/
data.html
2072 lines (1879 loc) · 91.6 KB
/
data.html
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
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
<meta name="generator" content="pdoc 0.9.2" />
<title>ktrain.vision.data API documentation</title>
<meta name="description" content="" />
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/styles/github.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/highlight.min.js" integrity="sha256-Uv3H6lx7dJmRfRvH8TH6kJD1TSK1aFcwgx+mdg3epi8=" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>ktrain.vision.data</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">from ..imports import *
from .. import utils as U
from .preprocessor import ImagePreprocessor
def show_image(img_path):
"""
```
Given file path to image, show it in Jupyter notebook
```
"""
if not os.path.isfile(img_path):
raise ValueError('%s is not valid file' % (img_path))
img = plt.imread(img_path)
out = plt.imshow(img)
return out
def show_random_images(img_folder, n=4, rows=1):
"""
```
display random images from a img_folder
```
"""
fnames = []
for ext in ('*.gif', '*.png', '*.jpg'):
fnames.extend(glob.glob(os.path.join(img_folder, ext)))
ims = []
for i in range(n):
img_path = random.choice(fnames)
img = image.load_img(img_path)
x = image.img_to_array(img)
x = x/255.
ims.append(x)
U.plots(ims, rows=rows)
return
def preview_data_aug(img_path, data_aug, rows=1, n=4):
"""
```
Preview data augmentation (ImageDatagenerator)
on a supplied image.
```
"""
if type(img_path) != type('') or not os.path.isfile(img_path):
raise ValueError('img_path must be valid file path to image')
idg = copy.copy(data_aug)
idg.featurewise_center = False
idg.featurewise_std_normalization = False
idg.samplewise_center = False
idg.samplewise_std_normalization = False
idg.rescale = None
idg.zca_whitening = False
idg.preprocessing_function = None
img = image.load_img(img_path)
x = image.img_to_array(img)
x = x/255.
x = x.reshape((1,) + x.shape)
i = 0
ims = []
for batch in idg.flow(x, batch_size=1):
ims.append(np.squeeze(batch))
i += 1
if i >= n: break
U.plots(ims, rows=rows)
return
def preview_data_aug_OLD(img_path, data_aug, n=4):
"""
```
Preview data augmentation (ImageDatagenerator)
on a supplied image.
```
"""
if type(img_path) != type('') or not os.path.isfile(img_path):
raise ValueError('img_path must be valid file path to image')
idg = copy.copy(data_aug)
idg.featurewise_center = False
idg.featurewise_std_normalization = False
idg.samplewise_center = False
idg.samplewise_std_normalization = False
idg.rescale = None
idg.zca_whitening = False
idg.preprocessing_function = None
img = image.load_img(img_path)
x = image.img_to_array(img)
x = x/255.
x = x.reshape((1,) + x.shape)
i = 0
for batch in idg.flow(x, batch_size=1):
plt.figure()
plt.imshow(np.squeeze(batch))
i += 1
if i >= n: break
return
def get_data_aug(
rotation_range=40,
zoom_range=0.2,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=False,
vertical_flip=False,
featurewise_center=True,
featurewise_std_normalization=True,
samplewise_center=False,
samplewise_std_normalization=False,
rescale=None,
**kwargs):
"""
```
This function is simply a wrapper around ImageDataGenerator
with some reasonable defaults for data augmentation.
Returns the default image_data_generator to support
data augmentation and data normalization.
Parameters can be adjusted by caller.
Note that the ktrain.vision.model.image_classifier
function may adjust these as needed.
