File size: 44,849 Bytes
1d409a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# pylint: skip-file
# HAT from https://github.com/XPixelGroup/HAT/blob/main/hat/archs/hat_arch.py
import math
import re

import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange

from .timm.helpers import to_2tuple
from .timm.weight_init import trunc_normal_


def drop_path(x, drop_prob: float = 0.0, training: bool = False):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
    From: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/drop.py
    """
    if drop_prob == 0.0 or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (
        x.ndim - 1
    )  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output


class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    From: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/drop.py
    """

    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training)  # type: ignore


class ChannelAttention(nn.Module):
    """Channel attention used in RCAN.
    Args:
        num_feat (int): Channel number of intermediate features.
        squeeze_factor (int): Channel squeeze factor. Default: 16.
    """

    def __init__(self, num_feat, squeeze_factor=16):
        super(ChannelAttention, self).__init__()
        self.attention = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(num_feat, num_feat // squeeze_factor, 1, padding=0),
            nn.ReLU(inplace=True),
            nn.Conv2d(num_feat // squeeze_factor, num_feat, 1, padding=0),
            nn.Sigmoid(),
        )

    def forward(self, x):
        y = self.attention(x)
        return x * y


class CAB(nn.Module):
    def __init__(self, num_feat, compress_ratio=3, squeeze_factor=30):
        super(CAB, self).__init__()

        self.cab = nn.Sequential(
            nn.Conv2d(num_feat, num_feat // compress_ratio, 3, 1, 1),
            nn.GELU(),
            nn.Conv2d(num_feat // compress_ratio, num_feat, 3, 1, 1),
            ChannelAttention(num_feat, squeeze_factor),
        )

    def forward(self, x):
        return self.cab(x)


class Mlp(nn.Module):
    def __init__(
        self,
        in_features,
        hidden_features=None,
        out_features=None,
        act_layer=nn.GELU,
        drop=0.0,
    ):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x


def window_partition(x, window_size):
    """
    Args:
        x: (b, h, w, c)
        window_size (int): window size
    Returns:
        windows: (num_windows*b, window_size, window_size, c)
    """
    b, h, w, c = x.shape
    x = x.view(b, h // window_size, window_size, w // window_size, window_size, c)
    windows = (
        x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, c)
    )
    return windows


def window_reverse(windows, window_size, h, w):
    """
    Args:
        windows: (num_windows*b, window_size, window_size, c)
        window_size (int): Window size
        h (int): Height of image
        w (int): Width of image
    Returns:
        x: (b, h, w, c)
    """
    b = int(windows.shape[0] / (h * w / window_size / window_size))
    x = windows.view(
        b, h // window_size, w // window_size, window_size, window_size, -1
    )
    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(b, h, w, -1)
    return x


class WindowAttention(nn.Module):
    r"""Window based multi-head self attention (W-MSA) module with relative position bias.
    It supports both of shifted and non-shifted window.
    Args:
        dim (int): Number of input channels.
        window_size (tuple[int]): The height and width of the window.
        num_heads (int): Number of attention heads.
        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
        attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
        proj_drop (float, optional): Dropout ratio of output. Default: 0.0
    """

    def __init__(
        self,
        dim,
        window_size,
        num_heads,
        qkv_bias=True,
        qk_scale=None,
        attn_drop=0.0,
        proj_drop=0.0,
    ):
        super().__init__()
        self.dim = dim
        self.window_size = window_size  # Wh, Ww
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim**-0.5

        # define a parameter table of relative position bias
        self.relative_position_bias_table = nn.Parameter(  # type: ignore
            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)
        )  # 2*Wh-1 * 2*Ww-1, nH

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)

        self.proj_drop = nn.Dropout(proj_drop)

        trunc_normal_(self.relative_position_bias_table, std=0.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, rpi, mask=None):
        """
        Args:
            x: input features with shape of (num_windows*b, n, c)
            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
        """
        b_, n, c = x.shape
        qkv = (
            self.qkv(x)
            .reshape(b_, n, 3, self.num_heads, c // self.num_heads)
            .permute(2, 0, 3, 1, 4)
        )
        q, k, v = (
            qkv[0],
            qkv[1],
            qkv[2],
        )  # make torchscript happy (cannot use tensor as tuple)

        q = q * self.scale
        attn = q @ k.transpose(-2, -1)

