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
|
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="canonical" href="http://keras.io/examples/image_ocr/">
<link rel="shortcut icon" href="../../img/favicon.ico">
<title>Image OCR - Keras Documentation</title>
<link href='https://fonts.googleapis.com/css?family=Lato:400,700|Source+Sans+Pro:400,700|Inconsolata:400,700' rel='stylesheet' type='text/css'>
<link rel="stylesheet" href="../../css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../css/theme_extra.css" type="text/css" />
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/github.min.css">
<script>
// Current page data
var mkdocs_page_name = "Image OCR";
var mkdocs_page_input_path = "examples/image_ocr.md";
var mkdocs_page_url = "/examples/image_ocr/";
</script>
<script src="../../js/jquery-2.1.1.min.js" defer></script>
<script src="../../js/modernizr-2.8.3.min.js" defer></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/highlight.min.js"></script>
<script>hljs.initHighlightingOnLoad();</script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-61785484-1', 'keras.io');
ga('send', 'pageview');
</script>
</head>
<body class="wy-body-for-nav" role="document">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side stickynav">
<div class="wy-side-scroll">
<a href="">
<div class="keras-logo">
<img src="/img/keras-logo-small.jpg" class="keras-logo-img">
Keras Documentation
</div>
</a>
<div class="wy-side-nav-search">
<div role="search">
<form id ="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" title="Type search term here" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../..">Home</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../why-use-keras/">Why use Keras</a>
</li>
</ul>
<p class="caption"><span class="caption-text">Getting started</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../getting-started/sequential-model-guide/">Guide to the Sequential model</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../getting-started/functional-api-guide/">Guide to the Functional API</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../getting-started/faq/">FAQ</a>
</li>
</ul>
<p class="caption"><span class="caption-text">Models</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../models/about-keras-models/">About Keras models</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../models/sequential/">Sequential</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../models/model/">Model (functional API)</a>
</li>
</ul>
<p class="caption"><span class="caption-text">Layers</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../layers/about-keras-layers/">About Keras layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/core/">Core Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/convolutional/">Convolutional Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/pooling/">Pooling Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/local/">Locally-connected Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/recurrent/">Recurrent Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/embeddings/">Embedding Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/merge/">Merge Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/advanced-activations/">Advanced Activations Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/normalization/">Normalization Layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/noise/">Noise layers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/wrappers/">Layer wrappers</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../layers/writing-your-own-keras-layers/">Writing your own Keras layers</a>
</li>
</ul>
<p class="caption"><span class="caption-text">Preprocessing</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../preprocessing/sequence/">Sequence Preprocessing</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../preprocessing/text/">Text Preprocessing</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../preprocessing/image/">Image Preprocessing</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../losses/">Losses</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../metrics/">Metrics</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../optimizers/">Optimizers</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../activations/">Activations</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../callbacks/">Callbacks</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../datasets/">Datasets</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../applications/">Applications</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../backend/">Backend</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../initializers/">Initializers</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../regularizers/">Regularizers</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../constraints/">Constraints</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../visualization/">Visualization</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../scikit-learn-api/">Scikit-learn API</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../utils/">Utils</a>
</li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../contributing/">Contributing</a>
</li>
</ul>
<p class="caption"><span class="caption-text">Examples</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../addition_rnn/">Addition RNN</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../antirectifier/">Custom layer - antirectifier</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../babi_rnn/">Baby RNN</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../babi_memnn/">Baby MemNN</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../cifar10_cnn/">CIFAR-10 CNN</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../cifar10_resnet/">CIFAR-10 ResNet</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../conv_filter_visualization/">Convolution filter visualization</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../conv_lstm/">Convolutional LSTM</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../deep_dream/">Deep Dream</a>
