File size: 64,989 Bytes
a6dac9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
"""PyTorch ResNet

This started as a copy of https://github.com/pytorch/vision 'resnet.py' (BSD-3-Clause) with
additional dropout and dynamic global avg/max pool.

ResNeXt, SE-ResNeXt, SENet, and MXNet Gluon stem/downsample variants, tiered stems added by Ross Wightman
Copyright 2020 Ross Wightman
"""
import math
from functools import partial

import torch
import torch.nn as nn
import torch.nn.functional as F

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from .helpers import build_model_with_cfg
from .layers import DropBlock2d, DropPath, AvgPool2dSame, BlurPool2d, create_attn, get_attn, create_classifier
from .registry import register_model

__all__ = ['ResNet', 'BasicBlock', 'Bottleneck']  # model_registry will add each entrypoint fn to this


def _cfg(url='', **kwargs):
    return {
        'url': url,
        'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': (7, 7),
        'crop_pct': 0.875, 'interpolation': 'bilinear',
        'mean': IMAGENET_DEFAULT_MEAN, 'std': IMAGENET_DEFAULT_STD,
        'first_conv': 'conv1', 'classifier': 'fc',
        **kwargs
    }


default_cfgs = {
    # ResNet and Wide ResNet
    'resnet18': _cfg(url='https://download.pytorch.org/models/resnet18-5c106cde.pth'),
    'resnet18d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet18d_ra2-48a79e06.pth',
        interpolation='bicubic', first_conv='conv1.0'),
    'resnet34': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet34-43635321.pth'),
    'resnet34d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet34d_ra2-f8dcfcaf.pth',
        interpolation='bicubic', first_conv='conv1.0'),
    'resnet26': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet26-9aa10e23.pth',
        interpolation='bicubic'),
    'resnet26d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet26d-69e92c46.pth',
        interpolation='bicubic', first_conv='conv1.0'),
    'resnet26t': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8)),
    'resnet50': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50_ram-a26f946b.pth',
        interpolation='bicubic'),
    'resnet50d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50d_ra2-464e36ba.pth',
        interpolation='bicubic', first_conv='conv1.0'),
    'resnet50t': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0'),
    'resnet101': _cfg(url='', interpolation='bicubic'),
    'resnet101d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet101d_ra2-2803ffab.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8),
        crop_pct=1.0, test_input_size=(3, 320, 320)),
    'resnet152': _cfg(url='', interpolation='bicubic'),
    'resnet152d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet152d_ra2-5cac0439.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8),
        crop_pct=1.0, test_input_size=(3, 320, 320)),
    'resnet200': _cfg(url='', interpolation='bicubic'),
    'resnet200d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet200d_ra2-bdba9bf9.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8),
        crop_pct=1.0, test_input_size=(3, 320, 320)),
    'tv_resnet34': _cfg(url='https://download.pytorch.org/models/resnet34-333f7ec4.pth'),
    'tv_resnet50': _cfg(url='https://download.pytorch.org/models/resnet50-19c8e357.pth'),
    'tv_resnet101': _cfg(url='https://download.pytorch.org/models/resnet101-5d3b4d8f.pth'),
    'tv_resnet152': _cfg(url='https://download.pytorch.org/models/resnet152-b121ed2d.pth'),
    'wide_resnet50_2': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/wide_resnet50_racm-8234f177.pth',
        interpolation='bicubic'),
    'wide_resnet101_2': _cfg(url='https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth'),

    # ResNeXt
    'resnext50_32x4d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnext50_32x4d_ra-d733960d.pth',
        interpolation='bicubic'),
    'resnext50d_32x4d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnext50d_32x4d-103e99f8.pth',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'resnext101_32x4d': _cfg(url=''),
    'resnext101_32x8d': _cfg(url='https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth'),
    'resnext101_64x4d': _cfg(url=''),
    'tv_resnext50_32x4d': _cfg(url='https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth'),

    #  ResNeXt models - Weakly Supervised Pretraining on Instagram Hashtags
    #  from https://github.com/facebookresearch/WSL-Images
    #  Please note the CC-BY-NC 4.0 license on theses weights, non-commercial use only.
    'ig_resnext101_32x8d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x8-c38310e5.pth'),
    'ig_resnext101_32x16d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x16-c6f796b0.pth'),
    'ig_resnext101_32x32d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x32-e4b90b00.pth'),
    'ig_resnext101_32x48d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x48-3e41cc8a.pth'),

    #  Semi-Supervised ResNe*t models from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models
    #  Please note the CC-BY-NC 4.0 license on theses weights, non-commercial use only.
    'ssl_resnet18':  _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnet18-d92f0530.pth'),
    'ssl_resnet50':  _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnet50-08389792.pth'),
    'ssl_resnext50_32x4d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext50_32x4-ddb3e555.pth'),
    'ssl_resnext101_32x4d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext101_32x4-dc43570a.pth'),
    'ssl_resnext101_32x8d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext101_32x8-2cfe2f8b.pth'),
    'ssl_resnext101_32x16d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext101_32x16-15fffa57.pth'),

    #  Semi-Weakly Supervised ResNe*t models from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models
    #  Please note the CC-BY-NC 4.0 license on theses weights, non-commercial use only.
    'swsl_resnet18': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnet18-118f1556.pth'),
    'swsl_resnet50': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnet50-16a12f1b.pth'),
    'swsl_resnext50_32x4d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnext50_32x4-72679e44.pth'),
    'swsl_resnext101_32x4d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnext101_32x4-3f87e46b.pth'),
    'swsl_resnext101_32x8d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnext101_32x8-b4712904.pth'),
    'swsl_resnext101_32x16d': _cfg(
        url='https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnext101_32x16-f3559a9c.pth'),

    #  Squeeze-Excitation ResNets, to eventually replace the models in senet.py
    'seresnet18': _cfg(
        url='',
        interpolation='bicubic'),
    'seresnet34': _cfg(
        url='',
        interpolation='bicubic'),
    'seresnet50': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/seresnet50_ra_224-8efdb4bb.pth',
        interpolation='bicubic'),
    'seresnet50t': _cfg(
        url='',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'seresnet101': _cfg(
        url='',
        interpolation='bicubic'),
    'seresnet152': _cfg(
        url='',
        interpolation='bicubic'),
    'seresnet152d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/seresnet152d_ra2-04464dd2.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8),
        crop_pct=1.0, test_input_size=(3, 320, 320)
    ),
    'seresnet200d': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), crop_pct=0.94, pool_size=(8, 8)),
    'seresnet269d': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), crop_pct=0.94, pool_size=(8, 8)),