```
"""
data_aug = image.ImageDataGenerator(
rotation_range=rotation_range,
zoom_range=zoom_range,
width_shift_range=width_shift_range,
height_shift_range=height_shift_range,
horizontal_flip=horizontal_flip,
vertical_flip=vertical_flip,
featurewise_center=featurewise_center,
featurewise_std_normalization=featurewise_std_normalization,
samplewise_center=samplewise_center,
samplewise_std_normalization=samplewise_std_normalization,
rescale=rescale,
**kwargs)
return data_aug
def get_test_datagen(data_aug=None):
if data_aug:
featurewise_center = data_aug.featurewise_center
featurewise_std_normalization = data_aug.featurewise_std_normalization
samplewise_center = data_aug.samplewise_center
samplewise_std_normalization = data_aug.samplewise_std_normalization
rescale = data_aug.rescale
zca_whitening = data_aug.zca_whitening
test_datagen = image.ImageDataGenerator(
rescale=rescale,
featurewise_center=featurewise_center,
samplewise_center=samplewise_center,
featurewise_std_normalization=featurewise_std_normalization,
samplewise_std_normalization=samplewise_std_normalization,
zca_whitening=zca_whitening)
else:
test_datagen = image.ImageDataGenerator()
return test_datagen
def process_datagen(data_aug, train_array=None, train_directory=None,
target_size=None,
color_mode='rgb',
flat_dir=False):
# set generators for train and test
if data_aug is not None:
train_datagen = data_aug
test_datagen = get_test_datagen(data_aug=data_aug)
else:
train_datagen = get_test_datagen()
test_datagen = get_test_datagen()
# compute statistics for normalization
fit_datagens(train_datagen, test_datagen,
train_array=train_array,
train_directory=train_directory,
target_size=target_size,
color_mode=color_mode, flat_dir=flat_dir)
return (train_datagen, test_datagen)
def fit_datagens(train_datagen, test_datagen,
train_array=None, train_directory=None,
target_size=None,
color_mode='rgb', flat_dir=False):
"""
```
computes stats of images for normalization
```
"""
if not datagen_needs_fit(train_datagen): return
if bool(train_array is not None) == bool(train_directory):
raise ValueError('only one of train_array or train_directory is required.')
if train_array is not None:
train_datagen.fit(train_array)
test_datagen.fit(train_array)
else:
if target_size is None:
raise ValueError('target_size is required when train_directory is supplied')
fit_samples = sample_image_folder(train_directory, target_size,
color_mode=color_mode, flat_dir=flat_dir)
train_datagen.fit(fit_samples)
test_datagen.fit(fit_samples)
return
def datagen_needs_fit(datagen):
if datagen.featurewise_center or datagen.featurewise_std_normalization or \
datagen.zca_whitening:
return True
else:
return False
def sample_image_folder(train_directory,
target_size,
color_mode='rgb', flat_dir=False):
# adjust train_directory
classes = None
if flat_dir and train_directory is not None:
folder = train_directory
if folder[-1] != os.sep: folder += os.sep
parent = os.path.dirname(os.path.dirname(folder))
folder_name = os.path.basename(os.path.dirname(folder))
train_directory = parent
classes = [folder_name]
# sample images
batch_size = 100
img_gen = image.ImageDataGenerator()
batches = img_gen.flow_from_directory(
directory=train_directory,
classes=classes,
target_size=target_size,
batch_size=batch_size,
color_mode=color_mode,
shuffle=True)
the_shape = batches[0][0].shape
sample_size = the_shape[0]
if K.image_data_format() == 'channels_first':
num_channels = the_shape[1]
else:
num_channels = the_shape[-1]
imgs, labels = next(batches)
return imgs
def detect_color_mode(train_directory,
target_size=(32,32)):
try:
fname = glob.glob(os.path.join(train_directory, '**/*'))[0]
img = Image.open(fname).resize(target_size)
num_channels = len(img.getbands())
if num_channels == 3: return 'rgb'
elif num_channels == 1: return 'grayscale'
else: return 'rgby'
except:
warnings.warn('could not detect color_mode from %s' % (train_directory))
return
def preprocess_csv(csv_in, csv_out, x_col='filename', y_col=None,
sep=',', label_sep=' ', suffix='', split_by=None):
"""
```
Takes a CSV where the one column contains a file name and a column
containing a string representations of the class(es) like here:
image_name,tags
01, sunny|hot
02, cloudy|cold
03, cloudy|hot
.... and one-hot encodes the classes to produce a CSV as follows:
image_name, cloudy, cold, hot, sunny
01.jpg,0,0,1,1
02.jpg,1,1,0,0
03.jpg,1,0,1,0
Args:
csv_in (str): filepath to input CSV file
csv_out (str): filepath to output CSV file
x_col (str): name of column containing file names
y_col (str): name of column containing the classes
sep (str): field delimiter of entire file (e.g., comma fore CSV)
label_sep (str): delimiter for column containing classes
suffix (str): adds suffix to x_col values
split_by(str): name of column. A separate CSV will be
created for each value in column. Useful
for splitting a CSV based on whether a column
contains 'train' or 'valid'.