</li>
<li class="toctree-l1 current"><a class="reference internal current" href="./">Image OCR</a>
<ul class="current">
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../imdb_bidirectional_lstm/">Bidirectional LSTM</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../imdb_cnn/">1D CNN for text classification</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../imdb_cnn_lstm/">Sentiment classification CNN-LSTM</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../imdb_fasttext/">Fasttext for text classification</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../imdb_lstm/">Sentiment classification LSTM</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../lstm_seq2seq/">Sequence to sequence - training</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../lstm_seq2seq_restore/">Sequence to sequence - prediction</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../lstm_stateful/">Stateful LSTM</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../lstm_text_generation/">LSTM for text generation</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../mnist_acgan/">Auxiliary Classifier GAN</a>
</li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../..">Keras Documentation</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../..">Docs</a> »</li>
<li>Examples »</li>
<li>Image OCR</li>
<li class="wy-breadcrumbs-aside">
<a href="https://github.com/keras-team/keras/tree/master/docs"
class="icon icon-github"> Edit on GitHub</a>
</li>
</ul>
<hr/>
</div>
<div role="main">
<div class="section">
<h1 id="optical-character-recognition">Optical character recognition</h1>
<p>This example uses a convolutional stack followed by a recurrent stack
and a CTC logloss function to perform optical character recognition
of generated text images. I have no evidence of whether it actually
learns general shapes of text, or just is able to recognize all
the different fonts thrown at it...the purpose is more to demonstrate CTC
inside of Keras. Note that the font list may need to be updated
for the particular OS in use.</p>
<p>This starts off with 4 letter words. For the first 12 epochs, the
difficulty is gradually increased using the TextImageGenerator class
which is both a generator class for test/train data and a Keras
callback class. After 20 epochs, longer sequences are thrown at it
by recompiling the model to handle a wider image and rebuilding
the word list to include two words separated by a space.</p>
<p>The table below shows normalized edit distance values. Theano uses
a slightly different CTC implementation, hence the different results.</p>
<table>
<thead>
<tr>
<th align="right">Epoch</th>
<th align="right">TF</th>
<th align="right">TH</th>
</tr>
</thead>
<tbody>
<tr>
<td align="right">10</td>
<td align="right">0.027</td>
<td align="right">0.064</td>
</tr>
<tr>
<td align="right">15</td>
<td align="right">0.038</td>
<td align="right">0.035</td>
</tr>
<tr>
<td align="right">20</td>
<td align="right">0.043</td>
<td align="right">0.045</td>
</tr>
<tr>
<td align="right">25</td>
<td align="right">0.014</td>
<td align="right">0.019</td>
</tr>
</tbody>
</table>
<h1 id="additional-dependencies">Additional dependencies</h1>
<p>This requires <code>cairo</code> and <code>editdistance</code> packages:</p>
<p>First, install the Cairo library: https://cairographics.org/</p>
<p>Then install Python dependencies:</p>
<pre><code class="python">pip install cairocffi
pip install editdistance
</code></pre>
<p>Created by Mike Henry
https://github.com/mbhenry/</p>
<pre><code class="python">import os
import itertools
import codecs
import re
import datetime
import cairocffi as cairo
import editdistance
import numpy as np
from scipy import ndimage
import pylab
from keras import backend as K
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.layers import Input, Dense, Activation
from keras.layers import Reshape, Lambda
from keras.layers.merge import add, concatenate
from keras.models import Model
from keras.layers.recurrent import GRU
from keras.optimizers import SGD
from keras.utils.data_utils import get_file
from keras.preprocessing import image
import keras.callbacks
OUTPUT_DIR = 'image_ocr'
# character classes and matching regex filter
regex = r'^[a-z ]+$'
alphabet = u'abcdefghijklmnopqrstuvwxyz '
np.random.seed(55)
# this creates larger "blotches" of noise which look
# more realistic than just adding gaussian noise
# assumes greyscale with pixels ranging from 0 to 1
def speckle(img):
severity = np.random.uniform(0, 0.6)
blur = ndimage.gaussian_filter(np.random.randn(*img.shape) * severity, 1)
img_speck = (img + blur)
img_speck[img_speck > 1] = 1
img_speck[img_speck <= 0] = 0
return img_speck
# paints the string in a random location the bounding box
# also uses a random font, a slight random rotation,
# and a random amount of speckle noise
def paint_text(text, w, h, rotate=False, ud=False, multi_fonts=False):
surface = cairo.ImageSurface(cairo.FORMAT_RGB24, w, h)
with cairo.Context(surface) as context:
context.set_source_rgb(1, 1, 1) # White
context.paint()
# this font list works in CentOS 7
if multi_fonts:
fonts = [
'Century Schoolbook', 'Courier', 'STIX',
'URW Chancery L', 'FreeMono']
context.select_font_face(
np.random.choice(fonts),
cairo.FONT_SLANT_NORMAL,
np.random.choice([cairo.FONT_WEIGHT_BOLD, cairo.FONT_WEIGHT_NORMAL]))
else:
context.select_font_face('Courier',
cairo.FONT_SLANT_NORMAL,
cairo.FONT_WEIGHT_BOLD)
context.set_font_size(25)
box = context.text_extents(text)
border_w_h = (4, 4)
if box[2] > (w - 2 * border_w_h[1]) or box[3] > (h - 2 * border_w_h[0]):
raise IOError(('Could not fit string into image.'
