File size: 45,905 Bytes
24bea5e
 
 
 
fe341fa
1e84a23
c6b5bfc
7a565f1
9e9219f
1e84a23
 
 
 
194f168
0155548
1e84a23
 
a64a4c8
1e84a23
 
 
 
69be8e7
b6fdd2e
0155548
09d1703
1e84a23
 
f7d8562
9c513ca
8f875d9
d8b5beb
1e84a23
fe341fa
f7d8562
8a66eba
 
c09fb2a
1e84a23
 
 
 
 
 
 
c6b5bfc
 
 
 
 
 
520f5de
 
1e84a23
 
 
 
 
 
 
 
 
cba4303
1e84a23
 
 
 
 
831773f
 
 
15e8c4c
831773f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
958ab92
09d1703
 
 
 
 
4102fcc
09d1703
 
 
4b5f480
958ab92
4b5f480
4949401
dd03b20
 
22fb2b0
 
d8b5beb
c43f135
09d1703
 
 
 
 
 
 
 
 
 
 
 
fe341fa
1e15aad
fe341fa
d3f9bf2
1e15aad
 
 
d49c52e
1e15aad
 
 
 
 
 
 
 
 
 
ed887b5
fe341fa
1e15aad
d49c52e
 
 
 
 
 
1e15aad
d49c52e
 
 
1e15aad
 
57ce73c
 
808bcad
c47be26
8412d44
9c0efdd
8412d44
 
eae3330
8412d44
eae3330
dd03b20
1e84a23
f7d8562
 
eae3330
1e84a23
 
a18efc3
1e84a23
eae3330
 
54043a9
808bcad
1e84a23
 
 
 
dd03b20
f7d8562
1e84a23
 
 
 
 
 
eae3330
1e84a23
 
 
 
 
 
 
1679aac
1e84a23
 
eae3330
1e84a23
 
 
 
 
 
 
7b1f7ae
1e84a23
 
 
 
fdbe527
7b1f7ae
 
1e84a23
 
808bcad
1e84a23
 
3c3f8fb
1e84a23
 
7b1f7ae
1e84a23
 
 
 
36b0a9e
1e84a23
 
eae3330
1e84a23
 
 
57ce73c
a18efc3
1e84a23
a18efc3
7d6af69
 
1e84a23
 
 
 
 
 
 
 
 
 
 
 
 
 
7d6af69
 
1e84a23
 
dd03b20
1e84a23
7b1f7ae
1e84a23
 
a18efc3
1e84a23
 
3c3f8fb
1e84a23
 
7b1f7ae
1e84a23
 
 
 
 
57ce73c
 
808bcad
54043a9
1e84a23
a18efc3
1e84a23
 
ed887b5
9fa7f9f
1e84a23
 
 
 
683cefe
d5289b5
808bcad
aff03be
 
7b1f7ae
aff03be
b40bdd6
e2b7bc0
aff03be
 
 
7b1f7ae
1e84a23
 
9e9219f
0e2f2cb
9e9219f
e2b7bc0
1e84a23
48b00db
7b1f7ae
683cefe
7b1f7ae
1e84a23
 
11f85e7
1e84a23
 
7b1f7ae
1e84a23
48b00db
683cefe
7d6af69
683cefe
1e84a23
 
 
7d6af69
7b833e3
48b00db
 
 
79bca2b
e8f8f2b
48b00db
683cefe
1e84a23
 
 
 
 
 
 
683cefe
1e84a23
 
 
 
683cefe
808bcad
1e84a23
 
 
 
 
3c3f8fb
1e84a23
 
7b1f7ae
1e84a23
 
9d86b54
1e84a23
 
89c7a5b
 
 
b83e1a4
89c7a5b
 
57ce73c
 
991c654
4fdaec0
93a6765
dd03b20
481d46c
 
 
 
 
 
 
 
73a0669
33202b7
4bdc5a3
1e84a23
520f5de
47bf173
548a98a
 
 
db3bbdd
548a98a
ed887b5
9fa7f9f
548a98a
47bf173
4bdc5a3
94342ac
dd03b20
4728840
db3bbdd
4728840
dd33d2a
f7d8562
1e84a23
520f5de
4728840
443af8b
 
 
4fdaec0
4728840
cba4303
bdd88e1
31f3310
89c7a5b
fd55271
bdd88e1
fd55271
c09fb2a
f527704
79bca2b
f7d8562
89c7a5b
d61930e
f527704
bdd88e1
520f5de
d61930e
4728840
d61930e
481d46c
 
 
 
 
9728e2b
481d46c
a346926
 
 
 
 
 
 
 
 
 
 
 
 
 
d61930e
1e84a23
 
31f3310
1e84a23
 
4728840
1e84a23
6649770
1e84a23
 
 
 
 
 
 
 
 
 
 
 
 
b8557f8
1e84a23
b57abb1
4728840
 
520f5de
1e84a23
4728840
 
 
c09fb2a
194f168
2d99063
4728840
b57abb1
4728840
 
2d99063
1e8ab3f
e2b7bc0
dd03b20
520f5de
 
f527704
28bff22
f7d8562
4728840
c09fb2a
cba4303
8d52c1c
 
 
 
