-
Notifications
You must be signed in to change notification settings - Fork 52
/
face_datasets.py
776 lines (646 loc) · 35.6 KB
/
face_datasets.py
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
import glob
import logging
import math
import os
import random
import shutil
import time
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from threading import Thread
import cv2
import numpy as np
import torch
from PIL import Image, ExifTags
from torch.utils.data import Dataset
from tqdm import tqdm
from utils.general import xyxy2xywh, xywh2xyxy, clean_str
from utils.torch_utils import torch_distributed_zero_first
# Parameters
help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng'] # acceptable image suffixes
vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes
logger = logging.getLogger(__name__)
# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
if ExifTags.TAGS[orientation] == 'Orientation':
break
def get_hash(files):
# Returns a single hash value of a list of files
return sum(os.path.getsize(f) for f in files if os.path.isfile(f))
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 [x.replace(sa, sb, 1).replace('.' + x.split('.')[-1], '.txt') for x in img_paths]
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:
pass
return s
class LoadFaceImagesAndLabels(Dataset): # for training/testing
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, rank=-1):
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
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)
elif p.is_file(): # file
with open(p, 'r') 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
else:
raise Exception('%s does not exist' % p)
self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats])
assert self.img_files, 'No images found'
except Exception as e:
raise Exception('Error loading data from %s: %s\nSee %s' % (path, e, help_url))
# Check cache
self.label_files = img2label_paths(self.img_files) # labels
cache_path = Path(self.label_files[0]).parent.with_suffix('.cache') # cached labels
if cache_path.is_file():
cache = torch.load(cache_path) # load
if cache['hash'] != get_hash(self.label_files + self.img_files) or 'results' not in cache: # changed
cache = self.cache_labels(cache_path) # re-cache
else:
cache = self.cache_labels(cache_path) # cache
# Display cache
[nf, nm, ne, nc, n] = cache.pop('results') # found, missing, empty, corrupted, total
desc = f"Scanning '{cache_path}' for images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
tqdm(None, desc=desc, total=n, initial=n)
assert nf > 0 or not augment, f'No labels found in {cache_path}. Can not train without labels. See {help_url}'
# Read cache
cache.pop('hash') # remove hash
labels, shapes = zip(*cache.values())
self.labels = list(labels)
self.shapes = np.array(shapes, dtype=np.float64)
self.img_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
if single_cls:
for x in self.labels:
x[:, 0] = 0
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)
# Rectangular Training
if self.rect:
# Sort by aspect ratio
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio
irect = ar.argsort()
self.img_files = [self.img_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 memory for faster training (WARNING: large datasets may exceed system RAM)
self.imgs = [None] * n
if cache_images:
gb = 0 # Gigabytes of cached images
self.img_hw0, self.img_hw = [None] * n, [None] * n
results = ThreadPool(8).imap(lambda x: load_image(*x), zip(repeat(self), range(n))) # 8 threads
pbar = tqdm(enumerate(results), total=n)
for i, x in pbar:
self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # img, hw_original, hw_resized = load_image(self, i)
gb += self.imgs[i].nbytes
pbar.desc = 'Caching images (%.1fGB)' % (gb / 1E9)