Return:
list : the list of clases (and csv_out will be new CSV file)
```
"""
if not y_col and not suffix:
raise ValueError('one or both of y_col and suffix should be supplied')
df = pd.read_csv(csv_in, sep=sep)
f_csv_out = open(csv_out, 'w')
writer = csv.writer(f_csv_out, delimiter=sep)
if y_col: df[y_col] = df[y_col].apply(str)
# write header
if y_col:
classes = set()
for row in df.iterrows():
data = row[1]
tags = data[y_col].split(label_sep)
classes.update(tags)
classes = list(classes)
classes.sort()
writer.writerow([x_col] + classes)
else:
classes = df.columns[:-1]
write.writerow(df.columns)
# write rows
for row in df.iterrows():
data = row[1]
data[x_col] = data[x_col] + suffix
if y_col:
out = list(data[[x_col]].values)
tags = set(data[y_col].strip().split(label_sep))
for c in classes:
if c in tags: out.append(1)
else: out.append(0)
else:
out = data
writer.writerow(out)
f_csv_out.close()
return classes
def images_from_folder(datadir, target_size=(224,224),
classes=None,
color_mode='rgb',
train_test_names=['train', 'test'],
data_aug=None, verbose=1):
"""
```
Returns image generator (Iterator instance).
Assumes output will be 2D one-hot-encoded labels for categorization.
Note: This function preprocesses the input in preparation
for a ResNet50 model.
Args:
datadir (string): path to training (or validation/test) dataset
Assumes folder follows this structure:
├── datadir
│ ├── train
│ │ ├── class0 # folder containing documents of class 0
│ │ ├── class1 # folder containing documents of class 1
│ │ ├── class2 # folder containing documents of class 2
│ │ └── classN # folder containing documents of class N
│ └── test
│ ├── class0 # folder containing documents of class 0
│ ├── class1 # folder containing documents of class 1
│ ├── class2 # folder containing documents of class 2
│ └── classN # folder containing documents of class N
target_size (tuple): image dimensions
classes (list): optional list of class subdirectories (e.g., ['cats','dogs'])
color_mode (string): color mode
train_test_names(list): names for train and test subfolders
data_aug(ImageDataGenerator): a keras.preprocessing.image.ImageDataGenerator
for data augmentation
verbose (bool): verbosity
Returns:
batches: a tuple of two Iterators - one for train and one for test
```
"""
# train/test names
train_str = train_test_names[0]
test_str = train_test_names[1]
train_dir = os.path.join(datadir, train_str)
test_dir = os.path.join(datadir, test_str)
# color mode warning
if PIL_INSTALLED:
inferred_color_mode = detect_color_mode(train_dir)
if inferred_color_mode is not None and (inferred_color_mode != color_mode):
U.vprint('color_mode detected (%s) different than color_mode selected (%s)' % (inferred_color_mode, color_mode),
verbose=verbose)
# get train and test data generators
(train_datagen, test_datagen) = process_datagen(data_aug,
train_directory=train_dir,
target_size=target_size,
color_mode=color_mode)
batches_tr = train_datagen.flow_from_directory(train_dir,
target_size=target_size,
classes=classes,
class_mode='categorical',
shuffle=True,
interpolation='bicubic',
color_mode = color_mode)
batches_te = test_datagen.flow_from_directory(test_dir,
target_size=target_size,
classes=classes,
class_mode='categorical',
shuffle=False,
interpolation='bicubic',
color_mode = color_mode)
# setup preprocessor
class_tup = sorted(batches_tr.class_indices.items(), key=operator.itemgetter(1))
preproc = ImagePreprocessor(test_datagen,
[x[0] for x in class_tup],
target_size=target_size,
color_mode=color_mode)
return (batches_tr, batches_te, preproc)
def images_from_df(train_df,
image_column,
label_columns=[],
directory=None,
val_directory=None,
suffix='',
val_df=None,
is_regression=False,
target_size=(224,224),
color_mode='rgb',
data_aug=None,
val_pct=0.1, random_state=None):
"""
```
Returns image generator (Iterator instance).