        relative_position_bias = self.relative_position_bias_table[rpi.view(-1)].view(
            self.window_size[0] * self.window_size[1],
            self.window_size[0] * self.window_size[1],
            -1,
        )  # Wh*Ww,Wh*Ww,nH
        relative_position_bias = relative_position_bias.permute(
            2, 0, 1
        ).contiguous()  # nH, Wh*Ww, Wh*Ww
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            nw = mask.shape[0]
            attn = attn.view(b_ // nw, nw, self.num_heads, n, n) + mask.unsqueeze(
                1
            ).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, n, n)
            attn = self.softmax(attn)
        else:
            attn = self.softmax(attn)

        attn = self.attn_drop(attn)

        x = (attn @ v).transpose(1, 2).reshape(b_, n, c)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


class HAB(nn.Module):
    r"""Hybrid Attention Block.
    Args:
        dim (int): Number of input channels.
        input_resolution (tuple[int]): Input resolution.
        num_heads (int): Number of attention heads.
        window_size (int): Window size.
        shift_size (int): Shift size for SW-MSA.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float, optional): Stochastic depth rate. Default: 0.0
        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(
        self,
        dim,
        input_resolution,
        num_heads,
        window_size=7,
        shift_size=0,
        compress_ratio=3,
        squeeze_factor=30,
        conv_scale=0.01,
        mlp_ratio=4.0,
        qkv_bias=True,
        qk_scale=None,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        act_layer=nn.GELU,
        norm_layer=nn.LayerNorm,
    ):
        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio
        if min(self.input_resolution) <= self.window_size:
            # if window size is larger than input resolution, we don't partition windows
            self.shift_size = 0
            self.window_size = min(self.input_resolution)
        assert (
            0 <= self.shift_size < self.window_size
        ), "shift_size must in 0-window_size"

        self.norm1 = norm_layer(dim)
        self.attn = WindowAttention(
            dim,
            window_size=to_2tuple(self.window_size),
            num_heads=num_heads,
            qkv_bias=qkv_bias,
            qk_scale=qk_scale,
            attn_drop=attn_drop,
            proj_drop=drop,
        )

        self.conv_scale = conv_scale
        self.conv_block = CAB(
            num_feat=dim, compress_ratio=compress_ratio, squeeze_factor=squeeze_factor
        )

        self.drop_path = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(
            in_features=dim,
            hidden_features=mlp_hidden_dim,
            act_layer=act_layer,
            drop=drop,
        )

    def forward(self, x, x_size, rpi_sa, attn_mask):
        h, w = x_size
        b, _, c = x.shape
        # assert seq_len == h * w, "input feature has wrong size"

        shortcut = x
        x = self.norm1(x)
        x = x.view(b, h, w, c)

        # Conv_X
        conv_x = self.conv_block(x.permute(0, 3, 1, 2))
        conv_x = conv_x.permute(0, 2, 3, 1).contiguous().view(b, h * w, c)

        # cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(
                x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2)
            )
            attn_mask = attn_mask
        else:
            shifted_x = x
            attn_mask = None

        # partition windows
        x_windows = window_partition(
            shifted_x, self.window_size
        )  # nw*b, window_size, window_size, c
        x_windows = x_windows.view(
            -1, self.window_size * self.window_size, c
        )  # nw*b, window_size*window_size, c

        # W-MSA/SW-MSA (to be compatible for testing on images whose shapes are the multiple of window size
        attn_windows = self.attn(x_windows, rpi=rpi_sa, mask=attn_mask)

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, c)
        shifted_x = window_reverse(attn_windows, self.window_size, h, w)  # b h' w' c

        # reverse cyclic shift
        if self.shift_size > 0:
            attn_x = torch.roll(
                shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2)
            )
        else:
            attn_x = shifted_x
        attn_x = attn_x.view(b, h * w, c)

        # FFN
        x = shortcut + self.drop_path(attn_x) + conv_x * self.conv_scale
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        return x


class PatchMerging(nn.Module):
    r"""Patch Merging Layer.
    Args:
        input_resolution (tuple[int]): Resolution of input feature.
        dim (int): Number of input channels.
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(self, input_resolution, dim, norm_layer=nn.LayerNorm):
        super().__init__()
        self.input_resolution = input_resolution
        self.dim = dim
        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
        self.norm = norm_layer(4 * dim)

    def forward(self, x):
        """
        x: b, h*w, c
        """
        h, w = self.input_resolution
        b, seq_len, c = x.shape
        assert seq_len == h * w, "input feature has wrong size"
        assert h % 2 == 0 and w % 2 == 0, f"x size ({h}*{w}) are not even."