def cache_labels(self, path=Path('./labels.cache')):
# Cache dataset labels, check images and read shapes
x = {} # dict
nm, nf, ne, nc = 0, 0, 0, 0 # number missing, found, empty, duplicate
pbar = tqdm(zip(self.img_files, self.label_files), desc='Scanning images', total=len(self.img_files))
for i, (im_file, lb_file) in enumerate(pbar):
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), 'image size <10 pixels'
# verify labels
if os.path.isfile(lb_file):
nf += 1 # label found
with open(lb_file, 'r') as f:
l = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels
if len(l):
assert l.shape[1] == 15, 'labels require 15 columns each'
assert (l >= -1).all(), 'negative labels'
assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels'
assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels'
else:
ne += 1 # label empty
l = np.zeros((0, 15), dtype=np.float32)
else:
nm += 1 # label missing
l = np.zeros((0, 15), dtype=np.float32)
x[im_file] = [l, shape]
except Exception as e:
nc += 1
print('WARNING: Ignoring corrupted image and/or label %s: %s' % (im_file, e))
pbar.desc = f"Scanning '{path.parent / path.stem}' for images and labels... " \
f"{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
if nf == 0:
print(f'WARNING: No labels found in {path}. See {help_url}')
x['hash'] = get_hash(self.label_files + self.img_files)
x['results'] = [nf, nm, ne, nc, i + 1]
torch.save(x, path) # save for next time
logging.info(f"New cache created: {path}")
return x
def __len__(self):
return len(self.img_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 = load_mosaic_face(self, index)
shapes = None
# MixUp https://arxiv.org/pdf/1710.09412.pdf
if random.random() < hyp['mixup']:
img2, labels2 = load_mosaic_face(self, random.randint(0, self.n - 1))
r = np.random.beta(8.0, 8.0) # mixup ratio, alpha=beta=8.0
img = (img * r + img2 * (1 - r)).astype(np.uint8)
labels = np.concatenate((labels, labels2), 0)
else:
# Load image
img, (h0, w0), (h, w) = load_image(self, 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
# Load labels
labels = []
x = self.labels[index]
if x.size > 0:
# Normalized xywh to pixel xyxy format
labels = x.copy()
labels[:, 1] = ratio[0] * w * (x[:, 1] - x[:, 3] / 2) + pad[0] # pad width
labels[:, 2] = ratio[1] * h * (x[:, 2] - x[:, 4] / 2) + pad[1] # pad height
labels[:, 3] = ratio[0] * w * (x[:, 1] + x[:, 3] / 2) + pad[0]
labels[:, 4] = ratio[1] * h * (x[:, 2] + x[:, 4] / 2) + pad[1]
#labels[:, 5] = ratio[0] * w * x[:, 5] + pad[0] # pad width
labels[:, 5] = np.array(x[:, 5] > 0, dtype=np.int32) * (ratio[0] * w * x[:, 5] + pad[0]) + (
np.array(x[:, 5] > 0, dtype=np.int32) - 1)
labels[:, 6] = np.array(x[:, 6] > 0, dtype=np.int32) * (ratio[1] * h * x[:, 6] + pad[1]) + (
np.array(x[:, 6] > 0, dtype=np.int32) - 1)
labels[:, 7] = np.array(x[:, 7] > 0, dtype=np.int32) * (ratio[0] * w * x[:, 7] + pad[0]) + (
np.array(x[:, 7] > 0, dtype=np.int32) - 1)
labels[:, 8] = np.array(x[:, 8] > 0, dtype=np.int32) * (ratio[1] * h * x[:, 8] + pad[1]) + (
np.array(x[:, 8] > 0, dtype=np.int32) - 1)
labels[:, 9] = np.array(x[:, 5] > 0, dtype=np.int32) * (ratio[0] * w * x[:, 9] + pad[0]) + (
np.array(x[:, 9] > 0, dtype=np.int32) - 1)
labels[:, 10] = np.array(x[:, 5] > 0, dtype=np.int32) * (ratio[1] * h * x[:, 10] + pad[1]) + (
np.array(x[:, 10] > 0, dtype=np.int32) - 1)
labels[:, 11] = np.array(x[:, 11] > 0, dtype=np.int32) * (ratio[0] * w * x[:, 11] + pad[0]) + (
np.array(x[:, 11] > 0, dtype=np.int32) - 1)
labels[:, 12] = np.array(x[:, 12] > 0, dtype=np.int32) * (ratio[1] * h * x[:, 12] + pad[1]) + (
np.array(x[:, 12] > 0, dtype=np.int32) - 1)
labels[:, 13] = np.array(x[:, 13] > 0, dtype=np.int32) * (ratio[0] * w * x[:, 13] + pad[0]) + (
