File size: 47,283 Bytes
5b2fcab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Common modules
"""

import ast
import contextlib
import json
import math
import platform
import warnings
import zipfile
from collections import OrderedDict, namedtuple
from copy import copy
from pathlib import Path
from urllib.parse import urlparse

import cv2
import numpy as np
import pandas as pd
import requests
import torch
import torch.nn as nn
from IPython.display import display
from PIL import Image
from torch.cuda import amp

from utils import TryExcept
from utils.dataloaders import exif_transpose, letterbox
from utils.general import (
    LOGGER,
    ROOT,
    Profile,
    check_requirements,
    check_suffix,
    check_version,
    colorstr,
    increment_path,
    is_notebook,
    make_divisible,
    non_max_suppression,
    scale_boxes,
    xywh2xyxy,
    xyxy2xywh,
    yaml_load,
)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import copy_attr, smart_inference_mode


def autopad(k, p=None, d=1):  # kernel, padding, dilation
    # Pad to 'same' shape outputs
    if d > 1:
        k = (
            d * (k - 1) + 1
            if isinstance(k, int)
            else [d * (x - 1) + 1 for x in k]
        )  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p


class Conv(nn.Module):
    # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__()
        self.conv = nn.Conv2d(
            c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False
        )
        self.bn = nn.BatchNorm2d(c2)
        self.act = (
            self.default_act
            if act is True
            else act
            if isinstance(act, nn.Module)
            else nn.Identity()
        )

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        return self.act(self.conv(x))


class DWConv(Conv):
    # Depth-wise convolution
    def __init__(
        self, c1, c2, k=1, s=1, d=1, act=True
    ):  # ch_in, ch_out, kernel, stride, dilation, activation
        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)


class DWConvTranspose2d(nn.ConvTranspose2d):
    # Depth-wise transpose convolution
    def __init__(
        self, c1, c2, k=1, s=1, p1=0, p2=0
    ):  # ch_in, ch_out, kernel, stride, padding, padding_out
        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))


class TransformerLayer(nn.Module):
    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
    def __init__(self, c, num_heads):
        super().__init__()
        self.q = nn.Linear(c, c, bias=False)
        self.k = nn.Linear(c, c, bias=False)
        self.v = nn.Linear(c, c, bias=False)
        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
        self.fc1 = nn.Linear(c, c, bias=False)
        self.fc2 = nn.Linear(c, c, bias=False)

    def forward(self, x):
        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
        x = self.fc2(self.fc1(x)) + x
        return x


class TransformerBlock(nn.Module):
    # Vision Transformer https://arxiv.org/abs/2010.11929
    def __init__(self, c1, c2, num_heads, num_layers):
        super().__init__()
        self.conv = None
        if c1 != c2:
            self.conv = Conv(c1, c2)
        self.linear = nn.Linear(c2, c2)  # learnable position embedding
        self.tr = nn.Sequential(
            *(TransformerLayer(c2, num_heads) for _ in range(num_layers))
        )
        self.c2 = c2

    def forward(self, x):
        if self.conv is not None:
            x = self.conv(x)
        b, _, w, h = x.shape
        p = x.flatten(2).permute(2, 0, 1)
        return (
            self.tr(p + self.linear(p))
            .permute(1, 2, 0)
            .reshape(b, self.c2, w, h)
        )


class Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(
        self, c1, c2, shortcut=True, g=1, e=0.5
    ):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class BottleneckCSP(nn.Module):
    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(
        self, c1, c2, n=1, shortcut=True, g=1, e=0.5
    ):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
        self.cv4 = Conv(2 * c_, c2, 1, 1)
        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
        self.act = nn.SiLU()
        self.m = nn.Sequential(
            *(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))
        )

    def forward(self, x):
        y1 = self.cv3(self.m(self.cv1(x)))
        y2 = self.cv2(x)
        return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))


class CrossConv(nn.Module):
    # Cross Convolution Downsample
    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, (1, k), (1, s))
        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class C3(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(
        self, c1, c2, n=1, shortcut=True, g=1, e=0.5
    ):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(
            *(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))
        )

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))


class C3x(C3):
    # C3 module with cross-convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)
        self.m = nn.Sequential(
            *(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n))
        )


class C3TR(C3):
    # C3 module with TransformerBlock()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)
        self.m = TransformerBlock(c_, c_, 4, n)


class C3SPP(C3):
    # C3 module with SPP()
    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)
        self.m = SPP(c_, c_, k)


class C3Ghost(C3):
    # C3 module with GhostBottleneck()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))


class SPP(nn.Module):
    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList(
            [nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]
        )