    #  Squeeze-Excitation ResNeXts, to eventually replace the models in senet.py
    'seresnext26d_32x4d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/seresnext26d_32x4d-80fa48a3.pth',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'seresnext26t_32x4d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/seresnext26tn_32x4d-569cb627.pth',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'seresnext50_32x4d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/seresnext50_32x4d_racm-a304a460.pth',
        interpolation='bicubic'),
    'seresnext101_32x4d': _cfg(
        url='',
        interpolation='bicubic'),
    'seresnext101_32x8d': _cfg(
        url='',
        interpolation='bicubic'),
    'senet154': _cfg(
        url='',
        interpolation='bicubic',
        first_conv='conv1.0'),

    # Efficient Channel Attention ResNets
    'ecaresnet26t': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/ecaresnet26t_ra2-46609757.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8),
        crop_pct=0.95, test_input_size=(3, 320, 320)),
    'ecaresnetlight': _cfg(
        url='https://imvl-automl-sh.oss-cn-shanghai.aliyuncs.com/darts/hyperml/hyperml/job_45402/outputs/ECAResNetLight_4f34b35b.pth',
        interpolation='bicubic'),
    'ecaresnet50d': _cfg(
        url='https://imvl-automl-sh.oss-cn-shanghai.aliyuncs.com/darts/hyperml/hyperml/job_45402/outputs/ECAResNet50D_833caf58.pth',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'ecaresnet50d_pruned': _cfg(
        url='https://imvl-automl-sh.oss-cn-shanghai.aliyuncs.com/darts/hyperml/hyperml/job_45899/outputs/ECAResNet50D_P_9c67f710.pth',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'ecaresnet50t': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/ecaresnet50t_ra2-f7ac63c4.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), pool_size=(8, 8),
        crop_pct=0.95, test_input_size=(3, 320, 320)),
    'ecaresnet101d': _cfg(
        url='https://imvl-automl-sh.oss-cn-shanghai.aliyuncs.com/darts/hyperml/hyperml/job_45402/outputs/ECAResNet101D_281c5844.pth',
        interpolation='bicubic', first_conv='conv1.0'),
    'ecaresnet101d_pruned': _cfg(
        url='https://imvl-automl-sh.oss-cn-shanghai.aliyuncs.com/darts/hyperml/hyperml/job_45610/outputs/ECAResNet101D_P_75a3370e.pth',
        interpolation='bicubic',
        first_conv='conv1.0'),
    'ecaresnet200d': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 256, 256), crop_pct=0.94, pool_size=(8, 8)),
    'ecaresnet269d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/ecaresnet269d_320_ra2-7baa55cb.pth',
        interpolation='bicubic', first_conv='conv1.0', input_size=(3, 320, 320), pool_size=(10, 10),
        crop_pct=1.0, test_input_size=(3, 352, 352)),

    # Efficient Channel Attention ResNeXts
    'ecaresnext26t_32x4d': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0'),
    'ecaresnext50t_32x4d': _cfg(
        url='',
        interpolation='bicubic', first_conv='conv1.0'),

    # ResNets with anti-aliasing blur pool
    'resnetblur18': _cfg(
        interpolation='bicubic'),
    'resnetblur50': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnetblur50-84f4748f.pth',
        interpolation='bicubic'),

    # ResNet-RS models
    'resnetrs50': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs50_ema-6b53758b.pth',
        input_size=(3, 160, 160), pool_size=(5, 5), crop_pct=0.91, test_input_size=(3, 224, 224),
        interpolation='bicubic', first_conv='conv1.0'),
    'resnetrs101': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs101_i192_ema-1509bbf6.pth',
        input_size=(3, 192, 192), pool_size=(6, 6), crop_pct=0.94, test_input_size=(3, 288, 288),
        interpolation='bicubic', first_conv='conv1.0'),
    'resnetrs152': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs152_i256_ema-a9aff7f9.pth',
        input_size=(3, 256, 256), pool_size=(8, 8), crop_pct=1.0, test_input_size=(3, 320, 320),
        interpolation='bicubic', first_conv='conv1.0'),
    'resnetrs200': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs200_ema-623d2f59.pth',
        input_size=(3, 256, 256), pool_size=(8, 8), crop_pct=1.0, test_input_size=(3, 320, 320),
        interpolation='bicubic', first_conv='conv1.0'),
    'resnetrs270': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs270_ema-b40e674c.pth',
        input_size=(3, 256, 256), pool_size=(8, 8), crop_pct=1.0, test_input_size=(3, 352, 352),
        interpolation='bicubic', first_conv='conv1.0'),
    'resnetrs350': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs350_i256_ema-5a1aa8f1.pth',
        input_size=(3, 288, 288), pool_size=(9, 9), crop_pct=1.0, test_input_size=(3, 384, 384),
        interpolation='bicubic', first_conv='conv1.0'),
    'resnetrs420': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rs-weights/resnetrs420_ema-972dee69.pth',
        input_size=(3, 320, 320), pool_size=(10, 10), crop_pct=1.0, test_input_size=(3, 416, 416),
        interpolation='bicubic', first_conv='conv1.0'),
}


def get_padding(kernel_size, stride, dilation=1):
    padding = ((stride - 1) + dilation * (kernel_size - 1)) // 2
    return padding