28bff22
cba4303
f527704
 
fd55271
e2b7bc0
8d52c1c
f527704
79bca2b
89c7a5b
79bca2b
4728840
 
f527704
4fdaec0
955eea8
443af8b
 
79bca2b
955eea8
79bca2b
520f5de
1e84a23
 
4728840
1e84a23
 
 
89c7a5b
1e84a23
 
 
 
9728e2b
1e84a23
 
f1c63e2
 
1e84a23
b57abb1
1e84a23
 
9e8fb9f
127cbeb
b57abb1
9e8fb9f
1e84a23
 
b57abb1
1e84a23
 
 
 
 
 
d921214
 
 
1e84a23
33202b7
bcd452c
 
 
 
127cbeb
 
1e84a23
33202b7
 
80299a5
1e84a23
 
33202b7
 
11f85e7
33202b7
 
 
 
 
127cbeb
1e84a23
33202b7
1e84a23
 
33202b7
127cbeb
 
33202b7
127cbeb
 
33202b7
b3dabdc
d885799
33202b7
 
 
1e84a23
 
 
3c3f8fb
1e84a23
 
4728840
1e84a23
b57abb1
4728840
 
b57abb1
4728840
 
b57abb1
 
 
 
 
 
 
 
 
 
 
4728840
 
 
 
 
 
 
b57abb1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e84a23
 
4728840
cba4303
 
4728840
1e84a23
69be8e7
 
 
 
4728840
69be8e7
5866646
 
 
69be8e7
 
 
5866646
69be8e7
cba4303
69be8e7
 
cba4303
4728840
cba4303
69be8e7
cba4303
 
69be8e7
4728840
69be8e7
1e84a23
4b5f480
 
1e84a23
 
 
 
19e2482
 
9c513ca
19e2482
9c513ca
19e2482
 
 
4798e66
 
9c513ca
89c7a5b
 
 
 
 
 
f7d8562
89c7a5b
 
 
 
 
 
 
ed887b5
cff9263
89c7a5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2b7bc0
9c513ca
354109c
f899417
38ff499
f899417
 
 
4798e66
 
ed887b5
354109c
f899417
354109c
38ff499
4798e66
f899417
38ff499
 
354109c
38ff499
f899417
 
28bff22
 
6c0e1d9
28bff22
6c0e1d9
11f85e7
28bff22
 
 
 
 
 
f7d8562
d808855
 
 
11f85e7
15e8c4c
991c654
28bff22
 
 
 
ed887b5
cba4303
caf7ad0
cba4303
 
 
 
 
991c654
cba4303
 
 
 
6903251
cba4303
6903251
 
 
28bff22
 
cba4303
28bff22
 
cba4303
 
28bff22
 
991c654
f527704
b6fdd2e
 
fe7de6a
b6fdd2e
5d66e48
fe7de6a
9c513ca
b6fdd2e
8c6f9e1
1b5edb6
b6fdd2e
 
9b6dba6
 
 
ed887b5
9b6dba6
8c6f9e1
 
 
5d66e48
a64a4c8
 
5d66e48
8c6f9e1
 
 
5d66e48
276b674
 
 
 
 
 
 
d5b21b1
276b674
 
 
 
 
 
5ca5dd4
276b674
5d66e48
8c6f9e1
a2b3c71
b6fdd2e
8c6f9e1
 
fe7de6a
5d66e48
 
b6fdd2e
3213d87
b6fdd2e
 
 
5d66e48
b6fdd2e
5d66e48
b6fdd2e
7a565f1
 
 
9b6dba6
4728840
7a565f1
5d66e48
 
 
4728840
5d66e48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed887b5
5d66e48
 
 
7a565f1
5d66e48
 
 
 
b6fdd2e
9b6dba6
b6fdd2e
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
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Dataloaders and dataset utils
"""

import glob
import hashlib
import json
import math
import os
import random
import shutil
import time
from itertools import repeat
from multiprocessing.pool import Pool, ThreadPool
from pathlib import Path
from threading import Thread
from zipfile import ZipFile

import cv2
import numpy as np
import torch
import torch.nn.functional as F
import yaml
from PIL import ExifTags, Image, ImageOps
from torch.utils.data import DataLoader, Dataset, dataloader, distributed
from tqdm import tqdm

from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective
from utils.general import (DATASETS_DIR, LOGGER, NUM_THREADS, check_dataset, check_requirements, check_yaml, clean_str,
                           segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn)
from utils.torch_utils import torch_distributed_zero_first

# Parameters
HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
IMG_FORMATS = 'bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp'  # include image suffixes
VID_FORMATS = 'asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'ts', 'wmv'  # include video suffixes
BAR_FORMAT = '{l_bar}{bar:10}{r_bar}{bar:-10b}'  # tqdm bar format

# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
    if ExifTags.TAGS[orientation] == 'Orientation':
        break


def get_hash(paths):
    # Returns a single hash value of a list of paths (files or dirs)
    size = sum(os.path.getsize(p) for p in paths if os.path.exists(p))  # sizes
    h = hashlib.md5(str(size).encode())  # hash sizes
    h.update(''.join(paths).encode())  # hash paths
    return h.hexdigest()  # return hash


def exif_size(img):
    # Returns exif-corrected PIL size
    s = img.size  # (width, height)
    try:
        rotation = dict(img._getexif().items())[orientation]
        if rotation == 6:  # rotation 270
            s = (s[1], s[0])
        elif rotation == 8:  # rotation 90
            s = (s[1], s[0])
    except Exception:
        pass

    return s


def exif_transpose(image):
    """
    Transpose a PIL image accordingly if it has an EXIF Orientation tag.
    Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose()