Assumes output will be 2D one-hot-encoded labels for categorization.
Note: This function preprocesses the input in preparation
for a ResNet50 model.
Args:
train_df (DataFrame): pandas dataframe for training dataset
image_column (string): name of column containing the filenames of images
If values in image_column do not have a file extension,
the extension should be supplied with suffix argument.
If values in image_column are not full file paths,
then the path to directory containing images should be supplied
as directory argument.
label_columns(list or str): list or str representing the columns that store labels
Labels can be in any one of the following formats:
1. a single column string string (or integer) labels
image_fname,label
-----------------
image01,cat
image02,dog
2. multiple columns for one-hot-encoded labels
image_fname,cat,dog
image01,1,0
image02,0,1
3. a single column of numeric values for image regression
image_fname,age
-----------------
image01,68
image02,18
directory (string): path to directory containing images
not required if image_column contains full filepaths
val_directory(strin): path to directory containing validation images.
only required if validation images are in different folder than train images
suffix(str): will be appended to each entry in image_column
Used when the filenames in image_column do not contain file extensions.
The extension in suffx should include ".".
val_df (DataFrame): pandas dataframe for validation set
is_regression(bool): If True, task is treated as regression.
Used when there is single column of numeric values and
numeric values should be treated as numeric targets as opposed to class labels
target_size (tuple): image dimensions
color_mode (string): color mode
data_aug(ImageDataGenerator): a keras.preprocessing.image.ImageDataGenerator
for data augmentation
val_pct(float): proportion of training data to be used for validation
only used if val_filepath is None
random_state(int): random seed for train/test split
Returns:
batches: a tuple of two Iterators - one for train and one for test
```
"""
# read in train and test data
train_df = train_df.copy()
if val_df is not None:
val_df = val_df.copy()
else:
train_df, val_df = train_test_split(train_df, test_size=val_pct, random_state=random_state)
# transform labels
ytransdf = U.YTransformDataFrame(label_columns, is_regression=is_regression)
train_df = ytransdf.apply_train(train_df)
val_df = ytransdf.apply_test(val_df)
class_names = ytransdf.get_classes()
label_columns = ytransdf.get_label_columns(squeeze=True)
# get train and test data generators
if directory:
img_folder = directory
else:
img_folder = os.path.dirname(train_df[image_column].iloc[0])
(train_datagen, test_datagen) = process_datagen(data_aug,
train_directory=img_folder,
target_size=target_size,
color_mode=color_mode,
flat_dir=True)
# fix file extensions, if necessary
if suffix:
train_df = train_df.copy()
val_df = val_df.copy()
train_df[image_column] = train_df.copy()[image_column].apply(lambda x : str(x)+suffix)
val_df[image_column] = val_df.copy()[image_column].apply(lambda x : str(x)+suffix)
# get generators
batches_tr = train_datagen.flow_from_dataframe(
train_df,
directory=directory,
x_col = image_column,
y_col=label_columns,
target_size=target_size,
class_mode='other',
shuffle=True,
interpolation='bicubic',
color_mode = color_mode)
batches_te = None
if val_df is not None:
d = val_directory if val_directory is not None else directory
batches_te = test_datagen.flow_from_dataframe(
val_df,
directory=d,
x_col = image_column,
y_col=label_columns,
target_size=target_size,
class_mode='other',
shuffle=False,
interpolation='bicubic',
color_mode = color_mode)
# setup preprocessor
preproc = ImagePreprocessor(test_datagen,
class_names,
target_size=target_size,
color_mode=color_mode)
return (batches_tr, batches_te, preproc)
def images_from_csv(train_filepath,
image_column,
label_columns=[],
directory=None,
suffix='',
val_filepath=None,
is_regression=False,
target_size=(224,224),
color_mode='rgb',
data_aug=None,
val_pct=0.1, random_state=None):
"""
```
Returns image generator (Iterator instance).