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, cardinality=1, base_width=64,
                 reduce_first=1, dilation=1, first_dilation=None, act_layer=nn.ReLU, norm_layer=nn.BatchNorm2d,
                 attn_layer=None, aa_layer=None, drop_block=None, drop_path=None):
        super(BasicBlock, self).__init__()

        assert cardinality == 1, 'BasicBlock only supports cardinality of 1'
        assert base_width == 64, 'BasicBlock does not support changing base width'
        first_planes = planes // reduce_first
        outplanes = planes * self.expansion
        first_dilation = first_dilation or dilation
        use_aa = aa_layer is not None and (stride == 2 or first_dilation != dilation)

        self.conv1 = nn.Conv2d(
            inplanes, first_planes, kernel_size=3, stride=1 if use_aa else stride, padding=first_dilation,
            dilation=first_dilation, bias=False)
        self.bn1 = norm_layer(first_planes)
        self.act1 = act_layer(inplace=True)
        self.aa = aa_layer(channels=first_planes, stride=stride) if use_aa else None

        self.conv2 = nn.Conv2d(
            first_planes, outplanes, kernel_size=3, padding=dilation, dilation=dilation, bias=False)
        self.bn2 = norm_layer(outplanes)

        self.se = create_attn(attn_layer, outplanes)

        self.act2 = act_layer(inplace=True)
        self.downsample = downsample
        self.stride = stride
        self.dilation = dilation
        self.drop_block = drop_block
        self.drop_path = drop_path

    def zero_init_last_bn(self):
        nn.init.zeros_(self.bn2.weight)

    def forward(self, x):
        shortcut = x

        x = self.conv1(x)
        x = self.bn1(x)
        if self.drop_block is not None:
            x = self.drop_block(x)
        x = self.act1(x)
        if self.aa is not None:
            x = self.aa(x)

        x = self.conv2(x)
        x = self.bn2(x)
        if self.drop_block is not None:
            x = self.drop_block(x)

        if self.se is not None:
            x = self.se(x)

        if self.drop_path is not None:
            x = self.drop_path(x)

        if self.downsample is not None:
            shortcut = self.downsample(shortcut)
        x += shortcut
        x = self.act2(x)

        return x


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, cardinality=1, base_width=64,
                 reduce_first=1, dilation=1, first_dilation=None, act_layer=nn.ReLU, norm_layer=nn.BatchNorm2d,
                 attn_layer=None, aa_layer=None, drop_block=None, drop_path=None):
        super(Bottleneck, self).__init__()

        width = int(math.floor(planes * (base_width / 64)) * cardinality)
        first_planes = width // reduce_first
        outplanes = planes * self.expansion
        first_dilation = first_dilation or dilation
        use_aa = aa_layer is not None and (stride == 2 or first_dilation != dilation)

        self.conv1 = nn.Conv2d(inplanes, first_planes, kernel_size=1, bias=False)
        self.bn1 = norm_layer(first_planes)
        self.act1 = act_layer(inplace=True)

        self.conv2 = nn.Conv2d(
            first_planes, width, kernel_size=3, stride=1 if use_aa else stride,
            padding=first_dilation, dilation=first_dilation, groups=cardinality, bias=False)
        self.bn2 = norm_layer(width)
        self.act2 = act_layer(inplace=True)
        self.aa = aa_layer(channels=width, stride=stride) if use_aa else None

        self.conv3 = nn.Conv2d(width, outplanes, kernel_size=1, bias=False)
        self.bn3 = norm_layer(outplanes)

        self.se = create_attn(attn_layer, outplanes)

        self.act3 = act_layer(inplace=True)
        self.downsample = downsample
        self.stride = stride
        self.dilation = dilation
        self.drop_block = drop_block
        self.drop_path = drop_path

    def zero_init_last_bn(self):
        nn.init.zeros_(self.bn3.weight)

    def forward(self, x):
        shortcut = x

        x = self.conv1(x)
        x = self.bn1(x)
        if self.drop_block is not None:
            x = self.drop_block(x)
        x = self.act1(x)

        x = self.conv2(x)
        x = self.bn2(x)
        if self.drop_block is not None:
            x = self.drop_block(x)
        x = self.act2(x)
        if self.aa is not None:
            x = self.aa(x)

        x = self.conv3(x)
        x = self.bn3(x)
        if self.drop_block is not None:
            x = self.drop_block(x)

        if self.se is not None:
            x = self.se(x)

        if self.drop_path is not None:
            x = self.drop_path(x)

        if self.downsample is not None:
            shortcut = self.downsample(shortcut)
        x += shortcut
        x = self.act3(x)

        return x


def downsample_conv(
        in_channels, out_channels, kernel_size, stride=1, dilation=1, first_dilation=None, norm_layer=None):
    norm_layer = norm_layer or nn.BatchNorm2d
    kernel_size = 1 if stride == 1 and dilation == 1 else kernel_size
    first_dilation = (first_dilation or dilation) if kernel_size > 1 else 1
    p = get_padding(kernel_size, stride, first_dilation)

    return nn.Sequential(*[
        nn.Conv2d(
            in_channels, out_channels, kernel_size, stride=stride, padding=p, dilation=first_dilation, bias=False),
        norm_layer(out_channels)
    ])


def downsample_avg(
        in_channels, out_channels, kernel_size, stride=1, dilation=1, first_dilation=None, norm_layer=None):
    norm_layer = norm_layer or nn.BatchNorm2d
    avg_stride = stride if dilation == 1 else 1
    if stride == 1 and dilation == 1:
        pool = nn.Identity()
    else:
        avg_pool_fn = AvgPool2dSame if avg_stride == 1 and dilation > 1 else nn.AvgPool2d
        pool = avg_pool_fn(2, avg_stride, ceil_mode=True, count_include_pad=False)

    return nn.Sequential(*[
        pool,
        nn.Conv2d(in_channels, out_channels, 1, stride=1, padding=0, bias=False),
        norm_layer(out_channels)
    ])


def drop_blocks(drop_block_rate=0.):
    return [
        None, None,
        DropBlock2d(drop_block_rate, 5, 0.25) if drop_block_rate else None,
        DropBlock2d(drop_block_rate, 3, 1.00) if drop_block_rate else None]


def make_blocks(
        block_fn, channels, block_repeats, inplanes, reduce_first=1, output_stride=32,
        down_kernel_size=1, avg_down=False, drop_block_rate=0., drop_path_rate=0., **kwargs):
    stages = []
    feature_info = []
    net_num_blocks = sum(block_repeats)
    net_block_idx = 0
    net_stride = 4
    dilation = prev_dilation = 1
    for stage_idx, (planes, num_blocks, db) in enumerate(zip(channels, block_repeats, drop_blocks(drop_block_rate))):
        stage_name = f'layer{stage_idx + 1}'  # never liked this name, but weight compat requires it
        stride = 1 if stage_idx == 0 else 2
        if net_stride >= output_stride:
            dilation *= stride
            stride = 1
        else:
            net_stride *= stride