        x = x.view(b, h, w, c)

        x0 = x[:, 0::2, 0::2, :]  # b h/2 w/2 c
        x1 = x[:, 1::2, 0::2, :]  # b h/2 w/2 c
        x2 = x[:, 0::2, 1::2, :]  # b h/2 w/2 c
        x3 = x[:, 1::2, 1::2, :]  # b h/2 w/2 c
        x = torch.cat([x0, x1, x2, x3], -1)  # b h/2 w/2 4*c
        x = x.view(b, -1, 4 * c)  # b h/2*w/2 4*c

        x = self.norm(x)
        x = self.reduction(x)

        return x


class OCAB(nn.Module):
    # overlapping cross-attention block

    def __init__(
        self,
        dim,
        input_resolution,
        window_size,
        overlap_ratio,
        num_heads,
        qkv_bias=True,
        qk_scale=None,
        mlp_ratio=2,
        norm_layer=nn.LayerNorm,
    ):
        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.window_size = window_size
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim**-0.5
        self.overlap_win_size = int(window_size * overlap_ratio) + window_size

        self.norm1 = norm_layer(dim)
        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.unfold = nn.Unfold(
            kernel_size=(self.overlap_win_size, self.overlap_win_size),
            stride=window_size,
            padding=(self.overlap_win_size - window_size) // 2,
        )

        # define a parameter table of relative position bias
        self.relative_position_bias_table = nn.Parameter(  # type: ignore
            torch.zeros(
                (window_size + self.overlap_win_size - 1)
                * (window_size + self.overlap_win_size - 1),
                num_heads,
            )
        )  # 2*Wh-1 * 2*Ww-1, nH

        trunc_normal_(self.relative_position_bias_table, std=0.02)
        self.softmax = nn.Softmax(dim=-1)

        self.proj = nn.Linear(dim, dim)

        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(
            in_features=dim, hidden_features=mlp_hidden_dim, act_layer=nn.GELU
        )

    def forward(self, x, x_size, rpi):
        h, w = x_size
        b, _, c = x.shape

        shortcut = x
        x = self.norm1(x)
        x = x.view(b, h, w, c)

        qkv = self.qkv(x).reshape(b, h, w, 3, c).permute(3, 0, 4, 1, 2)  # 3, b, c, h, w
        q = qkv[0].permute(0, 2, 3, 1)  # b, h, w, c
        kv = torch.cat((qkv[1], qkv[2]), dim=1)  # b, 2*c, h, w

        # partition windows
        q_windows = window_partition(
            q, self.window_size
        )  # nw*b, window_size, window_size, c
        q_windows = q_windows.view(
            -1, self.window_size * self.window_size, c
        )  # nw*b, window_size*window_size, c

        kv_windows = self.unfold(kv)  # b, c*w*w, nw
        kv_windows = rearrange(
            kv_windows,
            "b (nc ch owh oww) nw -> nc (b nw) (owh oww) ch",
            nc=2,
            ch=c,
            owh=self.overlap_win_size,
            oww=self.overlap_win_size,
        ).contiguous()  # 2, nw*b, ow*ow, c
        # Do the above rearrangement without the rearrange function
        # kv_windows = kv_windows.view(
        #     2, b, self.overlap_win_size, self.overlap_win_size, c, -1
        # )
        # kv_windows = kv_windows.permute(0, 5, 1, 2, 3, 4).contiguous()
        # kv_windows = kv_windows.view(
        #     2, -1, self.overlap_win_size * self.overlap_win_size, c
        # )

        k_windows, v_windows = kv_windows[0], kv_windows[1]  # nw*b, ow*ow, c

        b_, nq, _ = q_windows.shape
        _, n, _ = k_windows.shape
        d = self.dim // self.num_heads
        q = q_windows.reshape(b_, nq, self.num_heads, d).permute(
            0, 2, 1, 3
        )  # nw*b, nH, nq, d
        k = k_windows.reshape(b_, n, self.num_heads, d).permute(
            0, 2, 1, 3
        )  # nw*b, nH, n, d
        v = v_windows.reshape(b_, n, self.num_heads, d).permute(
            0, 2, 1, 3
        )  # nw*b, nH, n, d

        q = q * self.scale
        attn = q @ k.transpose(-2, -1)

        relative_position_bias = self.relative_position_bias_table[rpi.view(-1)].view(
            self.window_size * self.window_size,
            self.overlap_win_size * self.overlap_win_size,
            -1,
        )  # ws*ws, wse*wse, nH
        relative_position_bias = relative_position_bias.permute(
            2, 0, 1
        ).contiguous()  # nH, ws*ws, wse*wse
        attn = attn + relative_position_bias.unsqueeze(0)

        attn = self.softmax(attn)
        attn_windows = (attn @ v).transpose(1, 2).reshape(b_, nq, self.dim)