    :param image: The image to transpose.
    :return: An image.
    """
    exif = image.getexif()
    orientation = exif.get(0x0112, 1)  # default 1
    if orientation > 1:
        method = {2: Image.FLIP_LEFT_RIGHT,
                  3: Image.ROTATE_180,
                  4: Image.FLIP_TOP_BOTTOM,
                  5: Image.TRANSPOSE,
                  6: Image.ROTATE_270,
                  7: Image.TRANSVERSE,
                  8: Image.ROTATE_90,
                  }.get(orientation)
        if method is not None:
            image = image.transpose(method)
            del exif[0x0112]
            image.info["exif"] = exif.tobytes()
    return image


def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0,
                      rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix='', shuffle=False):
    if rect and shuffle:
        LOGGER.warning('WARNING: --rect is incompatible with DataLoader shuffle, setting shuffle=False')
        shuffle = False
    with torch_distributed_zero_first(rank):  # init dataset *.cache only once if DDP
        dataset = LoadImagesAndLabels(path, imgsz, batch_size,
                                      augment=augment,  # augmentation
                                      hyp=hyp,  # hyperparameters
                                      rect=rect,  # rectangular batches
                                      cache_images=cache,
                                      single_cls=single_cls,
                                      stride=int(stride),
                                      pad=pad,
                                      image_weights=image_weights,
                                      prefix=prefix)

    batch_size = min(batch_size, len(dataset))
    nd = torch.cuda.device_count()  # number of CUDA devices
    nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers])  # number of workers
    sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
    loader = DataLoader if image_weights else InfiniteDataLoader  # only DataLoader allows for attribute updates
    return loader(dataset,
                  batch_size=batch_size,
                  shuffle=shuffle and sampler is None,
                  num_workers=nw,
                  sampler=sampler,
                  pin_memory=True,
                  collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn), dataset


class InfiniteDataLoader(dataloader.DataLoader):
    """ Dataloader that reuses workers

    Uses same syntax as vanilla DataLoader
    """

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
        self.iterator = super().__iter__()

    def __len__(self):
        return len(self.batch_sampler.sampler)

    def __iter__(self):
        for i in range(len(self)):
            yield next(self.iterator)


class _RepeatSampler:
    """ Sampler that repeats forever

    Args:
        sampler (Sampler)
    """

    def __init__(self, sampler):
        self.sampler = sampler

    def __iter__(self):
        while True:
            yield from iter(self.sampler)


class LoadImages:
    # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
    def __init__(self, path, img_size=640, stride=32, auto=True):
        p = str(Path(path).resolve())  # os-agnostic absolute path
        if '*' in p:
            files = sorted(glob.glob(p, recursive=True))  # glob
        elif os.path.isdir(p):
            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
        elif os.path.isfile(p):
            files = [p]  # files
        else:
            raise Exception(f'ERROR: {p} does not exist')

        images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
        videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
        ni, nv = len(images), len(videos)

        self.img_size = img_size
        self.stride = stride
        self.files = images + videos
        self.nf = ni + nv  # number of files
        self.video_flag = [False] * ni + [True] * nv
        self.mode = 'image'
        self.auto = auto
        if any(videos):
            self.new_video(videos[0])  # new video
        else:
            self.cap = None
        assert self.nf > 0, f'No images or videos found in {p}. ' \
                            f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'

    def __iter__(self):
        self.count = 0
        return self

    def __next__(self):
        if self.count == self.nf:
            raise StopIteration
        path = self.files[self.count]

        if self.video_flag[self.count]:
            # Read video
            self.mode = 'video'
            ret_val, img0 = self.cap.read()
            while not ret_val:
                self.count += 1
                self.cap.release()
                if self.count == self.nf:  # last video
                    raise StopIteration
                else:
                    path = self.files[self.count]
                    self.new_video(path)
                    ret_val, img0 = self.cap.read()

            self.frame += 1
            s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '

        else:
            # Read image
            self.count += 1
            img0 = cv2.imread(path)  # BGR
            assert img0 is not None, f'Image Not Found {path}'
            s = f'image {self.count}/{self.nf} {path}: '

        # Padded resize
        img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]

        # Convert
        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
        img = np.ascontiguousarray(img)

        return path, img, img0, self.cap, s

    def new_video(self, path):
        self.frame = 0
        self.cap = cv2.VideoCapture(path)
        self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))

    def __len__(self):
        return self.nf  # number of files


class LoadWebcam:  # for inference
    # YOLOv5 local webcam dataloader, i.e. `python detect.py --source 0`
    def __init__(self, pipe='0', img_size=640, stride=32):
        self.img_size = img_size
        self.stride = stride
        self.pipe = eval(pipe) if pipe.isnumeric() else pipe
        self.cap = cv2.VideoCapture(self.pipe)  # video capture object
        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size

    def __iter__(self):
        self.count = -1
        return self

    def __next__(self):
        self.count += 1
        if cv2.waitKey(1) == ord('q'):  # q to quit
            self.cap.release()
            cv2.destroyAllWindows()
            raise StopIteration