Assumes output will be 2D one-hot-encoded labels for categorization.
Note: This function preprocesses the input in preparation
for a ResNet50 model.
Args:
train_filepath (string): path to training dataset in CSV format with header row
image_column (string): name of column containing the filenames of images
If values in image_column do not have a file extension,
the extension should be supplied with suffix argument.
If values in image_column are not full file paths,
then the path to directory containing images should be supplied
as directory argument.
label_columns(list or str): list or str representing the columns that store labels
Labels can be in any one of the following formats:
1. a single column string string (or integer) labels
image_fname,label
-----------------
image01,cat
image02,dog
2. multiple columns for one-hot-encoded labels
image_fname,cat,dog
image01,1,0
image02,0,1
3. a single column of numeric values for image regression
image_fname,age
-----------------
image01,68
image02,18
directory (string): path to directory containing images
not required if image_column contains full filepaths
suffix(str): will be appended to each entry in image_column
Used when the filenames in image_column do not contain file extensions.
The extension in suffx should include ".".
val_filepath (string): path to validation dataset in CSV format
suffix(string): suffix to add to file names in image_column
is_regression(bool): If True, task is treated as regression.
Used when there is single column of numeric values and
numeric values should be treated as numeric targets as opposed to class labels
target_size (tuple): image dimensions
color_mode (string): color mode
data_aug(ImageDataGenerator): a keras.preprocessing.image.ImageDataGenerator
for data augmentation
val_pct(float): proportion of training data to be used for validation
only used if val_filepath is None
random_state(int): random seed for train/test split
Returns:
batches: a tuple of two Iterators - one for train and one for test
```
"""
# convert to dataframes
train_df = pd.read_csv(train_filepath)
val_df = None
if val_filepath is not None:
val_df = pd.read_csv(val_filepath)
return images_from_df(train_df,
image_column,
label_columns=label_columns,
directory=directory,
suffix=suffix,
val_df=val_df,
is_regression=is_regression,
target_size=target_size,
color_mode=color_mode,
data_aug=data_aug,
val_pct=val_pct, random_state=random_state)
def images_from_fname( train_folder,
pattern=r'([^/]+)_\d+.jpg$',
val_folder=None,
is_regression=False,
target_size=(224,224),
color_mode='rgb',
data_aug=None,
val_pct=0.1, random_state=None,
verbose=1):
"""
```
Returns image generator (Iterator instance).
Args:
train_folder (str): directory containing images
pat (str): regular expression to extract class from file name of each image
Example: r'([^/]+)_\d+.jpg$' to match 'english_setter' in 'english_setter_140.jpg'
By default, it will extract classes from file names of the form:
<class_name>_<numbers>.jpg
val_folder (str): directory containing validation images. default:None
is_regression(bool): If True, task is treated as regression.