        # merge windows
        attn_windows = attn_windows.view(
            -1, self.window_size, self.window_size, self.dim
        )
        x = window_reverse(attn_windows, self.window_size, h, w)  # b h w c
        x = x.view(b, h * w, self.dim)

        x = self.proj(x) + shortcut

        x = x + self.mlp(self.norm2(x))
        return x


class AttenBlocks(nn.Module):
    """A series of attention blocks for one RHAG.
    Args:
        dim (int): Number of input channels.
        input_resolution (tuple[int]): Input resolution.
        depth (int): Number of blocks.
        num_heads (int): Number of attention heads.
        window_size (int): Local window size.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    """

    def __init__(
        self,
        dim,
        input_resolution,
        depth,
        num_heads,
        window_size,
        compress_ratio,
        squeeze_factor,
        conv_scale,
        overlap_ratio,
        mlp_ratio=4.0,
        qkv_bias=True,
        qk_scale=None,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        norm_layer=nn.LayerNorm,
        downsample=None,
        use_checkpoint=False,
    ):
        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.depth = depth
        self.use_checkpoint = use_checkpoint

        # build blocks
        self.blocks = nn.ModuleList(
            [
                HAB(
                    dim=dim,
                    input_resolution=input_resolution,
                    num_heads=num_heads,
                    window_size=window_size,
                    shift_size=0 if (i % 2 == 0) else window_size // 2,
                    compress_ratio=compress_ratio,
                    squeeze_factor=squeeze_factor,
                    conv_scale=conv_scale,
                    mlp_ratio=mlp_ratio,
                    qkv_bias=qkv_bias,
                    qk_scale=qk_scale,
                    drop=drop,
                    attn_drop=attn_drop,
                    drop_path=drop_path[i]
                    if isinstance(drop_path, list)
                    else drop_path,
                    norm_layer=norm_layer,
                )
                for i in range(depth)
            ]
        )

        # OCAB
        self.overlap_attn = OCAB(
            dim=dim,
            input_resolution=input_resolution,
            window_size=window_size,
            overlap_ratio=overlap_ratio,
            num_heads=num_heads,
            qkv_bias=qkv_bias,
            qk_scale=qk_scale,
            mlp_ratio=mlp_ratio,  # type: ignore
            norm_layer=norm_layer,
        )

        # patch merging layer
        if downsample is not None:
            self.downsample = downsample(
                input_resolution, dim=dim, norm_layer=norm_layer
            )
        else:
            self.downsample = None

    def forward(self, x, x_size, params):
        for blk in self.blocks:
            x = blk(x, x_size, params["rpi_sa"], params["attn_mask"])

        x = self.overlap_attn(x, x_size, params["rpi_oca"])

        if self.downsample is not None:
            x = self.downsample(x)
        return x


class RHAG(nn.Module):
    """Residual Hybrid Attention Group (RHAG).
    Args:
        dim (int): Number of input channels.
        input_resolution (tuple[int]): Input resolution.
        depth (int): Number of blocks.
        num_heads (int): Number of attention heads.
        window_size (int): Local window size.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
        img_size: Input image size.
        patch_size: Patch size.
        resi_connection: The convolutional block before residual connection.
    """

    def __init__(
        self,
        dim,
        input_resolution,
        depth,
        num_heads,
        window_size,
        compress_ratio,
        squeeze_factor,
        conv_scale,
        overlap_ratio,
        mlp_ratio=4.0,
        qkv_bias=True,
        qk_scale=None,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        norm_layer=nn.LayerNorm,
        downsample=None,
        use_checkpoint=False,
        img_size=224,
        patch_size=4,
        resi_connection="1conv",
    ):
        super(RHAG, self).__init__()

        self.dim = dim
        self.input_resolution = input_resolution

        self.residual_group = AttenBlocks(
            dim=dim,
            input_resolution=input_resolution,
            depth=depth,
            num_heads=num_heads,
            window_size=window_size,
            compress_ratio=compress_ratio,
            squeeze_factor=squeeze_factor,
            conv_scale=conv_scale,
            overlap_ratio=overlap_ratio,
            mlp_ratio=mlp_ratio,
            qkv_bias=qkv_bias,
            qk_scale=qk_scale,
            drop=drop,
            attn_drop=attn_drop,
            drop_path=drop_path,
            norm_layer=norm_layer,
            downsample=downsample,
            use_checkpoint=use_checkpoint,
        )