np.array(x[:, 13] > 0, dtype=np.int32) - 1)
labels[:, 14] = np.array(x[:, 14] > 0, dtype=np.int32) * (ratio[1] * h * x[:, 14] + pad[1]) + (
np.array(x[:, 14] > 0, dtype=np.int32) - 1)
if self.augment:
# Augment imagespace
if not mosaic:
img, labels = random_perspective(img, labels,
degrees=hyp['degrees'],
translate=hyp['translate'],
scale=hyp['scale'],
shear=hyp['shear'],
perspective=hyp['perspective'])
# Augment colorspace
augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
# Apply cutouts
# if random.random() < 0.9:
# labels = cutout(img, labels)
nL = len(labels) # number of labels
if nL:
labels[:, 1:5] = xyxy2xywh(labels[:, 1:5]) # convert xyxy to xywh
labels[:, [2, 4]] /= img.shape[0] # normalized height 0-1
labels[:, [1, 3]] /= img.shape[1] # normalized width 0-1
labels[:, [5, 7, 9, 11, 13]] /= img.shape[1] # normalized landmark x 0-1
labels[:, [5, 7, 9, 11, 13]] = np.where(labels[:, [5, 7, 9, 11, 13]] < 0, -1, labels[:, [5, 7, 9, 11, 13]])
labels[:, [6, 8, 10, 12, 14]] /= img.shape[0] # normalized landmark y 0-1
labels[:, [6, 8, 10, 12, 14]] = np.where(labels[:, [6, 8, 10, 12, 14]] < 0, -1, labels[:, [6, 8, 10, 12, 14]])
if self.augment:
# flip up-down
if random.random() < hyp['flipud']:
img = np.flipud(img)
if nL:
labels[:, 2] = 1 - labels[:, 2]
labels[:, 6] = np.where(labels[:,6] < 0, -1, 1 - labels[:, 6])
labels[:, 8] = np.where(labels[:, 8] < 0, -1, 1 - labels[:, 8])
labels[:, 10] = np.where(labels[:, 10] < 0, -1, 1 - labels[:, 10])
labels[:, 12] = np.where(labels[:, 12] < 0, -1, 1 - labels[:, 12])
labels[:, 14] = np.where(labels[:, 14] < 0, -1, 1 - labels[:, 14])
# flip left-right
if random.random() < hyp['fliplr']:
img = np.fliplr(img)
if nL:
labels[:, 1] = 1 - labels[:, 1]
labels[:, 5] = np.where(labels[:, 5] < 0, -1, 1 - labels[:, 5])
labels[:, 7] = np.where(labels[:, 7] < 0, -1, 1 - labels[:, 7])
labels[:, 9] = np.where(labels[:, 9] < 0, -1, 1 - labels[:, 9])
labels[:, 11] = np.where(labels[:, 11] < 0, -1, 1 - labels[:, 11])
labels[:, 13] = np.where(labels[:, 13] < 0, -1, 1 - labels[:, 13])
#左右镜像的时候,左眼、右眼, 左嘴角、右嘴角无法区分, 应该交换位置,便于网络学习
eye_left = np.copy(labels[:, [5, 6]])
mouth_left = np.copy(labels[:, [11, 12]])
labels[:, [5, 6]] = labels[:, [7, 8]]
labels[:, [7, 8]] = eye_left
labels[:, [11, 12]] = labels[:, [13, 14]]
labels[:, [13, 14]] = mouth_left
labels_out = torch.zeros((nL, 16))
if nL:
labels_out[:, 1:] = torch.from_numpy(labels)
#showlabels(img, labels[:, 1:5], labels[:, 5:15])
# Convert
img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
img = np.ascontiguousarray(img)
#print(index, ' --- labels_out: ', labels_out)
#if nL:
#print( ' : landmarks : ', torch.max(labels_out[:, 5:15]), ' --- ', torch.min(labels_out[:, 5:15]))
return torch.from_numpy(img), labels_out, self.img_files[index], shapes
@staticmethod
def collate_fn(batch):
img, label, path, shapes = zip(*batch) # transposed
for i, l in enumerate(label):
l[:, 0] = i # add target image index for build_targets()
return torch.stack(img, 0), torch.cat(label, 0), path, shapes
def showlabels(img, boxs, landmarks):
for box in boxs:
x,y,w,h = box[0] * img.shape[1], box[1] * img.shape[0], box[2] * img.shape[1], box[3] * img.shape[0]
#cv2.rectangle(image, (x,y), (x+w,y+h), (0,255,0), 2)
cv2.rectangle(img, (int(x - w/2), int(y - h/2)), (int(x + w/2), int(y + h/2)), (0, 255, 0), 2)
for landmark in landmarks:
#cv2.circle(img,(60,60),30,(0,0,255))
for i in range(5):
cv2.circle(img, (int(landmark[2*i] * img.shape[1]), int(landmark[2*i+1]*img.shape[0])), 3 ,(0,0,255), -1)
cv2.imshow('test', img)
cv2.waitKey(0)
def load_mosaic_face(self, index):
# loads images in a mosaic
labels4 = []
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] + [self.indices[random.randint(0, self.n - 1)] for _ in range(3)] # 3 additional image indices