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter(
                "ignore"
            )  # suppress torch 1.9.0 max_pool2d() warning
            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))


class SPPF(nn.Module):
    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter(
                "ignore"
            )  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))


class Focus(nn.Module):
    # Focus wh information into c-space
    def __init__(
        self, c1, c2, k=1, s=1, p=None, g=1, act=True
    ):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)
        # self.contract = Contract(gain=2)

    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
        return self.conv(
            torch.cat(
                (
                    x[..., ::2, ::2],
                    x[..., 1::2, ::2],
                    x[..., ::2, 1::2],
                    x[..., 1::2, 1::2],
                ),
                1,
            )
        )
        # return self.conv(self.contract(x))


class GhostConv(nn.Module):
    # Ghost Convolution https://github.com/huawei-noah/ghostnet
    def __init__(
        self, c1, c2, k=1, s=1, g=1, act=True
    ):  # ch_in, ch_out, kernel, stride, groups
        super().__init__()
        c_ = c2 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)

    def forward(self, x):
        y = self.cv1(x)
        return torch.cat((y, self.cv2(y)), 1)


class GhostBottleneck(nn.Module):
    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
        super().__init__()
        c_ = c2 // 2
        self.conv = nn.Sequential(
            GhostConv(c1, c_, 1, 1),  # pw
            DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
            GhostConv(c_, c2, 1, 1, act=False),
        )  # pw-linear
        self.shortcut = (
            nn.Sequential(
                DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1, act=False)
            )
            if s == 2
            else nn.Identity()
        )

    def forward(self, x):
        return self.conv(x) + self.shortcut(x)


class Contract(nn.Module):
    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
    def __init__(self, gain=2):
        super().__init__()
        self.gain = gain

    def forward(self, x):
        (
            b,
            c,
            h,
            w,
        ) = (
            x.size()
        )  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
        s = self.gain
        x = x.view(b, c, h // s, s, w // s, s)  # x(1,64,40,2,40,2)
        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
        return x.view(b, c * s * s, h // s, w // s)  # x(1,256,40,40)


class Expand(nn.Module):
    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
    def __init__(self, gain=2):
        super().__init__()
        self.gain = gain

    def forward(self, x):
        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
        s = self.gain
        x = x.view(b, s, s, c // s**2, h, w)  # x(1,2,2,16,80,80)
        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
        return x.view(b, c // s**2, h * s, w * s)  # x(1,16,160,160)


class Concat(nn.Module):
    # Concatenate a list of tensors along dimension
    def __init__(self, dimension=1):
        super().__init__()
        self.d = dimension

    def forward(self, x):
        return torch.cat(x, self.d)


class DetectMultiBackend(nn.Module):
    # YOLOv5 MultiBackend class for python inference on various backends
    def __init__(
        self,
        weights="yolov5s.pt",
        device=torch.device("cpu"),
        dnn=False,
        data=None,
        fp16=False,
        fuse=True,
    ):
        # Usage:
        #   PyTorch:              weights = *.pt
        #   TorchScript:                    *.torchscript
        #   ONNX Runtime:                   *.onnx
        #   ONNX OpenCV DNN:                *.onnx --dnn
        #   OpenVINO:                       *_openvino_model
        #   CoreML:                         *.mlmodel
        #   TensorRT:                       *.engine
        #   TensorFlow SavedModel:          *_saved_model
        #   TensorFlow GraphDef:            *.pb
        #   TensorFlow Lite:                *.tflite
        #   TensorFlow Edge TPU:            *_edgetpu.tflite
        #   PaddlePaddle:                   *_paddle_model
        from models.experimental import (  # scoped to avoid circular import
            attempt_download,
            attempt_load,
        )

        super().__init__()
        w = str(weights[0] if isinstance(weights, list) else weights)
        (
            pt,
            jit,
            onnx,
            xml,
            engine,
            coreml,
            saved_model,
            pb,
            tflite,
            edgetpu,
            tfjs,
            paddle,
            triton,
        ) = self._model_type(w)
        fp16 &= pt or jit or onnx or engine  # FP16
        nhwc = (
            coreml or saved_model or pb or tflite or edgetpu
        )  # BHWC formats (vs torch BCWH)
        stride = 32  # default stride
        cuda = torch.cuda.is_available() and device.type != "cpu"  # use CUDA
        if not (pt or triton):
            w = attempt_download(w)  # download if not local