        # Read frame
        ret_val, img0 = self.cap.read()
        img0 = cv2.flip(img0, 1)  # flip left-right

        # Print
        assert ret_val, f'Camera Error {self.pipe}'
        img_path = 'webcam.jpg'
        s = f'webcam {self.count}: '

        # Padded resize
        img = letterbox(img0, self.img_size, stride=self.stride)[0]

        # Convert
        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
        img = np.ascontiguousarray(img)

        return img_path, img, img0, None, s

    def __len__(self):
        return 0


class LoadStreams:
    # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streams`
    def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
        self.mode = 'stream'
        self.img_size = img_size
        self.stride = stride

        if os.path.isfile(sources):
            with open(sources) as f:
                sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
        else:
            sources = [sources]

        n = len(sources)
        self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
        self.sources = [clean_str(x) for x in sources]  # clean source names for later
        self.auto = auto
        for i, s in enumerate(sources):  # index, source
            # Start thread to read frames from video stream
            st = f'{i + 1}/{n}: {s}... '
            if 'youtube.com/' in s or 'youtu.be/' in s:  # if source is YouTube video
                check_requirements(('pafy', 'youtube_dl==2020.12.2'))
                import pafy
                s = pafy.new(s).getbest(preftype="mp4").url  # YouTube URL
            s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
            cap = cv2.VideoCapture(s)
            assert cap.isOpened(), f'{st}Failed to open {s}'
            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
            fps = cap.get(cv2.CAP_PROP_FPS)  # warning: may return 0 or nan
            self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf')  # infinite stream fallback
            self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30  # 30 FPS fallback

            _, self.imgs[i] = cap.read()  # guarantee first frame
            self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
            LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
            self.threads[i].start()
        LOGGER.info('')  # newline

        # check for common shapes
        s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
        if not self.rect:
            LOGGER.warning('WARNING: Stream shapes differ. For optimal performance supply similarly-shaped streams.')

    def update(self, i, cap, stream):
        # Read stream `i` frames in daemon thread
        n, f, read = 0, self.frames[i], 1  # frame number, frame array, inference every 'read' frame
        while cap.isOpened() and n < f:
            n += 1
            # _, self.imgs[index] = cap.read()
            cap.grab()
            if n % read == 0:
                success, im = cap.retrieve()
                if success:
                    self.imgs[i] = im
                else:
                    LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.')
                    self.imgs[i] = np.zeros_like(self.imgs[i])
                    cap.open(stream)  # re-open stream if signal was lost
            time.sleep(1 / self.fps[i])  # wait time

    def __iter__(self):
        self.count = -1
        return self

    def __next__(self):
        self.count += 1
        if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'):  # q to quit
            cv2.destroyAllWindows()
            raise StopIteration

        # Letterbox
        img0 = self.imgs.copy()
        img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]

        # Stack
        img = np.stack(img, 0)

        # Convert
        img = img[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW
        img = np.ascontiguousarray(img)

        return self.sources, img, img0, None, ''

    def __len__(self):
        return len(self.sources)  # 1E12 frames = 32 streams at 30 FPS for 30 years


def img2label_paths(img_paths):
    # Define label paths as a function of image paths
    sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep  # /images/, /labels/ substrings
    return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]


class LoadImagesAndLabels(Dataset):
    # YOLOv5 train_loader/val_loader, loads images and labels for training and validation
    cache_version = 0.6  # dataset labels *.cache version

    def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
                 cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
        self.img_size = img_size
        self.augment = augment
        self.hyp = hyp
        self.image_weights = image_weights
        self.rect = False if image_weights else rect
        self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
        self.mosaic_border = [-img_size // 2, -img_size // 2]
        self.stride = stride
        self.path = path
        self.albumentations = Albumentations() if augment else None

        try:
            f = []  # image files
            for p in path if isinstance(path, list) else [path]:
                p = Path(p)  # os-agnostic
                if p.is_dir():  # dir
                    f += glob.glob(str(p / '**' / '*.*'), recursive=True)
                    # f = list(p.rglob('*.*'))  # pathlib
                elif p.is_file():  # file
                    with open(p) as t:
                        t = t.read().strip().splitlines()
                        parent = str(p.parent) + os.sep
                        f += [x.replace('./', parent) if x.startswith('./') else x for x in t]  # local to global path
                        # f += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
                else:
                    raise Exception(f'{prefix}{p} does not exist')
            self.im_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS])  # pathlib
            assert self.im_files, f'{prefix}No images found'
        except Exception as e:
            raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')

        # Check cache
        self.label_files = img2label_paths(self.im_files)  # labels
        cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
        try:
            cache, exists = np.load(cache_path, allow_pickle=True).item(), True  # load dict
            assert cache['version'] == self.cache_version  # same version
            assert cache['hash'] == get_hash(self.label_files + self.im_files)  # same hash
        except Exception:
            cache, exists = self.cache_labels(cache_path, prefix), False  # cache

        # Display cache
        nf, nm, ne, nc, n = cache.pop('results')  # found, missing, empty, corrupt, total
        if exists:
            d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt"
            tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=BAR_FORMAT)  # display cache results
            if cache['msgs']:
                LOGGER.info('\n'.join(cache['msgs']))  # display warnings
        assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'