        downsample = None
        if stride != 1 or inplanes != planes * block_fn.expansion:
            down_kwargs = dict(
                in_channels=inplanes, out_channels=planes * block_fn.expansion, kernel_size=down_kernel_size,
                stride=stride, dilation=dilation, first_dilation=prev_dilation, norm_layer=kwargs.get('norm_layer'))
            downsample = downsample_avg(**down_kwargs) if avg_down else downsample_conv(**down_kwargs)

        block_kwargs = dict(reduce_first=reduce_first, dilation=dilation, drop_block=db, **kwargs)
        blocks = []
        for block_idx in range(num_blocks):
            downsample = downsample if block_idx == 0 else None
            stride = stride if block_idx == 0 else 1
            block_dpr = drop_path_rate * net_block_idx / (net_num_blocks - 1)  # stochastic depth linear decay rule
            blocks.append(block_fn(
                inplanes, planes, stride, downsample, first_dilation=prev_dilation,
                drop_path=DropPath(block_dpr) if block_dpr > 0. else None, **block_kwargs))
            prev_dilation = dilation
            inplanes = planes * block_fn.expansion
            net_block_idx += 1

        stages.append((stage_name, nn.Sequential(*blocks)))
        feature_info.append(dict(num_chs=inplanes, reduction=net_stride, module=stage_name))

    return stages, feature_info


class ResNet(nn.Module):
    """ResNet / ResNeXt / SE-ResNeXt / SE-Net

    This class implements all variants of ResNet, ResNeXt, SE-ResNeXt, and SENet that
      * have > 1 stride in the 3x3 conv layer of bottleneck
      * have conv-bn-act ordering

    This ResNet impl supports a number of stem and downsample options based on the v1c, v1d, v1e, and v1s
    variants included in the MXNet Gluon ResNetV1b model. The C and D variants are also discussed in the
    'Bag of Tricks' paper: https://arxiv.org/pdf/1812.01187. The B variant is equivalent to torchvision default.

    ResNet variants (the same modifications can be used in SE/ResNeXt models as well):
      * normal, b - 7x7 stem, stem_width = 64, same as torchvision ResNet, NVIDIA ResNet 'v1.5', Gluon v1b
      * c - 3 layer deep 3x3 stem, stem_width = 32 (32, 32, 64)
      * d - 3 layer deep 3x3 stem, stem_width = 32 (32, 32, 64), average pool in downsample
      * e - 3 layer deep 3x3 stem, stem_width = 64 (64, 64, 128), average pool in downsample
      * s - 3 layer deep 3x3 stem, stem_width = 64 (64, 64, 128)
      * t - 3 layer deep 3x3 stem, stem width = 32 (24, 48, 64), average pool in downsample
      * tn - 3 layer deep 3x3 stem, stem width = 32 (24, 32, 64), average pool in downsample

    ResNeXt
      * normal - 7x7 stem, stem_width = 64, standard cardinality and base widths
      * same c,d, e, s variants as ResNet can be enabled

    SE-ResNeXt
      * normal - 7x7 stem, stem_width = 64
      * same c, d, e, s variants as ResNet can be enabled

    SENet-154 - 3 layer deep 3x3 stem (same as v1c-v1s), stem_width = 64, cardinality=64,
        reduction by 2 on width of first bottleneck convolution, 3x3 downsample convs after first block

    Parameters
    ----------
    block : Block
        Class for the residual block. Options are BasicBlockGl, BottleneckGl.
    layers : list of int
        Numbers of layers in each block
    num_classes : int, default 1000
        Number of classification classes.
    in_chans : int, default 3
        Number of input (color) channels.
    cardinality : int, default 1
        Number of convolution groups for 3x3 conv in Bottleneck.
    base_width : int, default 64
        Factor determining bottleneck channels. `planes * base_width / 64 * cardinality`
    stem_width : int, default 64
        Number of channels in stem convolutions
    stem_type : str, default ''
        The type of stem:
          * '', default - a single 7x7 conv with a width of stem_width
          * 'deep' - three 3x3 convolution layers of widths stem_width, stem_width, stem_width * 2
          * 'deep_tiered' - three 3x3 conv layers of widths stem_width//4 * 3, stem_width, stem_width * 2
    block_reduce_first: int, default 1
        Reduction factor for first convolution output width of residual blocks,
        1 for all archs except senets, where 2
    down_kernel_size: int, default 1
        Kernel size of residual block downsampling path, 1x1 for most archs, 3x3 for senets
    avg_down : bool, default False
        Whether to use average pooling for projection skip connection between stages/downsample.
    output_stride : int, default 32
        Set the output stride of the network, 32, 16, or 8. Typically used in segmentation.
    act_layer : nn.Module, activation layer
    norm_layer : nn.Module, normalization layer
    aa_layer : nn.Module, anti-aliasing layer
    drop_rate : float, default 0.
        Dropout probability before classifier, for training
    global_pool : str, default 'avg'
        Global pooling type. One of 'avg', 'max', 'avgmax', 'catavgmax'
    """

    def __init__(self, block, layers, num_classes=1000, in_chans=3,
                 cardinality=1, base_width=64, stem_width=64, stem_type='', replace_stem_pool=False,
                 output_stride=32, block_reduce_first=1, down_kernel_size=1, avg_down=False,
                 act_layer=nn.ReLU, norm_layer=nn.BatchNorm2d, aa_layer=None, drop_rate=0.0, drop_path_rate=0.,
                 drop_block_rate=0., global_pool='avg', zero_init_last_bn=True, block_args=None):
        block_args = block_args or dict()
        assert output_stride in (8, 16, 32)
        self.num_classes = num_classes
        self.drop_rate = drop_rate
        super(ResNet, self).__init__()

