> output = m(input)



    """

    output_size: _size_3_opt_t

    def forward(self, input: Tensor) -> Tensor:
        return F.adaptive_avg_pool3d(input, self.output_size)