        if pt:  # PyTorch
            model = attempt_load(
                weights if isinstance(weights, list) else w,
                device=device,
                inplace=True,
                fuse=fuse,
            )
            stride = max(int(model.stride.max()), 32)  # model stride
            names = (
                model.module.names if hasattr(model, "module") else model.names
            )  # get class names
            model.half() if fp16 else model.float()
            self.model = (
                model  # explicitly assign for to(), cpu(), cuda(), half()
            )
        elif jit:  # TorchScript
            LOGGER.info(f"Loading {w} for TorchScript inference...")
            extra_files = {"config.txt": ""}  # model metadata
            model = torch.jit.load(
                w, _extra_files=extra_files, map_location=device
            )
            model.half() if fp16 else model.float()
            if extra_files["config.txt"]:  # load metadata dict
                d = json.loads(
                    extra_files["config.txt"],
                    object_hook=lambda d: {
                        int(k) if k.isdigit() else k: v for k, v in d.items()
                    },
                )
                stride, names = int(d["stride"]), d["names"]
        elif dnn:  # ONNX OpenCV DNN
            LOGGER.info(f"Loading {w} for ONNX OpenCV DNN inference...")
            check_requirements("opencv-python>=4.5.4")
            net = cv2.dnn.readNetFromONNX(w)
        elif onnx:  # ONNX Runtime
            LOGGER.info(f"Loading {w} for ONNX Runtime inference...")
            check_requirements(
                ("onnx", "onnxruntime-gpu" if cuda else "onnxruntime")
            )
            import onnxruntime

            providers = (
                ["CUDAExecutionProvider", "CPUExecutionProvider"]
                if cuda
                else ["CPUExecutionProvider"]
            )
            session = onnxruntime.InferenceSession(w, providers=providers)
            output_names = [x.name for x in session.get_outputs()]
            meta = session.get_modelmeta().custom_metadata_map  # metadata
            if "stride" in meta:
                stride, names = int(meta["stride"]), eval(meta["names"])
        elif xml:  # OpenVINO
            LOGGER.info(f"Loading {w} for OpenVINO inference...")
            check_requirements(
                "openvino"
            )  # requires openvino-dev: https://pypi.org/project/openvino-dev/
            from openvino.runtime import Core, Layout, get_batch

            ie = Core()
            if not Path(w).is_file():  # if not *.xml
                w = next(
                    Path(w).glob("*.xml")
                )  # get *.xml file from *_openvino_model dir
            network = ie.read_model(
                model=w, weights=Path(w).with_suffix(".bin")
            )
            if network.get_parameters()[0].get_layout().empty:
                network.get_parameters()[0].set_layout(Layout("NCHW"))
            batch_dim = get_batch(network)
            if batch_dim.is_static:
                batch_size = batch_dim.get_length()
            executable_network = ie.compile_model(
                network, device_name="CPU"
            )  # device_name="MYRIAD" for Intel NCS2
            stride, names = self._load_metadata(
                Path(w).with_suffix(".yaml")
            )  # load metadata
        elif engine:  # TensorRT
            LOGGER.info(f"Loading {w} for TensorRT inference...")
            import tensorrt as trt  # https://developer.nvidia.com/nvidia-tensorrt-download

            check_version(
                trt.__version__, "7.0.0", hard=True
            )  # require tensorrt>=7.0.0
            if device.type == "cpu":
                device = torch.device("cuda:0")
            Binding = namedtuple(
                "Binding", ("name", "dtype", "shape", "data", "ptr")
            )
            logger = trt.Logger(trt.Logger.INFO)
            with open(w, "rb") as f, trt.Runtime(logger) as runtime:
                model = runtime.deserialize_cuda_engine(f.read())
            context = model.create_execution_context()
            bindings = OrderedDict()
            output_names = []
            fp16 = False  # default updated below
            dynamic = False
            for i in range(model.num_bindings):
                name = model.get_binding_name(i)
                dtype = trt.nptype(model.get_binding_dtype(i))
                if model.binding_is_input(i):
                    if -1 in tuple(model.get_binding_shape(i)):  # dynamic
                        dynamic = True
                        context.set_binding_shape(
                            i, tuple(model.get_profile_shape(0, i)[2])
                        )
                    if dtype == np.float16:
                        fp16 = True
                else:  # output
                    output_names.append(name)
                shape = tuple(context.get_binding_shape(i))
                im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
                bindings[name] = Binding(
                    name, dtype, shape, im, int(im.data_ptr())
                )
            binding_addrs = OrderedDict(
                (n, d.ptr) for n, d in bindings.items()
            )
            batch_size = bindings["images"].shape[
                0
            ]  # if dynamic, this is instead max batch size
        elif coreml:  # CoreML
            LOGGER.info(f"Loading {w} for CoreML inference...")
            import coremltools as ct