        if resi_connection == "1conv":
            self.conv = nn.Conv2d(dim, dim, 3, 1, 1)
        elif resi_connection == "identity":
            self.conv = nn.Identity()

        self.patch_embed = PatchEmbed(
            img_size=img_size,
            patch_size=patch_size,
            in_chans=0,
            embed_dim=dim,
            norm_layer=None,
        )

        self.patch_unembed = PatchUnEmbed(
            img_size=img_size,
            patch_size=patch_size,
            in_chans=0,
            embed_dim=dim,
            norm_layer=None,
        )

    def forward(self, x, x_size, params):
        return (
            self.patch_embed(
                self.conv(
                    self.patch_unembed(self.residual_group(x, x_size, params), x_size)
                )
            )
            + x
        )


class PatchEmbed(nn.Module):
    r"""Image to Patch Embedding
    Args:
        img_size (int): Image size.  Default: 224.
        patch_size (int): Patch token size. Default: 4.
        in_chans (int): Number of input image channels. Default: 3.
        embed_dim (int): Number of linear projection output channels. Default: 96.
        norm_layer (nn.Module, optional): Normalization layer. Default: None
    """

    def __init__(
        self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None
    ):
        super().__init__()
        img_size = to_2tuple(img_size)
        patch_size = to_2tuple(patch_size)
        patches_resolution = [
            img_size[0] // patch_size[0],  # type: ignore
            img_size[1] // patch_size[1],  # type: ignore
        ]
        self.img_size = img_size
        self.patch_size = patch_size
        self.patches_resolution = patches_resolution
        self.num_patches = patches_resolution[0] * patches_resolution[1]

        self.in_chans = in_chans
        self.embed_dim = embed_dim

        if norm_layer is not None:
            self.norm = norm_layer(embed_dim)
        else:
            self.norm = None

    def forward(self, x):
        x = x.flatten(2).transpose(1, 2)  # b Ph*Pw c
        if self.norm is not None:
            x = self.norm(x)
        return x


class PatchUnEmbed(nn.Module):
    r"""Image to Patch Unembedding
    Args:
        img_size (int): Image size.  Default: 224.
        patch_size (int): Patch token size. Default: 4.
        in_chans (int): Number of input image channels. Default: 3.
        embed_dim (int): Number of linear projection output channels. Default: 96.
        norm_layer (nn.Module, optional): Normalization layer. Default: None
    """

    def __init__(
        self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None
    ):
        super().__init__()
        img_size = to_2tuple(img_size)
        patch_size = to_2tuple(patch_size)
        patches_resolution = [
            img_size[0] // patch_size[0],  # type: ignore
            img_size[1] // patch_size[1],  # type: ignore
        ]
        self.img_size = img_size
        self.patch_size = patch_size
        self.patches_resolution = patches_resolution
        self.num_patches = patches_resolution[0] * patches_resolution[1]

        self.in_chans = in_chans
        self.embed_dim = embed_dim

    def forward(self, x, x_size):
        x = (
            x.transpose(1, 2)
            .contiguous()
            .view(x.shape[0], self.embed_dim, x_size[0], x_size[1])
        )  # b Ph*Pw c
        return x


class Upsample(nn.Sequential):
    """Upsample module.
    Args:
        scale (int): Scale factor. Supported scales: 2^n and 3.
        num_feat (int): Channel number of intermediate features.
    """

    def __init__(self, scale, num_feat):
        m = []
        if (scale & (scale - 1)) == 0:  # scale = 2^n
            for _ in range(int(math.log(scale, 2))):
                m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
                m.append(nn.PixelShuffle(2))
        elif scale == 3:
            m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
            m.append(nn.PixelShuffle(3))
        else:
            raise ValueError(
                f"scale {scale} is not supported. " "Supported scales: 2^n and 3."
            )
        super(Upsample, self).__init__(*m)


class HAT(nn.Module):
    r"""Hybrid Attention Transformer
        A PyTorch implementation of : `Activating More Pixels in Image Super-Resolution Transformer`.
        Some codes are based on SwinIR.
    Args:
        img_size (int | tuple(int)): Input image size. Default 64
        patch_size (int | tuple(int)): Patch size. Default: 1
        in_chans (int): Number of input image channels. Default: 3
        embed_dim (int): Patch embedding dimension. Default: 96
        depths (tuple(int)): Depth of each Swin Transformer layer.
        num_heads (tuple(int)): Number of attention heads in different layers.
        window_size (int): Window size. Default: 7
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4
        qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float): Override default qk scale of head_dim ** -0.5 if set. Default: None
        drop_rate (float): Dropout rate. Default: 0
        attn_drop_rate (float): Attention dropout rate. Default: 0
        drop_path_rate (float): Stochastic depth rate. Default: 0.1
        norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
        ape (bool): If True, add absolute position embedding to the patch embedding. Default: False
        patch_norm (bool): If True, add normalization after patch embedding. Default: True
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False
        upscale: Upscale factor. 2/3/4/8 for image SR, 1 for denoising and compress artifact reduction
        img_range: Image range. 1. or 255.
        upsampler: The reconstruction reconstruction module. 'pixelshuffle'/'pixelshuffledirect'/'nearest+conv'/None
        resi_connection: The convolutional block before residual connection. '1conv'/'3conv'
    """