        # Read cache
        [cache.pop(k) for k in ('hash', 'version', 'msgs')]  # remove items
        labels, shapes, self.segments = zip(*cache.values())
        self.labels = list(labels)
        self.shapes = np.array(shapes, dtype=np.float64)
        self.im_files = list(cache.keys())  # update
        self.label_files = img2label_paths(cache.keys())  # update
        n = len(shapes)  # number of images
        bi = np.floor(np.arange(n) / batch_size).astype(np.int)  # batch index
        nb = bi[-1] + 1  # number of batches
        self.batch = bi  # batch index of image
        self.n = n
        self.indices = range(n)

        # Update labels
        include_class = []  # filter labels to include only these classes (optional)
        include_class_array = np.array(include_class).reshape(1, -1)
        for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
            if include_class:
                j = (label[:, 0:1] == include_class_array).any(1)
                self.labels[i] = label[j]
                if segment:
                    self.segments[i] = segment[j]
            if single_cls:  # single-class training, merge all classes into 0
                self.labels[i][:, 0] = 0
                if segment:
                    self.segments[i][:, 0] = 0

        # Rectangular Training
        if self.rect:
            # Sort by aspect ratio
            s = self.shapes  # wh
            ar = s[:, 1] / s[:, 0]  # aspect ratio
            irect = ar.argsort()
            self.im_files = [self.im_files[i] for i in irect]
            self.label_files = [self.label_files[i] for i in irect]
            self.labels = [self.labels[i] for i in irect]
            self.shapes = s[irect]  # wh
            ar = ar[irect]

            # Set training image shapes
            shapes = [[1, 1]] * nb
            for i in range(nb):
                ari = ar[bi == i]
                mini, maxi = ari.min(), ari.max()
                if maxi < 1:
                    shapes[i] = [maxi, 1]
                elif mini > 1:
                    shapes[i] = [1, 1 / mini]

            self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride

        # Cache images into RAM/disk for faster training (WARNING: large datasets may exceed system resources)
        self.ims = [None] * n
        self.npy_files = [Path(f).with_suffix('.npy') for f in self.im_files]
        if cache_images:
            gb = 0  # Gigabytes of cached images
            self.im_hw0, self.im_hw = [None] * n, [None] * n
            fcn = self.cache_images_to_disk if cache_images == 'disk' else self.load_image
            results = ThreadPool(NUM_THREADS).imap(fcn, range(n))
            pbar = tqdm(enumerate(results), total=n, bar_format=BAR_FORMAT)
            for i, x in pbar:
                if cache_images == 'disk':
                    gb += self.npy_files[i].stat().st_size
                else:  # 'ram'
                    self.ims[i], self.im_hw0[i], self.im_hw[i] = x  # im, hw_orig, hw_resized = load_image(self, i)
                    gb += self.ims[i].nbytes
                pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
            pbar.close()

    def cache_labels(self, path=Path('./labels.cache'), prefix=''):
        # Cache dataset labels, check images and read shapes
        x = {}  # dict
        nm, nf, ne, nc, msgs = 0, 0, 0, 0, []  # number missing, found, empty, corrupt, messages
        desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..."
        with Pool(NUM_THREADS) as pool:
            pbar = tqdm(pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix))),
                        desc=desc, total=len(self.im_files), bar_format=BAR_FORMAT)
            for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
                nm += nm_f
                nf += nf_f
                ne += ne_f
                nc += nc_f
                if im_file:
                    x[im_file] = [lb, shape, segments]
                if msg:
                    msgs.append(msg)
                pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupt"

        pbar.close()
        if msgs:
            LOGGER.info('\n'.join(msgs))
        if nf == 0:
            LOGGER.warning(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
        x['hash'] = get_hash(self.label_files + self.im_files)
        x['results'] = nf, nm, ne, nc, len(self.im_files)
        x['msgs'] = msgs  # warnings
        x['version'] = self.cache_version  # cache version
        try:
            np.save(path, x)  # save cache for next time
            path.with_suffix('.cache.npy').rename(path)  # remove .npy suffix
            LOGGER.info(f'{prefix}New cache created: {path}')
        except Exception as e:
            LOGGER.warning(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}')  # not writeable
        return x

    def __len__(self):
        return len(self.im_files)

    # def __iter__(self):
    #     self.count = -1
    #     print('ran dataset iter')
    #     #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
    #     return self

    def __getitem__(self, index):
        index = self.indices[index]  # linear, shuffled, or image_weights

        hyp = self.hyp
        mosaic = self.mosaic and random.random() < hyp['mosaic']
        if mosaic:
            # Load mosaic
            img, labels = self.load_mosaic(index)
            shapes = None

            # MixUp augmentation
            if random.random() < hyp['mixup']:
                img, labels = mixup(img, labels, *self.load_mosaic(random.randint(0, self.n - 1)))

        else:
            # Load image
            img, (h0, w0), (h, w) = self.load_image(index)