            model = ct.models.MLModel(w)
        elif saved_model:  # TF SavedModel
            LOGGER.info(f"Loading {w} for TensorFlow SavedModel inference...")
            import tensorflow as tf

            keras = False  # assume TF1 saved_model
            model = (
                tf.keras.models.load_model(w)
                if keras
                else tf.saved_model.load(w)
            )
        elif (
            pb
        ):  # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
            LOGGER.info(f"Loading {w} for TensorFlow GraphDef inference...")
            import tensorflow as tf

            def wrap_frozen_graph(gd, inputs, outputs):
                x = tf.compat.v1.wrap_function(
                    lambda: tf.compat.v1.import_graph_def(gd, name=""), []
                )  # wrapped
                ge = x.graph.as_graph_element
                return x.prune(
                    tf.nest.map_structure(ge, inputs),
                    tf.nest.map_structure(ge, outputs),
                )

            def gd_outputs(gd):
                name_list, input_list = [], []
                for (
                    node
                ) in gd.node:  # tensorflow.core.framework.node_def_pb2.NodeDef
                    name_list.append(node.name)
                    input_list.extend(node.input)
                return sorted(
                    f"{x}:0"
                    for x in list(set(name_list) - set(input_list))
                    if not x.startswith("NoOp")
                )

            gd = tf.Graph().as_graph_def()  # TF GraphDef
            with open(w, "rb") as f:
                gd.ParseFromString(f.read())
            frozen_func = wrap_frozen_graph(
                gd, inputs="x:0", outputs=gd_outputs(gd)
            )
        elif (
            tflite or edgetpu
        ):  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
            try:  # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
                from tflite_runtime.interpreter import Interpreter, load_delegate
            except ImportError:
                import tensorflow as tf

                Interpreter, load_delegate = (
                    tf.lite.Interpreter,
                    tf.lite.experimental.load_delegate,
                )
            if (
                edgetpu
            ):  # TF Edge TPU https://coral.ai/software/#edgetpu-runtime
                LOGGER.info(
                    f"Loading {w} for TensorFlow Lite Edge TPU inference..."
                )
                delegate = {
                    "Linux": "libedgetpu.so.1",
                    "Darwin": "libedgetpu.1.dylib",
                    "Windows": "edgetpu.dll",
                }[platform.system()]
                interpreter = Interpreter(
                    model_path=w,
                    experimental_delegates=[load_delegate(delegate)],
                )
            else:  # TFLite
                LOGGER.info(f"Loading {w} for TensorFlow Lite inference...")
                interpreter = Interpreter(model_path=w)  # load TFLite model
            interpreter.allocate_tensors()  # allocate
            input_details = interpreter.get_input_details()  # inputs
            output_details = interpreter.get_output_details()  # outputs
            # load metadata
            with contextlib.suppress(zipfile.BadZipFile):
                with zipfile.ZipFile(w, "r") as model:
                    meta_file = model.namelist()[0]
                    meta = ast.literal_eval(
                        model.read(meta_file).decode("utf-8")
                    )
                    stride, names = int(meta["stride"]), meta["names"]
        elif tfjs:  # TF.js
            raise NotImplementedError(
                "ERROR: YOLOv5 TF.js inference is not supported"
            )
        elif paddle:  # PaddlePaddle
            LOGGER.info(f"Loading {w} for PaddlePaddle inference...")
            check_requirements("paddlepaddle-gpu" if cuda else "paddlepaddle")
            import paddle.inference as pdi

            if not Path(w).is_file():  # if not *.pdmodel
                w = next(
                    Path(w).rglob("*.pdmodel")
                )  # get *.pdmodel file from *_paddle_model dir
            weights = Path(w).with_suffix(".pdiparams")
            config = pdi.Config(str(w), str(weights))
            if cuda:
                config.enable_use_gpu(
                    memory_pool_init_size_mb=2048, device_id=0
                )
            predictor = pdi.create_predictor(config)
            input_handle = predictor.get_input_handle(
                predictor.get_input_names()[0]
            )
            output_names = predictor.get_output_names()
        elif triton:  # NVIDIA Triton Inference Server
            LOGGER.info(f"Using {w} as Triton Inference Server...")
            check_requirements("tritonclient[all]")
            from utils.triton import TritonRemoteModel

            model = TritonRemoteModel(url=w)
            nhwc = model.runtime.startswith("tensorflow")
        else:
            raise NotImplementedError(f"ERROR: {w} is not a supported format")