        # Stem
        deep_stem = 'deep' in stem_type
        inplanes = stem_width * 2 if deep_stem else 64
        if deep_stem:
            stem_chs = (stem_width, stem_width)
            if 'tiered' in stem_type:
                stem_chs = (3 * (stem_width // 4), stem_width)
            self.conv1 = nn.Sequential(*[
                nn.Conv2d(in_chans, stem_chs[0], 3, stride=2, padding=1, bias=False),
                norm_layer(stem_chs[0]),
                act_layer(inplace=True),
                nn.Conv2d(stem_chs[0], stem_chs[1], 3, stride=1, padding=1, bias=False),
                norm_layer(stem_chs[1]),
                act_layer(inplace=True),
                nn.Conv2d(stem_chs[1], inplanes, 3, stride=1, padding=1, bias=False)])
        else:
            self.conv1 = nn.Conv2d(in_chans, inplanes, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = norm_layer(inplanes)
        self.act1 = act_layer(inplace=True)
        self.feature_info = [dict(num_chs=inplanes, reduction=2, module='act1')]

        # Stem Pooling
        if replace_stem_pool:
            self.maxpool = nn.Sequential(*filter(None, [
                nn.Conv2d(inplanes, inplanes, 3, stride=1 if aa_layer else 2, padding=1, bias=False),
                aa_layer(channels=inplanes, stride=2) if aa_layer else None,
                norm_layer(inplanes),
                act_layer(inplace=True)
            ]))
        else:
            if aa_layer is not None:
                self.maxpool = nn.Sequential(*[
                    nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
                    aa_layer(channels=inplanes, stride=2)])
            else:
                self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        # Feature Blocks
        channels = [64, 128, 256, 512]
        stage_modules, stage_feature_info = make_blocks(
            block, channels, layers, inplanes, cardinality=cardinality, base_width=base_width,
            output_stride=output_stride, reduce_first=block_reduce_first, avg_down=avg_down,
            down_kernel_size=down_kernel_size, act_layer=act_layer, norm_layer=norm_layer, aa_layer=aa_layer,
            drop_block_rate=drop_block_rate, drop_path_rate=drop_path_rate, **block_args)
        for stage in stage_modules:
            self.add_module(*stage)  # layer1, layer2, etc
        self.feature_info.extend(stage_feature_info)

        # Head (Pooling and Classifier)
        self.num_features = 512 * block.expansion
        self.global_pool, self.fc = create_classifier(self.num_features, self.num_classes, pool_type=global_pool)

        self.init_weights(zero_init_last_bn=zero_init_last_bn)

    def init_weights(self, zero_init_last_bn=True):
        for n, m in self.named_modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.ones_(m.weight)
                nn.init.zeros_(m.bias)
        if zero_init_last_bn:
            for m in self.modules():
                if hasattr(m, 'zero_init_last_bn'):
                    m.zero_init_last_bn()

    def get_classifier(self):
        return self.fc

    def reset_classifier(self, num_classes, global_pool='avg'):
        self.num_classes = num_classes
        self.global_pool, self.fc = create_classifier(self.num_features, self.num_classes, pool_type=global_pool)

    def forward_features(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.act1(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        return x

    def forward(self, x):
        x = self.forward_features(x)
        x = self.global_pool(x)
        if self.drop_rate:
            x = F.dropout(x, p=float(self.drop_rate), training=self.training)
        x = self.fc(x)
        return x


def _create_resnet(variant, pretrained=False, **kwargs):
    return build_model_with_cfg(
        ResNet, variant, pretrained,
        default_cfg=default_cfgs[variant],
        **kwargs)


@register_model
def resnet18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model.
    """
    model_args = dict(block=BasicBlock, layers=[2, 2, 2, 2], **kwargs)
    return _create_resnet('resnet18', pretrained, **model_args)


@register_model
def resnet18d(pretrained=False, **kwargs):
    """Constructs a ResNet-18-D model.
    """
    model_args = dict(
        block=BasicBlock, layers=[2, 2, 2, 2], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet18d', pretrained, **model_args)


@register_model
def resnet34(pretrained=False, **kwargs):
    """Constructs a ResNet-34 model.
    """
    model_args = dict(block=BasicBlock, layers=[3, 4, 6, 3], **kwargs)
    return _create_resnet('resnet34', pretrained, **model_args)


@register_model
def resnet34d(pretrained=False, **kwargs):
    """Constructs a ResNet-34-D model.
    """
    model_args = dict(
        block=BasicBlock, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet34d', pretrained, **model_args)


@register_model
def resnet26(pretrained=False, **kwargs):
    """Constructs a ResNet-26 model.
    """
    model_args = dict(block=Bottleneck, layers=[2, 2, 2, 2], **kwargs)
    return _create_resnet('resnet26', pretrained, **model_args)


@register_model
def resnet26t(pretrained=False, **kwargs):
    """Constructs a ResNet-26-T model.
    """
    model_args = dict(
        block=Bottleneck, layers=[2, 2, 2, 2], stem_width=32, stem_type='deep_tiered', avg_down=True, **kwargs)
    return _create_resnet('resnet26t', pretrained, **model_args)


@register_model
def resnet26d(pretrained=False, **kwargs):
    """Constructs a ResNet-26-D model.
    """
    model_args = dict(block=Bottleneck, layers=[2, 2, 2, 2], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet26d', pretrained, **model_args)


@register_model
def resnet50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3],  **kwargs)
    return _create_resnet('resnet50', pretrained, **model_args)


@register_model
def resnet50d(pretrained=False, **kwargs):
    """Constructs a ResNet-50-D model.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet50d', pretrained, **model_args)


@register_model
def resnet50t(pretrained=False, **kwargs):
    """Constructs a ResNet-50-T model.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep_tiered', avg_down=True, **kwargs)
    return _create_resnet('resnet50t', pretrained, **model_args)


@register_model
def resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], **kwargs)
    return _create_resnet('resnet101', pretrained, **model_args)


@register_model
def resnet101d(pretrained=False, **kwargs):
    """Constructs a ResNet-101-D model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet101d', pretrained, **model_args)