            # Letterbox
            shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size  # final letterboxed shape
            img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
            shapes = (h0, w0), ((h / h0, w / w0), pad)  # for COCO mAP rescaling

            labels = self.labels[index].copy()
            if labels.size:  # normalized xywh to pixel xyxy format
                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])

            if self.augment:
                img, labels = random_perspective(img, labels,
                                                 degrees=hyp['degrees'],
                                                 translate=hyp['translate'],
                                                 scale=hyp['scale'],
                                                 shear=hyp['shear'],
                                                 perspective=hyp['perspective'])

        nl = len(labels)  # number of labels
        if nl:
            labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)

        if self.augment:
            # Albumentations
            img, labels = self.albumentations(img, labels)
            nl = len(labels)  # update after albumentations

            # HSV color-space
            augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])

            # Flip up-down
            if random.random() < hyp['flipud']:
                img = np.flipud(img)
                if nl:
                    labels[:, 2] = 1 - labels[:, 2]

            # Flip left-right
            if random.random() < hyp['fliplr']:
                img = np.fliplr(img)
                if nl:
                    labels[:, 1] = 1 - labels[:, 1]

            # Cutouts
            # labels = cutout(img, labels, p=0.5)
            # nl = len(labels)  # update after cutout

        labels_out = torch.zeros((nl, 6))
        if nl:
            labels_out[:, 1:] = torch.from_numpy(labels)

        # Convert
        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
        img = np.ascontiguousarray(img)

        return torch.from_numpy(img), labels_out, self.im_files[index], shapes

    def load_image(self, i):
        # Loads 1 image from dataset index 'i', returns (im, original hw, resized hw)
        im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i],
        if im is None:  # not cached in RAM
            if fn.exists():  # load npy
                im = np.load(fn)
            else:  # read image
                im = cv2.imread(f)  # BGR
                assert im is not None, f'Image Not Found {f}'
            h0, w0 = im.shape[:2]  # orig hw
            r = self.img_size / max(h0, w0)  # ratio
            if r != 1:  # if sizes are not equal
                im = cv2.resize(im,
                                (int(w0 * r), int(h0 * r)),
                                interpolation=cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA)
            return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
        else:
            return self.ims[i], self.im_hw0[i], self.im_hw[i]  # im, hw_original, hw_resized

    def cache_images_to_disk(self, i):
        # Saves an image as an *.npy file for faster loading
        f = self.npy_files[i]
        if not f.exists():
            np.save(f.as_posix(), cv2.imread(self.im_files[i]))

    def load_mosaic(self, index):
        # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
        labels4, segments4 = [], []
        s = self.img_size
        yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border)  # mosaic center x, y
        indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
        random.shuffle(indices)
        for i, index in enumerate(indices):
            # Load image
            img, _, (h, w) = self.load_image(index)

            # place img in img4
            if i == 0:  # top left
                img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
                x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
                x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
            elif i == 1:  # top right
                x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
                x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
            elif i == 2:  # bottom left
                x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
                x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
            elif i == 3:  # bottom right
                x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
                x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

            img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
            padw = x1a - x1b
            padh = y1a - y1b

            # Labels
            labels, segments = self.labels[index].copy(), self.segments[index].copy()
            if labels.size:
                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
                segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
            labels4.append(labels)
            segments4.extend(segments)

        # Concat/clip labels
        labels4 = np.concatenate(labels4, 0)
        for x in (labels4[:, 1:], *segments4):
            np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
        # img4, labels4 = replicate(img4, labels4)  # replicate

        # Augment
        img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
        img4, labels4 = random_perspective(img4, labels4, segments4,
                                           degrees=self.hyp['degrees'],
                                           translate=self.hyp['translate'],
                                           scale=self.hyp['scale'],
                                           shear=self.hyp['shear'],
                                           perspective=self.hyp['perspective'],
                                           border=self.mosaic_border)  # border to remove

        return img4, labels4

    def load_mosaic9(self, index):
        # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
        labels9, segments9 = [], []
        s = self.img_size
        indices = [index] + random.choices(self.indices, k=8)  # 8 additional image indices
        random.shuffle(indices)
        hp, wp = -1, -1  # height, width previous
        for i, index in enumerate(indices):
            # Load image
            img, _, (h, w) = self.load_image(index)

            # place img in img9
            if i == 0:  # center
                img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
                h0, w0 = h, w
                c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
            elif i == 1:  # top
                c = s, s - h, s + w, s
            elif i == 2:  # top right
                c = s + wp, s - h, s + wp + w, s
            elif i == 3:  # right
                c = s + w0, s, s + w0 + w, s + h
            elif i == 4:  # bottom right
                c = s + w0, s + hp, s + w0 + w, s + hp + h
            elif i == 5:  # bottom
                c = s + w0 - w, s + h0, s + w0, s + h0 + h
            elif i == 6:  # bottom left
                c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
            elif i == 7:  # left
                c = s - w, s + h0 - h, s, s + h0
            elif i == 8:  # top left
                c = s - w, s + h0 - hp - h, s, s + h0 - hp

            padx, pady = c[:2]
            x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords

            # Labels
            labels, segments = self.labels[index].copy(), self.segments[index].copy()
            if labels.size:
                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady)  # normalized xywh to pixel xyxy format
                segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
            labels9.append(labels)
            segments9.extend(segments)

            # Image
            img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:]  # img9[ymin:ymax, xmin:xmax]
            hp, wp = h, w  # height, width previous