for i, index in enumerate(indices):
# Load image
img, _, (h, w) = load_image(self, 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
x = self.labels[index]
labels = x.copy()
if x.size > 0: # Normalized xywh to pixel xyxy format
#box, x1,y1,x2,y2
labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
#10 landmarks
labels[:, 5] = np.array(x[:, 5] > 0, dtype=np.int32) * (w * x[:, 5] + padw) + (np.array(x[:, 5] > 0, dtype=np.int32) - 1)
labels[:, 6] = np.array(x[:, 6] > 0, dtype=np.int32) * (h * x[:, 6] + padh) + (np.array(x[:, 6] > 0, dtype=np.int32) - 1)
labels[:, 7] = np.array(x[:, 7] > 0, dtype=np.int32) * (w * x[:, 7] + padw) + (np.array(x[:, 7] > 0, dtype=np.int32) - 1)
labels[:, 8] = np.array(x[:, 8] > 0, dtype=np.int32) * (h * x[:, 8] + padh) + (np.array(x[:, 8] > 0, dtype=np.int32) - 1)
labels[:, 9] = np.array(x[:, 9] > 0, dtype=np.int32) * (w * x[:, 9] + padw) + (np.array(x[:, 9] > 0, dtype=np.int32) - 1)
labels[:, 10] = np.array(x[:, 10] > 0, dtype=np.int32) * (h * x[:, 10] + padh) + (np.array(x[:, 10] > 0, dtype=np.int32) - 1)
labels[:, 11] = np.array(x[:, 11] > 0, dtype=np.int32) * (w * x[:, 11] + padw) + (np.array(x[:, 11] > 0, dtype=np.int32) - 1)
labels[:, 12] = np.array(x[:, 12] > 0, dtype=np.int32) * (h * x[:, 12] + padh) + (np.array(x[:, 12] > 0, dtype=np.int32) - 1)
labels[:, 13] = np.array(x[:, 13] > 0, dtype=np.int32) * (w * x[:, 13] + padw) + (np.array(x[:, 13] > 0, dtype=np.int32) - 1)
labels[:, 14] = np.array(x[:, 14] > 0, dtype=np.int32) * (h * x[:, 14] + padh) + (np.array(x[:, 14] > 0, dtype=np.int32) - 1)
labels4.append(labels)
# Concat/clip labels
if len(labels4):
labels4 = np.concatenate(labels4, 0)
np.clip(labels4[:, 1:5], 0, 2 * s, out=labels4[:, 1:5]) # use with random_perspective
# img4, labels4 = replicate(img4, labels4) # replicate
#landmarks
labels4[:, 5:] = np.where(labels4[:, 5:] < 0, -1, labels4[:, 5:])
labels4[:, 5:] = np.where(labels4[:, 5:] > 2 * s, -1, labels4[:, 5:])
labels4[:, 5] = np.where(labels4[:, 6] == -1, -1, labels4[:, 5])
labels4[:, 6] = np.where(labels4[:, 5] == -1, -1, labels4[:, 6])
labels4[:, 7] = np.where(labels4[:, 8] == -1, -1, labels4[:, 7])
labels4[:, 8] = np.where(labels4[:, 7] == -1, -1, labels4[:, 8])
labels4[:, 9] = np.where(labels4[:, 10] == -1, -1, labels4[:, 9])
labels4[:, 10] = np.where(labels4[:, 9] == -1, -1, labels4[:, 10])
labels4[:, 11] = np.where(labels4[:, 12] == -1, -1, labels4[:, 11])
labels4[:, 12] = np.where(labels4[:, 11] == -1, -1, labels4[:, 12])
labels4[:, 13] = np.where(labels4[:, 14] == -1, -1, labels4[:, 13])
labels4[:, 14] = np.where(labels4[:, 13] == -1, -1, labels4[:, 14])
# Augment
img4, labels4 = random_perspective(img4, labels4,
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
# Ancillary functions --------------------------------------------------------------------------------------------------
def load_image(self, index):
# loads 1 image from dataset, returns img, original hw, resized hw
img = self.imgs[index]
if img is None: # not cached
path = self.img_files[index]
img = cv2.imread(path) # BGR
assert img is not None, 'Image Not Found ' + path
h0, w0 = img.shape[:2] # orig hw
r = self.img_size / max(h0, w0) # resize image to img_size
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR
img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp)
return img, (h0, w0), img.shape[:2] # img, hw_original, hw_resized
else:
return self.imgs[index], self.img_hw0[index], self.img_hw[index] # img, hw_original, hw_resized
def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5):
r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
dtype = img.dtype # uint8