    def __init__(
        self,
        state_dict,
        **kwargs,
    ):
        super(HAT, self).__init__()

        # Defaults
        img_size = 64
        patch_size = 1
        in_chans = 3
        embed_dim = 96
        depths = (6, 6, 6, 6)
        num_heads = (6, 6, 6, 6)
        window_size = 7
        compress_ratio = 3
        squeeze_factor = 30
        conv_scale = 0.01
        overlap_ratio = 0.5
        mlp_ratio = 4.0
        qkv_bias = True
        qk_scale = None
        drop_rate = 0.0
        attn_drop_rate = 0.0
        drop_path_rate = 0.1
        norm_layer = nn.LayerNorm
        ape = False
        patch_norm = True
        use_checkpoint = False
        upscale = 2
        img_range = 1.0
        upsampler = ""
        resi_connection = "1conv"

        self.state = state_dict
        self.model_arch = "HAT"
        self.sub_type = "SR"
        self.supports_fp16 = False
        self.support_bf16 = True
        self.min_size_restriction = 16

        state_keys = list(state_dict.keys())

        num_feat = state_dict["conv_last.weight"].shape[1]
        in_chans = state_dict["conv_first.weight"].shape[1]
        num_out_ch = state_dict["conv_last.weight"].shape[0]
        embed_dim = state_dict["conv_first.weight"].shape[0]

        if "conv_before_upsample.0.weight" in state_keys:
            if "conv_up1.weight" in state_keys:
                upsampler = "nearest+conv"
            else:
                upsampler = "pixelshuffle"
                supports_fp16 = False
        elif "upsample.0.weight" in state_keys:
            upsampler = "pixelshuffledirect"
        else:
            upsampler = ""
        upscale = 1
        if upsampler == "nearest+conv":
            upsample_keys = [
                x for x in state_keys if "conv_up" in x and "bias" not in x
            ]

            for upsample_key in upsample_keys:
                upscale *= 2
        elif upsampler == "pixelshuffle":
            upsample_keys = [
                x
                for x in state_keys
                if "upsample" in x and "conv" not in x and "bias" not in x
            ]
            for upsample_key in upsample_keys:
                shape = self.state[upsample_key].shape[0]
                upscale *= math.sqrt(shape // num_feat)
            upscale = int(upscale)
        elif upsampler == "pixelshuffledirect":
            upscale = int(
                math.sqrt(self.state["upsample.0.bias"].shape[0] // num_out_ch)
            )

        max_layer_num = 0
        max_block_num = 0
        for key in state_keys:
            result = re.match(
                r"layers.(\d*).residual_group.blocks.(\d*).conv_block.cab.0.weight", key
            )
            if result:
                layer_num, block_num = result.groups()
                max_layer_num = max(max_layer_num, int(layer_num))
                max_block_num = max(max_block_num, int(block_num))

        depths = [max_block_num + 1 for _ in range(max_layer_num + 1)]

        if (
            "layers.0.residual_group.blocks.0.attn.relative_position_bias_table"
            in state_keys
        ):
            num_heads_num = self.state[
                "layers.0.residual_group.blocks.0.attn.relative_position_bias_table"
            ].shape[-1]
            num_heads = [num_heads_num for _ in range(max_layer_num + 1)]
        else:
            num_heads = depths

        mlp_ratio = float(
            self.state["layers.0.residual_group.blocks.0.mlp.fc1.bias"].shape[0]
            / embed_dim
        )

        # TODO: could actually count the layers, but this should do
        if "layers.0.conv.4.weight" in state_keys:
            resi_connection = "3conv"
        else:
            resi_connection = "1conv"

        window_size = int(math.sqrt(self.state["relative_position_index_SA"].shape[0]))