        # Offset
        yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border)  # mosaic center x, y
        img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]

        # Concat/clip labels
        labels9 = np.concatenate(labels9, 0)
        labels9[:, [1, 3]] -= xc
        labels9[:, [2, 4]] -= yc
        c = np.array([xc, yc])  # centers
        segments9 = [x - c for x in segments9]

        for x in (labels9[:, 1:], *segments9):
            np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
        # img9, labels9 = replicate(img9, labels9)  # replicate

        # Augment
        img9, labels9 = random_perspective(img9, labels9, segments9,
                                           degrees=self.hyp['degrees'],
                                           translate=self.hyp['translate'],
                                           scale=self.hyp['scale'],
                                           shear=self.hyp['shear'],
                                           perspective=self.hyp['perspective'],
                                           border=self.mosaic_border)  # border to remove

        return img9, labels9

    @staticmethod
    def collate_fn(batch):
        im, label, path, shapes = zip(*batch)  # transposed
        for i, lb in enumerate(label):
            lb[:, 0] = i  # add target image index for build_targets()
        return torch.stack(im, 0), torch.cat(label, 0), path, shapes

    @staticmethod
    def collate_fn4(batch):
        img, label, path, shapes = zip(*batch)  # transposed
        n = len(shapes) // 4
        im4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]

        ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]])
        wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]])
        s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]])  # scale
        for i in range(n):  # zidane torch.zeros(16,3,720,1280)  # BCHW
            i *= 4
            if random.random() < 0.5:
                im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear', align_corners=False)[
                    0].type(img[i].type())
                lb = label[i]
            else:
                im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
                lb = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
            im4.append(im)
            label4.append(lb)

        for i, lb in enumerate(label4):
            lb[:, 0] = i  # add target image index for build_targets()

        return torch.stack(im4, 0), torch.cat(label4, 0), path4, shapes4


# Ancillary functions --------------------------------------------------------------------------------------------------
def create_folder(path='./new'):
    # Create folder
    if os.path.exists(path):
        shutil.rmtree(path)  # delete output folder
    os.makedirs(path)  # make new output folder


def flatten_recursive(path=DATASETS_DIR / 'coco128'):
    # Flatten a recursive directory by bringing all files to top level
    new_path = Path(str(path) + '_flat')
    create_folder(new_path)
    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
        shutil.copyfile(file, new_path / Path(file).name)


def extract_boxes(path=DATASETS_DIR / 'coco128'):  # from utils.datasets import *; extract_boxes()
    # Convert detection dataset into classification dataset, with one directory per class
    path = Path(path)  # images dir
    shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None  # remove existing
    files = list(path.rglob('*.*'))
    n = len(files)  # number of files
    for im_file in tqdm(files, total=n):
        if im_file.suffix[1:] in IMG_FORMATS:
            # image
            im = cv2.imread(str(im_file))[..., ::-1]  # BGR to RGB
            h, w = im.shape[:2]

            # labels
            lb_file = Path(img2label_paths([str(im_file)])[0])
            if Path(lb_file).exists():
                with open(lb_file) as f:
                    lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels

                for j, x in enumerate(lb):
                    c = int(x[0])  # class
                    f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg'  # new filename
                    if not f.parent.is_dir():
                        f.parent.mkdir(parents=True)

                    b = x[1:] * [w, h, w, h]  # box
                    # b[2:] = b[2:].max()  # rectangle to square
                    b[2:] = b[2:] * 1.2 + 3  # pad
                    b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)

                    b[[0, 2]] = np.clip(b[[0, 2]], 0, w)  # clip boxes outside of image
                    b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
                    assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'


def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
    """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
    Usage: from utils.datasets import *; autosplit()
    Arguments
        path:            Path to images directory
        weights:         Train, val, test weights (list, tuple)
        annotated_only:  Only use images with an annotated txt file
    """
    path = Path(path)  # images dir
    files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS)  # image files only
    n = len(files)  # number of files
    random.seed(0)  # for reproducibility
    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split

    txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt']  # 3 txt files
    [(path.parent / x).unlink(missing_ok=True) for x in txt]  # remove existing

    print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
    for i, img in tqdm(zip(indices, files), total=n):
        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
            with open(path.parent / txt[i], 'a') as f:
                f.write('./' + img.relative_to(path.parent).as_posix() + '\n')  # add image to txt file


def verify_image_label(args):
    # Verify one image-label pair
    im_file, lb_file, prefix = args
    nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', []  # number (missing, found, empty, corrupt), message, segments
    try:
        # verify images
        im = Image.open(im_file)
        im.verify()  # PIL verify
        shape = exif_size(im)  # image size
        assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
        assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}'
        if im.format.lower() in ('jpg', 'jpeg'):
            with open(im_file, 'rb') as f:
                f.seek(-2, 2)
                if f.read() != b'\xff\xd9':  # corrupt JPEG
                    ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100)
                    msg = f'{prefix}WARNING: {im_file}: corrupt JPEG restored and saved'