@register_model
def resnet152(pretrained=False, **kwargs):
    """Constructs a ResNet-152 model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 8, 36, 3], **kwargs)
    return _create_resnet('resnet152', pretrained, **model_args)


@register_model
def resnet152d(pretrained=False, **kwargs):
    """Constructs a ResNet-152-D model.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 8, 36, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet152d', pretrained, **model_args)


@register_model
def resnet200(pretrained=False, **kwargs):
    """Constructs a ResNet-200 model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 24, 36, 3], **kwargs)
    return _create_resnet('resnet200', pretrained, **model_args)


@register_model
def resnet200d(pretrained=False, **kwargs):
    """Constructs a ResNet-200-D model.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 24, 36, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnet200d', pretrained, **model_args)


@register_model
def tv_resnet34(pretrained=False, **kwargs):
    """Constructs a ResNet-34 model with original Torchvision weights.
    """
    model_args = dict(block=BasicBlock, layers=[3, 4, 6, 3], **kwargs)
    return _create_resnet('tv_resnet34', pretrained, **model_args)


@register_model
def tv_resnet50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model with original Torchvision weights.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3],  **kwargs)
    return _create_resnet('tv_resnet50', pretrained, **model_args)


@register_model
def tv_resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model w/ Torchvision pretrained weights.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], **kwargs)
    return _create_resnet('tv_resnet101', pretrained, **model_args)


@register_model
def tv_resnet152(pretrained=False, **kwargs):
    """Constructs a ResNet-152 model w/ Torchvision pretrained weights.
    """
    model_args = dict(block=Bottleneck, layers=[3, 8, 36, 3], **kwargs)
    return _create_resnet('tv_resnet152', pretrained, **model_args)


@register_model
def wide_resnet50_2(pretrained=False, **kwargs):
    """Constructs a Wide ResNet-50-2 model.
    The model is the same as ResNet except for the bottleneck number of channels
    which is twice larger in every block. The number of channels in outer 1x1
    convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
    channels, and in Wide ResNet-50-2 has 2048-1024-2048.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], base_width=128, **kwargs)
    return _create_resnet('wide_resnet50_2', pretrained, **model_args)


@register_model
def wide_resnet101_2(pretrained=False, **kwargs):
    """Constructs a Wide ResNet-101-2 model.
    The model is the same as ResNet except for the bottleneck number of channels
    which is twice larger in every block. The number of channels in outer 1x1
    convolutions is the same.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], base_width=128, **kwargs)
    return _create_resnet('wide_resnet101_2', pretrained, **model_args)


@register_model
def resnext50_32x4d(pretrained=False, **kwargs):
    """Constructs a ResNeXt50-32x4d model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('resnext50_32x4d', pretrained, **model_args)


@register_model
def resnext50d_32x4d(pretrained=False, **kwargs):
    """Constructs a ResNeXt50d-32x4d model. ResNext50 w/ deep stem & avg pool downsample
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3],  cardinality=32, base_width=4,
        stem_width=32, stem_type='deep', avg_down=True, **kwargs)
    return _create_resnet('resnext50d_32x4d', pretrained, **model_args)


@register_model
def resnext101_32x4d(pretrained=False, **kwargs):
    """Constructs a ResNeXt-101 32x4d model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('resnext101_32x4d', pretrained, **model_args)


@register_model
def resnext101_32x8d(pretrained=False, **kwargs):
    """Constructs a ResNeXt-101 32x8d model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=8, **kwargs)
    return _create_resnet('resnext101_32x8d', pretrained, **model_args)


@register_model
def resnext101_64x4d(pretrained=False, **kwargs):
    """Constructs a ResNeXt101-64x4d model.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=64, base_width=4, **kwargs)
    return _create_resnet('resnext101_64x4d', pretrained, **model_args)


@register_model
def tv_resnext50_32x4d(pretrained=False, **kwargs):
    """Constructs a ResNeXt50-32x4d model with original Torchvision weights.
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('tv_resnext50_32x4d', pretrained, **model_args)


@register_model
def ig_resnext101_32x8d(pretrained=True, **kwargs):
    """Constructs a ResNeXt-101 32x8 model pre-trained on weakly-supervised data
    and finetuned on ImageNet from Figure 5 in
    `"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
    Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=8, **kwargs)
    return _create_resnet('ig_resnext101_32x8d', pretrained, **model_args)


@register_model
def ig_resnext101_32x16d(pretrained=True, **kwargs):
    """Constructs a ResNeXt-101 32x16 model pre-trained on weakly-supervised data
    and finetuned on ImageNet from Figure 5 in
    `"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
    Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=16, **kwargs)
    return _create_resnet('ig_resnext101_32x16d', pretrained, **model_args)


@register_model
def ig_resnext101_32x32d(pretrained=True, **kwargs):
    """Constructs a ResNeXt-101 32x32 model pre-trained on weakly-supervised data
    and finetuned on ImageNet from Figure 5 in
    `"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
    Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=32, **kwargs)
    return _create_resnet('ig_resnext101_32x32d', pretrained, **model_args)


@register_model
def ig_resnext101_32x48d(pretrained=True, **kwargs):
    """Constructs a ResNeXt-101 32x48 model pre-trained on weakly-supervised data
    and finetuned on ImageNet from Figure 5 in
    `"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
    Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=48, **kwargs)
    return _create_resnet('ig_resnext101_32x48d', pretrained, **model_args)


@register_model
def ssl_resnet18(pretrained=True, **kwargs):
    """Constructs a semi-supervised ResNet-18 model pre-trained on YFCC100M dataset and finetuned on ImageNet
    `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
    Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=BasicBlock, layers=[2, 2, 2, 2], **kwargs)
    return _create_resnet('ssl_resnet18', pretrained, **model_args)


@register_model
def ssl_resnet50(pretrained=True, **kwargs):
    """Constructs a semi-supervised ResNet-50 model pre-trained on YFCC100M dataset and finetuned on ImageNet
    `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
    Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3],  **kwargs)
    return _create_resnet('ssl_resnet50', pretrained, **model_args)


@register_model
def ssl_resnext50_32x4d(pretrained=True, **kwargs):
    """Constructs a semi-supervised ResNeXt-50 32x4 model pre-trained on YFCC100M dataset and finetuned on ImageNet
    `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
    Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('ssl_resnext50_32x4d', pretrained, **model_args)