        # class names
        if "names" not in locals():
            names = (
                yaml_load(data)["names"]
                if data
                else {i: f"class{i}" for i in range(999)}
            )
        if names[0] == "n01440764" and len(names) == 1000:  # ImageNet
            names = yaml_load(ROOT / "data/ImageNet.yaml")[
                "names"
            ]  # human-readable names

        self.__dict__.update(locals())  # assign all variables to self

    def forward(self, im, augment=False, visualize=False):
        # YOLOv5 MultiBackend inference
        b, ch, h, w = im.shape  # batch, channel, height, width
        if self.fp16 and im.dtype != torch.float16:
            im = im.half()  # to FP16
        if self.nhwc:
            im = im.permute(
                0, 2, 3, 1
            )  # torch BCHW to numpy BHWC shape(1,320,192,3)

        if self.pt:  # PyTorch
            y = (
                self.model(im, augment=augment, visualize=visualize)
                if augment or visualize
                else self.model(im)
            )
        elif self.jit:  # TorchScript
            y = self.model(im)
        elif self.dnn:  # ONNX OpenCV DNN
            im = im.cpu().numpy()  # torch to numpy
            self.net.setInput(im)
            y = self.net.forward()
        elif self.onnx:  # ONNX Runtime
            im = im.cpu().numpy()  # torch to numpy
            y = self.session.run(
                self.output_names, {self.session.get_inputs()[0].name: im}
            )
        elif self.xml:  # OpenVINO
            im = im.cpu().numpy()  # FP32
            y = list(self.executable_network([im]).values())
        elif self.engine:  # TensorRT
            if self.dynamic and im.shape != self.bindings["images"].shape:
                i = self.model.get_binding_index("images")
                self.context.set_binding_shape(
                    i, im.shape
                )  # reshape if dynamic
                self.bindings["images"] = self.bindings["images"]._replace(
                    shape=im.shape
                )
                for name in self.output_names:
                    i = self.model.get_binding_index(name)
                    self.bindings[name].data.resize_(
                        tuple(self.context.get_binding_shape(i))
                    )
            s = self.bindings["images"].shape
            assert (
                im.shape == s
            ), f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}"
            self.binding_addrs["images"] = int(im.data_ptr())
            self.context.execute_v2(list(self.binding_addrs.values()))
            y = [self.bindings[x].data for x in sorted(self.output_names)]
        elif self.coreml:  # CoreML
            im = im.cpu().numpy()
            im = Image.fromarray((im[0] * 255).astype("uint8"))
            # im = im.resize((192, 320), Image.ANTIALIAS)
            y = self.model.predict(
                {"image": im}
            )  # coordinates are xywh normalized
            if "confidence" in y:
                box = xywh2xyxy(
                    y["coordinates"] * [[w, h, w, h]]
                )  # xyxy pixels
                conf, cls = y["confidence"].max(1), y["confidence"].argmax(
                    1
                ).astype(np.float)
                y = np.concatenate(
                    (box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1
                )
            else:
                y = list(
                    reversed(y.values())
                )  # reversed for segmentation models (pred, proto)
        elif self.paddle:  # PaddlePaddle
            im = im.cpu().numpy().astype(np.float32)
            self.input_handle.copy_from_cpu(im)
            self.predictor.run()
            y = [
                self.predictor.get_output_handle(x).copy_to_cpu()
                for x in self.output_names
            ]
        elif self.triton:  # NVIDIA Triton Inference Server
            y = self.model(im)
        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
            im = im.cpu().numpy()
            if self.saved_model:  # SavedModel
                y = (
                    self.model(im, training=False)
                    if self.keras
                    else self.model(im)
                )
            elif self.pb:  # GraphDef
                y = self.frozen_func(x=self.tf.constant(im))
            else:  # Lite or Edge TPU
                input = self.input_details[0]
                int8 = (
                    input["dtype"] == np.uint8
                )  # is TFLite quantized uint8 model
                if int8:
                    scale, zero_point = input["quantization"]
                    im = (im / scale + zero_point).astype(np.uint8)  # de-scale
                self.interpreter.set_tensor(input["index"], im)
                self.interpreter.invoke()
                y = []
                for output in self.output_details:
                    x = self.interpreter.get_tensor(output["index"])
                    if int8:
                        scale, zero_point = output["quantization"]
                        x = (
                            x.astype(np.float32) - zero_point
                        ) * scale  # re-scale
                    y.append(x)
            y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y]
            y[0][..., :4] *= [w, h, w, h]  # xywh normalized to pixels