Used when there is single column of numeric values and
numeric values should be treated as numeric targets as opposed to class labels
target_size (tuple): image dimensions
color_mode (string): color mode
data_aug(ImageDataGenerator): a keras.preprocessing.image.ImageDataGenerator
for data augmentation
val_pct(float): proportion of training data to be used for validation
only used if val_folder is None
random_state(int): random seed for train/test split
verbose(bool): verbosity
Returns:
batches: a tuple of two Iterators - one for train and one for test
```
"""
image_column = 'image_name'
label_column = 'label'
train_df = _img_fnames_to_df(train_folder, pattern,
image_column=image_column, label_column=label_column, verbose=verbose)
val_df = None
if val_folder is not None:
val_df = _img_fnames_to_df(val_folder, pattern,
image_column=image_column, label_column=label_column, verbose=verbose)
return images_from_df(train_df,
image_column,
label_columns=label_column,
directory=train_folder,
val_directory=val_folder,
val_df=val_df,
is_regression=is_regression,
target_size=target_size,
color_mode=color_mode,
data_aug=data_aug,
val_pct=val_pct, random_state=random_state)
def _img_fnames_to_df(img_folder,pattern, image_column='image_name', label_column='label', verbose=1):
# get fnames
fnames = []
for ext in ('*.gif', '*.png', '*.jpg'):
fnames.extend(glob.glob(os.path.join(img_folder, ext)))
# process filenames and labels
image_names = []
labels = []
p = re.compile(pattern)
for fname in fnames:
r = p.search(fname)
if r:
image_names.append(os.path.basename(fname))
labels.append(r.group(1))
else:
warnings.warn('Could not extract target for %s - skipping this file'% (fname))
dct = {'image_name': image_names, 'label':labels}
return pd.DataFrame(dct)
# class_names = list(set(labels))
# class_names.sort()
# c2i = {k:v for v,k in enumerate(class_names)}
# labels = [c2i[label] for label in labels]
# labels = to_categorical(labels)
# #class_names = [str(c) in class_names]
# U.vprint('Found %s classes: %s' % (len(class_names), class_names), verbose=verbose)
# U.vprint('y shape: (%s,%s)' % (labels.shape[0], labels.shape[1]), verbose=verbose)
# dct = {'image_name': image_names}
# for i in range(labels.shape[1]):
# dct[class_names[i]] = labels[:,i]
# # convert to dataframes
# df = pd.DataFrame(dct)
# return (df, class_names)
def images_from_array(x_train, y_train,
validation_data=None,
val_pct=0.1,
random_state=None,
data_aug=None,
classes=None,
class_names=None,
is_regression=False):
"""
```
Returns image generator (Iterator instance) from training
and validation data in the form of NumPy arrays.
This function only supports image classification.
For image regression, please use images_from_df.
Args:
x_train(numpy.ndarray): training gdata
y_train(numpy.ndarray): labels must either be:
1. one-hot (or multi-hot) encoded arrays
2. integer values representing the label
validation_data (tuple): tuple of numpy.ndarrays for validation data.
labels should be in one of the formats listed above.
val_pct(float): percentage of training data to use for validaton if validation_data is None
random_state(int): random state to use for splitting data
data_aug(ImageDataGenerator): a keras.preprocessing.image.ImageDataGenerator
classes(str): old name for class_names - should no longer be used
class_names(str): list of strings to use as class names
is_regression(bool): If True, task is treated as regression.
Used when there is single column of numeric values and
numeric values should be treated as numeric targets as opposed to class labels
Returns:
batches: a tuple of two image.Iterator - one for train and one for test and ImagePreprocessor instance
```
"""
if classes is not None: raise ValueError('Please use class_names argument instead of "classes".')
if class_names and is_regression:
warnings.warn('is_regression=True, but class_names is not empty. Task being treated as regression.')