@register_model
def ssl_resnext101_32x4d(pretrained=True, **kwargs):
    """Constructs a semi-supervised ResNeXt-101 32x4 model pre-trained on YFCC100M dataset and finetuned on ImageNet
    `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
    Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('ssl_resnext101_32x4d', pretrained, **model_args)


@register_model
def ssl_resnext101_32x8d(pretrained=True, **kwargs):
    """Constructs a semi-supervised ResNeXt-101 32x8 model pre-trained on YFCC100M dataset and finetuned on ImageNet
    `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
    Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=8, **kwargs)
    return _create_resnet('ssl_resnext101_32x8d', pretrained, **model_args)


@register_model
def ssl_resnext101_32x16d(pretrained=True, **kwargs):
    """Constructs a semi-supervised ResNeXt-101 32x16 model pre-trained on YFCC100M dataset and finetuned on ImageNet
    `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
    Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=16, **kwargs)
    return _create_resnet('ssl_resnext101_32x16d', pretrained, **model_args)


@register_model
def swsl_resnet18(pretrained=True, **kwargs):
    """Constructs a semi-weakly supervised Resnet-18 model pre-trained on 1B weakly supervised
       image dataset and finetuned on ImageNet.
       `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
       Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=BasicBlock, layers=[2, 2, 2, 2], **kwargs)
    return _create_resnet('swsl_resnet18', pretrained, **model_args)


@register_model
def swsl_resnet50(pretrained=True, **kwargs):
    """Constructs a semi-weakly supervised ResNet-50 model pre-trained on 1B weakly supervised
       image dataset and finetuned on ImageNet.
       `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
       Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3],  **kwargs)
    return _create_resnet('swsl_resnet50', pretrained, **model_args)


@register_model
def swsl_resnext50_32x4d(pretrained=True, **kwargs):
    """Constructs a semi-weakly supervised ResNeXt-50 32x4 model pre-trained on 1B weakly supervised
       image dataset and finetuned on ImageNet.
       `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
       Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('swsl_resnext50_32x4d', pretrained, **model_args)


@register_model
def swsl_resnext101_32x4d(pretrained=True, **kwargs):
    """Constructs a semi-weakly supervised ResNeXt-101 32x4 model pre-trained on 1B weakly supervised
       image dataset and finetuned on ImageNet.
       `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
       Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=4, **kwargs)
    return _create_resnet('swsl_resnext101_32x4d', pretrained, **model_args)


@register_model
def swsl_resnext101_32x8d(pretrained=True, **kwargs):
    """Constructs a semi-weakly supervised ResNeXt-101 32x8 model pre-trained on 1B weakly supervised
       image dataset and finetuned on ImageNet.
       `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
       Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=8, **kwargs)
    return _create_resnet('swsl_resnext101_32x8d', pretrained, **model_args)


@register_model
def swsl_resnext101_32x16d(pretrained=True, **kwargs):
    """Constructs a semi-weakly supervised ResNeXt-101 32x16 model pre-trained on 1B weakly supervised
       image dataset and finetuned on ImageNet.
       `"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
       Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=16, **kwargs)
    return _create_resnet('swsl_resnext101_32x16d', pretrained, **model_args)


@register_model
def ecaresnet26t(pretrained=False, **kwargs):
    """Constructs an ECA-ResNeXt-26-T model.
    This is technically a 28 layer ResNet, like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels
    in the deep stem and ECA attn.
    """
    model_args = dict(
        block=Bottleneck, layers=[2, 2, 2, 2], stem_width=32,
        stem_type='deep_tiered', avg_down=True, block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet26t', pretrained, **model_args)


@register_model
def ecaresnet50d(pretrained=False, **kwargs):
    """Constructs a ResNet-50-D model with eca.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet50d', pretrained, **model_args)


@register_model
def resnetrs50(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-50 model.
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs50', pretrained, **model_args)


@register_model
def resnetrs101(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-101 model.
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 23, 3], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs101', pretrained, **model_args)


@register_model
def resnetrs152(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-152 model.
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[3, 8, 36, 3], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs152', pretrained, **model_args)


@register_model
def resnetrs200(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-200 model.
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[3, 24, 36, 3], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs200', pretrained, **model_args)


@register_model
def resnetrs270(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-270 model.
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[4, 29, 53, 4], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs270', pretrained, **model_args)



@register_model
def resnetrs350(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-350 model.
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[4, 36, 72, 4], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs350', pretrained, **model_args)


@register_model
def resnetrs420(pretrained=False, **kwargs):
    """Constructs a ResNet-RS-420 model
    Paper: Revisiting ResNets - https://arxiv.org/abs/2103.07579
    Pretrained weights from https://github.com/tensorflow/tpu/tree/bee9c4f6/models/official/resnet/resnet_rs
    """
    attn_layer = partial(get_attn('se'), rd_ratio=0.25)
    model_args = dict(
        block=Bottleneck, layers=[4, 44, 87, 4], stem_width=32, stem_type='deep', replace_stem_pool=True,
        avg_down=True,  block_args=dict(attn_layer=attn_layer), **kwargs)
    return _create_resnet('resnetrs420', pretrained, **model_args)


@register_model
def ecaresnet50d_pruned(pretrained=False, **kwargs):
    """Constructs a ResNet-50-D model pruned with eca.
        The pruning has been obtained using https://arxiv.org/pdf/2002.08258.pdf
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet50d_pruned', pretrained, pruned=True, **model_args)


@register_model
def ecaresnet50t(pretrained=False, **kwargs):
    """Constructs an ECA-ResNet-50-T model.
    Like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels in the deep stem and ECA attn.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32,
        stem_type='deep_tiered', avg_down=True, block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet50t', pretrained, **model_args)


@register_model
def ecaresnetlight(pretrained=False, **kwargs):
    """Constructs a ResNet-50-D light model with eca.
    """
    model_args = dict(
        block=Bottleneck, layers=[1, 1, 11, 3], stem_width=32, avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnetlight', pretrained, **model_args)


@register_model
def ecaresnet101d(pretrained=False, **kwargs):
    """Constructs a ResNet-101-D model with eca.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 23, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet101d', pretrained, **model_args)