x = np.arange(0, 256, dtype=np.int16)
lut_hue = ((x * r[0]) % 180).astype(dtype)
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))).astype(dtype)
cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img) # no return needed
# Histogram equalization
# if random.random() < 0.2:
# for i in range(3):
# img[:, :, i] = cv2.equalizeHist(img[:, :, i])
def replicate(img, labels):
# Replicate labels
h, w = img.shape[:2]
boxes = labels[:, 1:].astype(int)
x1, y1, x2, y2 = boxes.T
s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels)
for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices
x1b, y1b, x2b, y2b = boxes[i]
bh, bw = y2b - y1b, x2b - x1b
yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y
x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
img[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
return img, labels
def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
# Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
shape = img.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better test mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, 32), np.mod(dh, 32) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return img, ratio, (dw, dh)
def random_perspective(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, border=(0, 0)):
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
# targets = [cls, xyxy]
height = img.shape[0] + border[0] * 2 # shape(h,w,c)
width = img.shape[1] + border[1] * 2
# Center
C = np.eye(3)
C[0, 2] = -img.shape[1] / 2 # x translation (pixels)
C[1, 2] = -img.shape[0] / 2 # y translation (pixels)
# Perspective
P = np.eye(3)
P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
# Rotation and Scale
R = np.eye(3)
a = random.uniform(-degrees, degrees)
# a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
s = random.uniform(1 - scale, 1 + scale)
# s = 2 ** random.uniform(-scale, scale)
R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
# Shear
S = np.eye(3)
S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
# Translation
T = np.eye(3)
T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels)
T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels)
# Combined rotation matrix
M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
if perspective:
img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114))
else: # affine
img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
# Visualize
# import matplotlib.pyplot as plt
# ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
# ax[0].imshow(img[:, :, ::-1]) # base
# ax[1].imshow(img2[:, :, ::-1]) # warped
# Transform label coordinates
n = len(targets)
if n:
# warp points
#xy = np.ones((n * 4, 3))
xy = np.ones((n * 9, 3))
xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14]].reshape(n * 9, 2) # x1y1, x2y2, x1y2, x2y1
xy = xy @ M.T # transform
if perspective:
xy = (xy[:, :2] / xy[:, 2:3]).reshape(n, 18) # rescale
else: # affine
xy = xy[:, :2].reshape(n, 18)
# create new boxes
x = xy[:, [0, 2, 4, 6]]
y = xy[:, [1, 3, 5, 7]]
landmarks = xy[:, [8, 9, 10, 11, 12, 13, 14, 15, 16, 17]]
mask = np.array(targets[:, 5:] > 0, dtype=np.int32)
landmarks = landmarks * mask
landmarks = landmarks + mask - 1
landmarks = np.where(landmarks < 0, -1, landmarks)
landmarks[:, [0, 2, 4, 6, 8]] = np.where(landmarks[:, [0, 2, 4, 6, 8]] > width, -1, landmarks[:, [0, 2, 4, 6, 8]])
landmarks[:, [1, 3, 5, 7, 9]] = np.where(landmarks[:, [1, 3, 5, 7, 9]] > height, -1,landmarks[:, [1, 3, 5, 7, 9]])
landmarks[:, 0] = np.where(landmarks[:, 1] == -1, -1, landmarks[:, 0])
landmarks[:, 1] = np.where(landmarks[:, 0] == -1, -1, landmarks[:, 1])
landmarks[:, 2] = np.where(landmarks[:, 3] == -1, -1, landmarks[:, 2])
landmarks[:, 3] = np.where(landmarks[:, 2] == -1, -1, landmarks[:, 3])