        # Not sure if this is needed or used at all anywhere in HAT's config
        if "layers.0.residual_group.blocks.1.attn_mask" in state_keys:
            img_size = int(
                math.sqrt(
                    self.state["layers.0.residual_group.blocks.1.attn_mask"].shape[0]
                )
                * window_size
            )

        self.window_size = window_size
        self.shift_size = window_size // 2
        self.overlap_ratio = overlap_ratio

        self.in_nc = in_chans
        self.out_nc = num_out_ch
        self.num_feat = num_feat
        self.embed_dim = embed_dim
        self.num_heads = num_heads
        self.depths = depths
        self.window_size = window_size
        self.mlp_ratio = mlp_ratio
        self.scale = upscale
        self.upsampler = upsampler
        self.img_size = img_size
        self.img_range = img_range
        self.resi_connection = resi_connection

        num_in_ch = in_chans
        # num_out_ch = in_chans
        # num_feat = 64
        self.img_range = img_range
        if in_chans == 3:
            rgb_mean = (0.4488, 0.4371, 0.4040)
            self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)
        else:
            self.mean = torch.zeros(1, 1, 1, 1)
        self.upscale = upscale
        self.upsampler = upsampler

        # relative position index
        relative_position_index_SA = self.calculate_rpi_sa()
        relative_position_index_OCA = self.calculate_rpi_oca()
        self.register_buffer("relative_position_index_SA", relative_position_index_SA)
        self.register_buffer("relative_position_index_OCA", relative_position_index_OCA)

        # ------------------------- 1, shallow feature extraction ------------------------- #
        self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1)

        # ------------------------- 2, deep feature extraction ------------------------- #
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.ape = ape
        self.patch_norm = patch_norm
        self.num_features = embed_dim
        self.mlp_ratio = mlp_ratio

        # split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            img_size=img_size,
            patch_size=patch_size,
            in_chans=embed_dim,
            embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None,
        )
        num_patches = self.patch_embed.num_patches
        patches_resolution = self.patch_embed.patches_resolution
        self.patches_resolution = patches_resolution

        # merge non-overlapping patches into image
        self.patch_unembed = PatchUnEmbed(
            img_size=img_size,
            patch_size=patch_size,
            in_chans=embed_dim,
            embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None,
        )

        # absolute position embedding
        if self.ape:
            self.absolute_pos_embed = nn.Parameter(  # type: ignore[arg-type]
                torch.zeros(1, num_patches, embed_dim)
            )
            trunc_normal_(self.absolute_pos_embed, std=0.02)

        self.pos_drop = nn.Dropout(p=drop_rate)

        # stochastic depth
        dpr = [
            x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))
        ]  # stochastic depth decay rule

        # build Residual Hybrid Attention Groups (RHAG)
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            layer = RHAG(
                dim=embed_dim,
                input_resolution=(patches_resolution[0], patches_resolution[1]),
                depth=depths[i_layer],
                num_heads=num_heads[i_layer],
                window_size=window_size,
                compress_ratio=compress_ratio,
                squeeze_factor=squeeze_factor,
                conv_scale=conv_scale,
                overlap_ratio=overlap_ratio,
                mlp_ratio=self.mlp_ratio,
                qkv_bias=qkv_bias,
                qk_scale=qk_scale,
                drop=drop_rate,
                attn_drop=attn_drop_rate,
                drop_path=dpr[
                    sum(depths[:i_layer]) : sum(depths[: i_layer + 1])  # type: ignore
                ],  # no impact on SR results
                norm_layer=norm_layer,
                downsample=None,
                use_checkpoint=use_checkpoint,
                img_size=img_size,
                patch_size=patch_size,
                resi_connection=resi_connection,
            )
            self.layers.append(layer)
        self.norm = norm_layer(self.num_features)

        # build the last conv layer in deep feature extraction
        if resi_connection == "1conv":
            self.conv_after_body = nn.Conv2d(embed_dim, embed_dim, 3, 1, 1)
        elif resi_connection == "identity":
            self.conv_after_body = nn.Identity()