@register_model
def ecaresnet101d_pruned(pretrained=False, **kwargs):
    """Constructs a ResNet-101-D model pruned with eca.
       The pruning has been obtained using https://arxiv.org/pdf/2002.08258.pdf
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 23, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet101d_pruned', pretrained, pruned=True, **model_args)


@register_model
def ecaresnet200d(pretrained=False, **kwargs):
    """Constructs a ResNet-200-D model with ECA.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 24, 36, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet200d', pretrained, **model_args)


@register_model
def ecaresnet269d(pretrained=False, **kwargs):
    """Constructs a ResNet-269-D model with ECA.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 30, 48, 8], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnet269d', pretrained, **model_args)


@register_model
def ecaresnext26t_32x4d(pretrained=False, **kwargs):
    """Constructs an ECA-ResNeXt-26-T model.
    This is technically a 28 layer ResNet, like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels
    in the deep stem. This model replaces SE module with the ECA module
    """
    model_args = dict(
        block=Bottleneck, layers=[2, 2, 2, 2], cardinality=32, base_width=4, stem_width=32,
        stem_type='deep_tiered', avg_down=True, block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnext26t_32x4d', pretrained, **model_args)


@register_model
def ecaresnext50t_32x4d(pretrained=False, **kwargs):
    """Constructs an ECA-ResNeXt-50-T model.
    This is technically a 28 layer ResNet, like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels
    in the deep stem. This model replaces SE module with the ECA module
    """
    model_args = dict(
        block=Bottleneck, layers=[2, 2, 2, 2], cardinality=32, base_width=4, stem_width=32,
        stem_type='deep_tiered', avg_down=True, block_args=dict(attn_layer='eca'), **kwargs)
    return _create_resnet('ecaresnext50t_32x4d', pretrained, **model_args)


@register_model
def resnetblur18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model with blur anti-aliasing
    """
    model_args = dict(block=BasicBlock, layers=[2, 2, 2, 2], aa_layer=BlurPool2d, **kwargs)
    return _create_resnet('resnetblur18', pretrained, **model_args)


@register_model
def resnetblur50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model with blur anti-aliasing
    """
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], aa_layer=BlurPool2d, **kwargs)
    return _create_resnet('resnetblur50', pretrained, **model_args)


@register_model
def seresnet18(pretrained=False, **kwargs):
    model_args = dict(block=BasicBlock, layers=[2, 2, 2, 2], block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet18', pretrained, **model_args)


@register_model
def seresnet34(pretrained=False, **kwargs):
    model_args = dict(block=BasicBlock, layers=[3, 4, 6, 3], block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet34', pretrained, **model_args)


@register_model
def seresnet50(pretrained=False, **kwargs):
    model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet50', pretrained, **model_args)


@register_model
def seresnet50t(pretrained=False, **kwargs):
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3],  stem_width=32, stem_type='deep_tiered', avg_down=True,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet50t', pretrained, **model_args)


@register_model
def seresnet101(pretrained=False, **kwargs):
    model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet101', pretrained, **model_args)


@register_model
def seresnet152(pretrained=False, **kwargs):
    model_args = dict(block=Bottleneck, layers=[3, 8, 36, 3], block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet152', pretrained, **model_args)


@register_model
def seresnet152d(pretrained=False, **kwargs):
    model_args = dict(
        block=Bottleneck, layers=[3, 8, 36, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet152d', pretrained, **model_args)


@register_model
def seresnet200d(pretrained=False, **kwargs):
    """Constructs a ResNet-200-D model with SE attn.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 24, 36, 3], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet200d', pretrained, **model_args)


@register_model
def seresnet269d(pretrained=False, **kwargs):
    """Constructs a ResNet-269-D model with SE attn.
    """
    model_args = dict(
        block=Bottleneck, layers=[3, 30, 48, 8], stem_width=32, stem_type='deep', avg_down=True,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnet269d', pretrained, **model_args)


@register_model
def seresnext26d_32x4d(pretrained=False, **kwargs):
    """Constructs a SE-ResNeXt-26-D model.`
    This is technically a 28 layer ResNet, using the 'D' modifier from Gluon / bag-of-tricks for
    combination of deep stem and avg_pool in downsample.
    """
    model_args = dict(
        block=Bottleneck, layers=[2, 2, 2, 2], cardinality=32, base_width=4, stem_width=32,
        stem_type='deep', avg_down=True, block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnext26d_32x4d', pretrained, **model_args)


@register_model
def seresnext26t_32x4d(pretrained=False, **kwargs):
    """Constructs a SE-ResNet-26-T model.
    This is technically a 28 layer ResNet, like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels
    in the deep stem.
    """
    model_args = dict(
        block=Bottleneck, layers=[2, 2, 2, 2], cardinality=32, base_width=4, stem_width=32,
        stem_type='deep_tiered', avg_down=True, block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnext26t_32x4d', pretrained, **model_args)


@register_model
def seresnext26tn_32x4d(pretrained=False, **kwargs):
    """Constructs a SE-ResNeXt-26-T model.
    NOTE I deprecated previous 't' model defs and replaced 't' with 'tn', this was the only tn model of note
    so keeping this def for backwards compat with any uses out there. Old 't' model is lost.
    """
    return seresnext26t_32x4d(pretrained=pretrained, **kwargs)


@register_model
def seresnext50_32x4d(pretrained=False, **kwargs):
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnext50_32x4d', pretrained, **model_args)


@register_model
def seresnext101_32x4d(pretrained=False, **kwargs):
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=4,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnext101_32x4d', pretrained, **model_args)


@register_model
def seresnext101_32x8d(pretrained=False, **kwargs):
    model_args = dict(
        block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=8,
        block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('seresnext101_32x8d', pretrained, **model_args)


@register_model
def senet154(pretrained=False, **kwargs):
    model_args = dict(
        block=Bottleneck, layers=[3, 8, 36, 3], cardinality=64, base_width=4, stem_type='deep',
        down_kernel_size=3, block_reduce_first=2, block_args=dict(attn_layer='se'), **kwargs)
    return _create_resnet('senet154', pretrained, **model_args)