        # verify labels
        if os.path.isfile(lb_file):
            nf = 1  # label found
            with open(lb_file) as f:
                lb = [x.split() for x in f.read().strip().splitlines() if len(x)]
                if any(len(x) > 6 for x in lb):  # is segment
                    classes = np.array([x[0] for x in lb], dtype=np.float32)
                    segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb]  # (cls, xy1...)
                    lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1)  # (cls, xywh)
                lb = np.array(lb, dtype=np.float32)
            nl = len(lb)
            if nl:
                assert lb.shape[1] == 5, f'labels require 5 columns, {lb.shape[1]} columns detected'
                assert (lb >= 0).all(), f'negative label values {lb[lb < 0]}'
                assert (lb[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {lb[:, 1:][lb[:, 1:] > 1]}'
                _, i = np.unique(lb, axis=0, return_index=True)
                if len(i) < nl:  # duplicate row check
                    lb = lb[i]  # remove duplicates
                    if segments:
                        segments = segments[i]
                    msg = f'{prefix}WARNING: {im_file}: {nl - len(i)} duplicate labels removed'
            else:
                ne = 1  # label empty
                lb = np.zeros((0, 5), dtype=np.float32)
        else:
            nm = 1  # label missing
            lb = np.zeros((0, 5), dtype=np.float32)
        return im_file, lb, shape, segments, nm, nf, ne, nc, msg
    except Exception as e:
        nc = 1
        msg = f'{prefix}WARNING: {im_file}: ignoring corrupt image/label: {e}'
        return [None, None, None, None, nm, nf, ne, nc, msg]


def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False):
    """ Return dataset statistics dictionary with images and instances counts per split per class
    To run in parent directory: export PYTHONPATH="$PWD/yolov5"
    Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True)
    Usage2: from utils.datasets import *; dataset_stats('path/to/coco128_with_yaml.zip')
    Arguments
        path:           Path to data.yaml or data.zip (with data.yaml inside data.zip)
        autodownload:   Attempt to download dataset if not found locally
        verbose:        Print stats dictionary
    """

    def round_labels(labels):
        # Update labels to integer class and 6 decimal place floats
        return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels]

    def unzip(path):
        # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
        if str(path).endswith('.zip'):  # path is data.zip
            assert Path(path).is_file(), f'Error unzipping {path}, file not found'
            ZipFile(path).extractall(path=path.parent)  # unzip
            dir = path.with_suffix('')  # dataset directory == zip name
            return True, str(dir), next(dir.rglob('*.yaml'))  # zipped, data_dir, yaml_path
        else:  # path is data.yaml
            return False, None, path

    def hub_ops(f, max_dim=1920):
        # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing
        f_new = im_dir / Path(f).name  # dataset-hub image filename
        try:  # use PIL
            im = Image.open(f)
            r = max_dim / max(im.height, im.width)  # ratio
            if r < 1.0:  # image too large
                im = im.resize((int(im.width * r), int(im.height * r)))
            im.save(f_new, 'JPEG', quality=75, optimize=True)  # save
        except Exception as e:  # use OpenCV
            print(f'WARNING: HUB ops PIL failure {f}: {e}')
            im = cv2.imread(f)
            im_height, im_width = im.shape[:2]
            r = max_dim / max(im_height, im_width)  # ratio
            if r < 1.0:  # image too large
                im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA)
            cv2.imwrite(str(f_new), im)

    zipped, data_dir, yaml_path = unzip(Path(path))
    with open(check_yaml(yaml_path), errors='ignore') as f:
        data = yaml.safe_load(f)  # data dict
        if zipped:
            data['path'] = data_dir  # TODO: should this be dir.resolve()?
    check_dataset(data, autodownload)  # download dataset if missing
    hub_dir = Path(data['path'] + ('-hub' if hub else ''))
    stats = {'nc': data['nc'], 'names': data['names']}  # statistics dictionary
    for split in 'train', 'val', 'test':
        if data.get(split) is None:
            stats[split] = None  # i.e. no test set
            continue
        x = []
        dataset = LoadImagesAndLabels(data[split])  # load dataset
        for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'):
            x.append(np.bincount(label[:, 0].astype(int), minlength=data['nc']))
        x = np.array(x)  # shape(128x80)
        stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
                        'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
                                        'per_class': (x > 0).sum(0).tolist()},
                        'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
                                   zip(dataset.im_files, dataset.labels)]}

        if hub:
            im_dir = hub_dir / 'images'
            im_dir.mkdir(parents=True, exist_ok=True)
            for _ in tqdm(ThreadPool(NUM_THREADS).imap(hub_ops, dataset.im_files), total=dataset.n, desc='HUB Ops'):
                pass

    # Profile
    stats_path = hub_dir / 'stats.json'
    if profile:
        for _ in range(1):
            file = stats_path.with_suffix('.npy')
            t1 = time.time()
            np.save(file, stats)
            t2 = time.time()
            x = np.load(file, allow_pickle=True)
            print(f'stats.npy times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')

            file = stats_path.with_suffix('.json')
            t1 = time.time()
            with open(file, 'w') as f:
                json.dump(stats, f)  # save stats *.json
            t2 = time.time()
            with open(file) as f:
                x = json.load(f)  # load hyps dict
            print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')

    # Save, print and return
    if hub:
        print(f'Saving {stats_path.resolve()}...')
        with open(stats_path, 'w') as f:
            json.dump(stats, f)  # save stats.json
    if verbose:
        print(json.dumps(stats, indent=2, sort_keys=False))
    return stats