        if isinstance(y, (list, tuple)):
            return (
                self.from_numpy(y[0])
                if len(y) == 1
                else [self.from_numpy(x) for x in y]
            )
        else:
            return self.from_numpy(y)

    def from_numpy(self, x):
        return (
            torch.from_numpy(x).to(self.device)
            if isinstance(x, np.ndarray)
            else x
        )

    def warmup(self, imgsz=(1, 3, 640, 640)):
        # Warmup model by running inference once
        warmup_types = (
            self.pt,
            self.jit,
            self.onnx,
            self.engine,
            self.saved_model,
            self.pb,
            self.triton,
        )
        if any(warmup_types) and (self.device.type != "cpu" or self.triton):
            im = torch.empty(
                *imgsz,
                dtype=torch.half if self.fp16 else torch.float,
                device=self.device,
            )  # input
            for _ in range(2 if self.jit else 1):  #
                self.forward(im)  # warmup

    @staticmethod
    def _model_type(p="path/to/model.pt"):
        # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
        # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle]
        from export import export_formats
        from utils.downloads import is_url

        sf = list(export_formats().Suffix)  # export suffixes
        if not is_url(p, check=False):
            check_suffix(p, sf)  # checks
        url = urlparse(p)  # if url may be Triton inference server
        types = [s in Path(p).name for s in sf]
        types[8] &= not types[9]  # tflite &= not edgetpu
        triton = not any(types) and all(
            [any(s in url.scheme for s in ["http", "grpc"]), url.netloc]
        )
        return types + [triton]

    @staticmethod
    def _load_metadata(f=Path("path/to/meta.yaml")):
        # Load metadata from meta.yaml if it exists
        if f.exists():
            d = yaml_load(f)
            return d["stride"], d["names"]  # assign stride, names
        return None, None


class AutoShape(nn.Module):
    # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
    conf = 0.25  # NMS confidence threshold
    iou = 0.45  # NMS IoU threshold
    agnostic = False  # NMS class-agnostic
    multi_label = False  # NMS multiple labels per box
    classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
    max_det = 1000  # maximum number of detections per image
    amp = False  # Automatic Mixed Precision (AMP) inference

    def __init__(self, model, verbose=True):
        super().__init__()
        if verbose:
            LOGGER.info("Adding AutoShape... ")
        copy_attr(
            self,
            model,
            include=("yaml", "nc", "hyp", "names", "stride", "abc"),
            exclude=(),
        )  # copy attributes
        self.dmb = isinstance(
            model, DetectMultiBackend
        )  # DetectMultiBackend() instance
        self.pt = not self.dmb or model.pt  # PyTorch model
        self.model = model.eval()
        if self.pt:
            m = (
                self.model.model.model[-1]
                if self.dmb
                else self.model.model[-1]
            )  # Detect()
            m.inplace = (
                False  # Detect.inplace=False for safe multithread inference
            )
            m.export = True  # do not output loss values

    def _apply(self, fn):
        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
        self = super()._apply(fn)
        if self.pt:
            m = (
                self.model.model.model[-1]
                if self.dmb
                else self.model.model[-1]
            )  # Detect()
            m.stride = fn(m.stride)
            m.grid = list(map(fn, m.grid))
            if isinstance(m.anchor_grid, list):
                m.anchor_grid = list(map(fn, m.anchor_grid))
        return self

    @smart_inference_mode()
    def forward(self, ims, size=640, augment=False, profile=False):
        # Inference from various sources. For size(height=640, width=1280), RGB images example inputs are:
        #   file:        ims = 'data/images/zidane.jpg'  # str or PosixPath
        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
        #   numpy:           = np.zeros((640,1280,3))  # HWC
        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images

        dt = (Profile(), Profile(), Profile())
        with dt[0]:
            if isinstance(size, int):  # expand
                size = (size, size)
            p = (
                next(self.model.parameters())
                if self.pt
                else torch.empty(1, device=self.model.device)
            )  # param
            autocast = self.amp and (
                p.device.type != "cpu"
            )  # Automatic Mixed Precision (AMP) inference
            if isinstance(ims, torch.Tensor):  # torch
                with amp.autocast(autocast):
                    return self.model(
                        ims.to(p.device).type_as(p), augment=augment
                    )  # inference