        # ------------------------- 3, high quality image reconstruction ------------------------- #
        if self.upsampler == "pixelshuffle":
            # for classical SR
            self.conv_before_upsample = nn.Sequential(
                nn.Conv2d(embed_dim, num_feat, 3, 1, 1), nn.LeakyReLU(inplace=True)
            )
            self.upsample = Upsample(upscale, num_feat)
            self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)

        self.apply(self._init_weights)
        self.load_state_dict(self.state, strict=False)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=0.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    def calculate_rpi_sa(self):
        # calculate relative position index for SA
        coords_h = torch.arange(self.window_size)
        coords_w = torch.arange(self.window_size)
        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
        relative_coords = (
            coords_flatten[:, :, None] - coords_flatten[:, None, :]
        )  # 2, Wh*Ww, Wh*Ww
        relative_coords = relative_coords.permute(
            1, 2, 0
        ).contiguous()  # Wh*Ww, Wh*Ww, 2
        relative_coords[:, :, 0] += self.window_size - 1  # shift to start from 0
        relative_coords[:, :, 1] += self.window_size - 1
        relative_coords[:, :, 0] *= 2 * self.window_size - 1
        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
        return relative_position_index

    def calculate_rpi_oca(self):
        # calculate relative position index for OCA
        window_size_ori = self.window_size
        window_size_ext = self.window_size + int(self.overlap_ratio * self.window_size)

        coords_h = torch.arange(window_size_ori)
        coords_w = torch.arange(window_size_ori)
        coords_ori = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, ws, ws
        coords_ori_flatten = torch.flatten(coords_ori, 1)  # 2, ws*ws

        coords_h = torch.arange(window_size_ext)
        coords_w = torch.arange(window_size_ext)
        coords_ext = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, wse, wse
        coords_ext_flatten = torch.flatten(coords_ext, 1)  # 2, wse*wse

        relative_coords = (
            coords_ext_flatten[:, None, :] - coords_ori_flatten[:, :, None]
        )  # 2, ws*ws, wse*wse

        relative_coords = relative_coords.permute(
            1, 2, 0
        ).contiguous()  # ws*ws, wse*wse, 2
        relative_coords[:, :, 0] += (
            window_size_ori - window_size_ext + 1
        )  # shift to start from 0
        relative_coords[:, :, 1] += window_size_ori - window_size_ext + 1

        relative_coords[:, :, 0] *= window_size_ori + window_size_ext - 1
        relative_position_index = relative_coords.sum(-1)
        return relative_position_index

    def calculate_mask(self, x_size):
        # calculate attention mask for SW-MSA
        h, w = x_size
        img_mask = torch.zeros((1, h, w, 1))  # 1 h w 1
        h_slices = (
            slice(0, -self.window_size),
            slice(-self.window_size, -self.shift_size),
            slice(-self.shift_size, None),
        )
        w_slices = (
            slice(0, -self.window_size),
            slice(-self.window_size, -self.shift_size),
            slice(-self.shift_size, None),
        )
        cnt = 0
        for h in h_slices:
            for w in w_slices:
                img_mask[:, h, w, :] = cnt
                cnt += 1

        mask_windows = window_partition(
            img_mask, self.window_size
        )  # nw, window_size, window_size, 1
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(
            attn_mask == 0, float(0.0)
        )

        return attn_mask

    @torch.jit.ignore  # type: ignore
    def no_weight_decay(self):
        return {"absolute_pos_embed"}

    @torch.jit.ignore  # type: ignore
    def no_weight_decay_keywords(self):
        return {"relative_position_bias_table"}

    def check_image_size(self, x):
        _, _, h, w = x.size()
        mod_pad_h = (self.window_size - h % self.window_size) % self.window_size
        mod_pad_w = (self.window_size - w % self.window_size) % self.window_size
        x = F.pad(x, (0, mod_pad_w, 0, mod_pad_h), "reflect")
        return x

    def forward_features(self, x):
        x_size = (x.shape[2], x.shape[3])

        # Calculate attention mask and relative position index in advance to speed up inference.
        # The original code is very time-cosuming for large window size.
        attn_mask = self.calculate_mask(x_size).to(x.device)
        params = {
            "attn_mask": attn_mask,
            "rpi_sa": self.relative_position_index_SA,
            "rpi_oca": self.relative_position_index_OCA,
        }

        x = self.patch_embed(x)
        if self.ape:
            x = x + self.absolute_pos_embed
        x = self.pos_drop(x)

        for layer in self.layers:
            x = layer(x, x_size, params)

        x = self.norm(x)  # b seq_len c
        x = self.patch_unembed(x, x_size)

        return x

    def forward(self, x):
        H, W = x.shape[2:]
        self.mean = self.mean.type_as(x)
        x = (x - self.mean) * self.img_range
        x = self.check_image_size(x)

        if self.upsampler == "pixelshuffle":
            # for classical SR
            x = self.conv_first(x)
            x = self.conv_after_body(self.forward_features(x)) + x
            x = self.conv_before_upsample(x)
            x = self.conv_last(self.upsample(x))

        x = x / self.img_range + self.mean

        return x[:, :, : H * self.upscale, : W * self.upscale]