landmarks[:, 4] = np.where(landmarks[:, 5] == -1, -1, landmarks[:, 4])
landmarks[:, 5] = np.where(landmarks[:, 4] == -1, -1, landmarks[:, 5])
landmarks[:, 6] = np.where(landmarks[:, 7] == -1, -1, landmarks[:, 6])
landmarks[:, 7] = np.where(landmarks[:, 6] == -1, -1, landmarks[:, 7])
landmarks[:, 8] = np.where(landmarks[:, 9] == -1, -1, landmarks[:, 8])
landmarks[:, 9] = np.where(landmarks[:, 8] == -1, -1, landmarks[:, 9])
targets[:,5:] = landmarks
xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
# # apply angle-based reduction of bounding boxes
# radians = a * math.pi / 180
# reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5
# x = (xy[:, 2] + xy[:, 0]) / 2
# y = (xy[:, 3] + xy[:, 1]) / 2
# w = (xy[:, 2] - xy[:, 0]) * reduction
# h = (xy[:, 3] - xy[:, 1]) * reduction
# xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T
# clip boxes
xy[:, [0, 2]] = xy[:, [0, 2]].clip(0, width)
xy[:, [1, 3]] = xy[:, [1, 3]].clip(0, height)
# filter candidates
i = box_candidates(box1=targets[:, 1:5].T * s, box2=xy.T)
targets = targets[i]
targets[:, 1:5] = xy[i]
return img, targets
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1): # box1(4,n), box2(4,n)
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
ar = np.maximum(w2 / (h2 + 1e-16), h2 / (w2 + 1e-16)) # aspect ratio
return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + 1e-16) > area_thr) & (ar < ar_thr) # candidates
def cutout(image, labels):
# Applies image cutout augmentation https://arxiv.org/abs/1708.04552
h, w = image.shape[:2]
def bbox_ioa(box1, box2):
# Returns the intersection over box2 area given box1, box2. box1 is 4, box2 is nx4. boxes are x1y1x2y2
box2 = box2.transpose()
# Get the coordinates of bounding boxes
b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
# Intersection area
inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
(np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)
# box2 area
box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + 1e-16
# Intersection over box2 area
return inter_area / box2_area
# create random masks
scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction
for s in scales:
mask_h = random.randint(1, int(h * s))
mask_w = random.randint(1, int(w * s))
# box
xmin = max(0, random.randint(0, w) - mask_w // 2)
ymin = max(0, random.randint(0, h) - mask_h // 2)
xmax = min(w, xmin + mask_w)
ymax = min(h, ymin + mask_h)
# apply random color mask
image[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
# return unobscured labels
if len(labels) and s > 0.03:
box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
labels = labels[ioa < 0.60] # remove >60% obscured labels
return labels
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='../coco128'):
# Flatten a recursive directory by bringing all files to top level
new_path = Path(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='../coco128/'): # from utils.datasets import *; extract_boxes('../coco128')
# 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, 'r') 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='../coco128', weights=(0.9, 0.1, 0.0)): # from utils.datasets import *; autosplit('../coco128')
""" Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
# Arguments
path: Path to images directory
weights: Train, val, test weights (list)
"""
path = Path(path) # images dir
files = list(path.rglob('*.*'))
n = len(files) # number of files
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 / x).unlink() for x in txt if (path / x).exists()] # remove existing
for i, img in tqdm(zip(indices, files), total=n):
if img.suffix[1:] in img_formats:
with open(path / txt[i], 'a') as f:
f.write(str(img) + '\n') # add image to txt file