            # Pre-process
            n, ims = (
                (len(ims), list(ims))
                if isinstance(ims, (list, tuple))
                else (1, [ims])
            )  # number, list of images
            shape0, shape1, files = (
                [],
                [],
                [],
            )  # image and inference shapes, filenames
            for i, im in enumerate(ims):
                f = f"image{i}"  # filename
                if isinstance(im, (str, Path)):  # filename or uri
                    im, f = (
                        Image.open(
                            requests.get(im, stream=True).raw
                            if str(im).startswith("http")
                            else im
                        ),
                        im,
                    )
                    im = np.asarray(exif_transpose(im))
                elif isinstance(im, Image.Image):  # PIL Image
                    im, f = (
                        np.asarray(exif_transpose(im)),
                        getattr(im, "filename", f) or f,
                    )
                files.append(Path(f).with_suffix(".jpg").name)
                if im.shape[0] < 5:  # image in CHW
                    im = im.transpose(
                        (1, 2, 0)
                    )  # reverse dataloader .transpose(2, 0, 1)
                im = (
                    im[..., :3]
                    if im.ndim == 3
                    else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR)
                )  # enforce 3ch input
                s = im.shape[:2]  # HWC
                shape0.append(s)  # image shape
                g = max(size) / max(s)  # gain
                shape1.append([int(y * g) for y in s])
                ims[i] = (
                    im if im.data.contiguous else np.ascontiguousarray(im)
                )  # update
            shape1 = [
                make_divisible(x, self.stride) for x in np.array(shape1).max(0)
            ]  # inf shape
            x = [letterbox(im, shape1, auto=False)[0] for im in ims]  # pad
            x = np.ascontiguousarray(
                np.array(x).transpose((0, 3, 1, 2))
            )  # stack and BHWC to BCHW
            x = (
                torch.from_numpy(x).to(p.device).type_as(p) / 255
            )  # uint8 to fp16/32

        with amp.autocast(autocast):
            # Inference
            with dt[1]:
                y = self.model(x, augment=augment)  # forward

            # Post-process
            with dt[2]:
                y = non_max_suppression(
                    y if self.dmb else y[0],
                    self.conf,
                    self.iou,
                    self.classes,
                    self.agnostic,
                    self.multi_label,
                    max_det=self.max_det,
                )  # NMS
                for i in range(n):
                    scale_boxes(shape1, y[i][:, :4], shape0[i])

            return Detections(ims, y, files, dt, self.names, x.shape)


class Detections:
    # YOLOv5 detections class for inference results
    def __init__(
        self, ims, pred, files, times=(0, 0, 0), names=None, shape=None
    ):
        super().__init__()
        d = pred[0].device  # device
        gn = [
            torch.tensor(
                [*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d
            )
            for im in ims
        ]  # normalizations
        self.ims = ims  # list of images as numpy arrays
        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
        self.names = names  # class names
        self.files = files  # image filenames
        self.times = times  # profiling times
        self.xyxy = pred  # xyxy pixels
        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
        self.n = len(self.pred)  # number of images (batch size)
        self.t = tuple(x.t / self.n * 1e3 for x in times)  # timestamps (ms)
        self.s = tuple(shape)  # inference BCHW shape

    def _run(
        self,
        pprint=False,
        show=False,
        save=False,
        crop=False,
        render=False,
        labels=True,
        save_dir=Path(""),
    ):
        s, crops = "", []
        for i, (im, pred) in enumerate(zip(self.ims, self.pred)):
            s += f"\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} "  # string
            if pred.shape[0]:
                for c in pred[:, -1].unique():
                    n = (pred[:, -1] == c).sum()  # detections per class
                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
                s = s.rstrip(", ")
                if show or save or render or crop:
                    annotator = Annotator(im, example=str(self.names))
                    for *box, conf, cls in reversed(
                        pred
                    ):  # xyxy, confidence, class
                        label = f"{self.names[int(cls)]} {conf:.2f}"
                        if crop:
                            file = (
                                save_dir
                                / "crops"
                                / self.names[int(cls)]
                                / self.files[i]
                                if save
                                else None
                            )
                            crops.append(
                                {
                                    "box": box,
                                    "conf": conf,
                                    "cls": cls,
                                    "label": label,
                                    "im": save_one_box(
                                        box, im, file=file, save=save
                                    ),
                                }
                            )
                        else:  # all others
                            annotator.box_label(
                                box, label if labels else "", color=colors(cls)
                            )
                    im = annotator.im
            else:
                s += "(no detections)"