# split out validation set if necessary
if validation_data:
x_test = validation_data[0]
y_test = validation_data[1]
elif val_pct is not None and val_pct >0:
x_train, x_test, y_train, y_test = train_test_split(x_train, y_train,
test_size=val_pct,
random_state=random_state)
else:
x_test = None
y_test = None
# transform labels
ytrans = U.YTransform(class_names=class_names if not is_regression else [])
y_train = ytrans.apply_train(y_train)
y_test = ytrans.apply_test(y_test)
class_names = ytrans.get_classes()
# train and test data generators
(train_datagen, test_datagen) = process_datagen(data_aug, train_array=x_train)
# Image preprocessor
preproc = ImagePreprocessor(test_datagen, class_names, target_size=None, color_mode=None)
# training data
batches_tr = train_datagen.flow(x_train, y_train, shuffle=True)
# validation data
batches_te = None
if x_test is not None and y_test is not None:
batches_te = test_datagen.flow(x_test, y_test,
shuffle=False)
return (batches_tr, batches_te, preproc)</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-functions">Functions</h2>
<dl>
<dt id="ktrain.vision.data.datagen_needs_fit"><code class="name flex">
<span>def <span class="ident">datagen_needs_fit</span></span>(<span>datagen)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def datagen_needs_fit(datagen):
if datagen.featurewise_center or datagen.featurewise_std_normalization or \
datagen.zca_whitening:
return True
else:
return False</code></pre>
</details>
</dd>
<dt id="ktrain.vision.data.detect_color_mode"><code class="name flex">
<span>def <span class="ident">detect_color_mode</span></span>(<span>train_directory, target_size=(32, 32))</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def detect_color_mode(train_directory,
target_size=(32,32)):
try:
fname = glob.glob(os.path.join(train_directory, '**/*'))[0]
img = Image.open(fname).resize(target_size)
num_channels = len(img.getbands())
if num_channels == 3: return 'rgb'
elif num_channels == 1: return 'grayscale'
else: return 'rgby'
except:
warnings.warn('could not detect color_mode from %s' % (train_directory))
return</code></pre>
</details>
</dd>
<dt id="ktrain.vision.data.fit_datagens"><code class="name flex">
<span>def <span class="ident">fit_datagens</span></span>(<span>train_datagen, test_datagen, train_array=None, train_directory=None, target_size=None, color_mode='rgb', flat_dir=False)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>computes stats of images for normalization
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def fit_datagens(train_datagen, test_datagen,
train_array=None, train_directory=None,
target_size=None,
color_mode='rgb', flat_dir=False):
"""
```
computes stats of images for normalization
```
"""
if not datagen_needs_fit(train_datagen): return
if bool(train_array is not None) == bool(train_directory):
raise ValueError('only one of train_array or train_directory is required.')
if train_array is not None:
train_datagen.fit(train_array)
test_datagen.fit(train_array)
else:
if target_size is None:
raise ValueError('target_size is required when train_directory is supplied')
fit_samples = sample_image_folder(train_directory, target_size,
color_mode=color_mode, flat_dir=flat_dir)
train_datagen.fit(fit_samples)
test_datagen.fit(fit_samples)
return</code></pre>
</details>
</dd>
<dt id="ktrain.vision.data.get_data_aug"><code class="name flex">
<span>def <span class="ident">get_data_aug</span></span>(<span>rotation_range=40, zoom_range=0.2, width_shift_range=0.2, height_shift_range=0.2, horizontal_flip=False, vertical_flip=False, featurewise_center=True, featurewise_std_normalization=True, samplewise_center=False, samplewise_std_normalization=False, rescale=None, **kwargs)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>This function is simply a wrapper around ImageDataGenerator
with some reasonable defaults for data augmentation.
Returns the default image_data_generator to support
data augmentation and data normalization.
Parameters can be adjusted by caller.
Note that the ktrain.vision.model.image_classifier
function may adjust these as needed.
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def get_data_aug(
rotation_range=40,
zoom_range=0.2,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=False,
vertical_flip=False,
featurewise_center=True,
featurewise_std_normalization=True,
samplewise_center=False,
samplewise_std_normalization=False,
rescale=None,
**kwargs):
"""
```
This function is simply a wrapper around ImageDataGenerator
with some reasonable defaults for data augmentation.
Returns the default image_data_generator to support
data augmentation and data normalization.
Parameters can be adjusted by caller.
Note that the ktrain.vision.model.image_classifier
function may adjust these as needed.
```
"""
data_aug = image.ImageDataGenerator(
rotation_range=rotation_range,
zoom_range=zoom_range,
width_shift_range=width_shift_range,
height_shift_range=height_shift_range,
horizontal_flip=horizontal_flip,
vertical_flip=vertical_flip,
featurewise_center=featurewise_center,
featurewise_std_normalization=featurewise_std_normalization,
samplewise_center=samplewise_center,
samplewise_std_normalization=samplewise_std_normalization,
rescale=rescale,
**kwargs)
return data_aug</code></pre>
</details>
</dd>
<dt id="ktrain.vision.data.get_test_datagen"><code class="name flex">