            im = (
                Image.fromarray(im.astype(np.uint8))
                if isinstance(im, np.ndarray)
                else im
            )  # from np
            if show:
                display(im) if is_notebook() else im.show(self.files[i])
            if save:
                f = self.files[i]
                im.save(save_dir / f)  # save
                if i == self.n - 1:
                    LOGGER.info(
                        f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}"
                    )
            if render:
                self.ims[i] = np.asarray(im)
        if pprint:
            s = s.lstrip("\n")
            return (
                f"{s}\nSpeed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {self.s}"
                % self.t
            )
        if crop:
            if save:
                LOGGER.info(f"Saved results to {save_dir}\n")
            return crops

    @TryExcept("Showing images is not supported in this environment")
    def show(self, labels=True):
        self._run(show=True, labels=labels)  # show results

    def save(self, labels=True, save_dir="runs/detect/exp", exist_ok=False):
        save_dir = increment_path(
            save_dir, exist_ok, mkdir=True
        )  # increment save_dir
        self._run(save=True, labels=labels, save_dir=save_dir)  # save results

    def crop(self, save=True, save_dir="runs/detect/exp", exist_ok=False):
        save_dir = (
            increment_path(save_dir, exist_ok, mkdir=True) if save else None
        )
        return self._run(
            crop=True, save=save, save_dir=save_dir
        )  # crop results

    def render(self, labels=True):
        self._run(render=True, labels=labels)  # render results
        return self.ims

    def pandas(self):
        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
        new = copy(self)  # return copy
        ca = (
            "xmin",
            "ymin",
            "xmax",
            "ymax",
            "confidence",
            "class",
            "name",
        )  # xyxy columns
        cb = (
            "xcenter",
            "ycenter",
            "width",
            "height",
            "confidence",
            "class",
            "name",
        )  # xywh columns
        for k, c in zip(["xyxy", "xyxyn", "xywh", "xywhn"], [ca, ca, cb, cb]):
            a = [
                [
                    x[:5] + [int(x[5]), self.names[int(x[5])]]
                    for x in x.tolist()
                ]
                for x in getattr(self, k)
            ]  # update
            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
        return new

    def tolist(self):
        # return a list of Detections objects, i.e. 'for result in results.tolist():'
        r = range(self.n)  # iterable
        x = [
            Detections(
                [self.ims[i]],
                [self.pred[i]],
                [self.files[i]],
                self.times,
                self.names,
                self.s,
            )
            for i in r
        ]
        # for d in x:
        #    for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
        #        setattr(d, k, getattr(d, k)[0])  # pop out of list
        return x

    def print(self):
        LOGGER.info(self.__str__())

    def __len__(self):  # override len(results)
        return self.n

    def __str__(self):  # override print(results)
        return self._run(pprint=True)  # print results

    def __repr__(self):
        return f"YOLOv5 {self.__class__} instance\n" + self.__str__()


class Proto(nn.Module):
    # YOLOv5 mask Proto module for segmentation models
    def __init__(
        self, c1, c_=256, c2=32
    ):  # ch_in, number of protos, number of masks
        super().__init__()
        self.cv1 = Conv(c1, c_, k=3)
        self.upsample = nn.Upsample(scale_factor=2, mode="nearest")
        self.cv2 = Conv(c_, c_, k=3)
        self.cv3 = Conv(c_, c2)

    def forward(self, x):
        return self.cv3(self.cv2(self.upsample(self.cv1(x))))


class Classify(nn.Module):
    # YOLOv5 classification head, i.e. x(b,c1,20,20) to x(b,c2)
    def __init__(
        self, c1, c2, k=1, s=1, p=None, g=1
    ):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        c_ = 1280  # efficientnet_b0 size
        self.conv = Conv(c1, c_, k, s, autopad(k, p), g)
        self.pool = nn.AdaptiveAvgPool2d(1)  # to x(b,c_,1,1)
        self.drop = nn.Dropout(p=0.0, inplace=True)
        self.linear = nn.Linear(c_, c2)  # to x(b,c2)

    def forward(self, x):
        if isinstance(x, list):
            x = torch.cat(x, 1)
        return self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))