'Max char count is too large for given image width.'))
# teach the RNN translational invariance by
# fitting text box randomly on canvas, with some room to rotate
max_shift_x = w - box[2] - border_w_h[0]
max_shift_y = h - box[3] - border_w_h[1]
top_left_x = np.random.randint(0, int(max_shift_x))
if ud:
top_left_y = np.random.randint(0, int(max_shift_y))
else:
top_left_y = h // 2
context.move_to(top_left_x - int(box[0]), top_left_y - int(box[1]))
context.set_source_rgb(0, 0, 0)
context.show_text(text)
buf = surface.get_data()
a = np.frombuffer(buf, np.uint8)
a.shape = (h, w, 4)
a = a[:, :, 0] # grab single channel
a = a.astype(np.float32) / 255
a = np.expand_dims(a, 0)
if rotate:
a = image.random_rotation(a, 3 * (w - top_left_x) / w + 1)
a = speckle(a)
return a
def shuffle_mats_or_lists(matrix_list, stop_ind=None):
ret = []
assert all([len(i) == len(matrix_list[0]) for i in matrix_list])
len_val = len(matrix_list[0])
if stop_ind is None:
stop_ind = len_val
assert stop_ind <= len_val
a = list(range(stop_ind))
np.random.shuffle(a)
a += list(range(stop_ind, len_val))
for mat in matrix_list:
if isinstance(mat, np.ndarray):
ret.append(mat[a])
elif isinstance(mat, list):
ret.append([mat[i] for i in a])
else:
raise TypeError('`shuffle_mats_or_lists` only supports '
'numpy.array and list objects.')
return ret
# Translation of characters to unique integer values
def text_to_labels(text):
ret = []
for char in text:
ret.append(alphabet.find(char))
return ret
# Reverse translation of numerical classes back to characters
def labels_to_text(labels):
ret = []
for c in labels:
if c == len(alphabet): # CTC Blank
ret.append("")
else:
ret.append(alphabet[c])
return "".join(ret)
# only a-z and space..probably not to difficult
# to expand to uppercase and symbols
def is_valid_str(in_str):
search = re.compile(regex, re.UNICODE).search
return bool(search(in_str))
# Uses generator functions to supply train/test with
# data. Image renderings and text are created on the fly
# each time with random perturbations
class TextImageGenerator(keras.callbacks.Callback):
def __init__(self, monogram_file, bigram_file, minibatch_size,
img_w, img_h, downsample_factor, val_split,
absolute_max_string_len=16):
self.minibatch_size = minibatch_size
self.img_w = img_w
self.img_h = img_h
self.monogram_file = monogram_file
self.bigram_file = bigram_file
self.downsample_factor = downsample_factor
self.val_split = val_split
self.blank_label = self.get_output_size() - 1
self.absolute_max_string_len = absolute_max_string_len
def get_output_size(self):
return len(alphabet) + 1
# num_words can be independent of the epoch size due to the use of generators
# as max_string_len grows, num_words can grow
def build_word_list(self, num_words, max_string_len=None, mono_fraction=0.5):
assert max_string_len <= self.absolute_max_string_len
assert num_words % self.minibatch_size == 0
assert (self.val_split * num_words) % self.minibatch_size == 0
self.num_words = num_words
self.string_list = [''] * self.num_words
tmp_string_list = []
self.max_string_len = max_string_len
self.Y_data = np.ones([self.num_words, self.absolute_max_string_len]) * -1
self.X_text = []
self.Y_len = [0] * self.num_words
def _is_length_of_word_valid(word):
return (max_string_len == -1 or
max_string_len is None or
len(word) <= max_string_len)
# monogram file is sorted by frequency in english speech
with codecs.open(self.monogram_file, mode='r', encoding='utf-8') as f:
for line in f:
if len(tmp_string_list) == int(self.num_words * mono_fraction):
break
word = line.rstrip()
if _is_length_of_word_valid(word):
tmp_string_list.append(word)
# bigram file contains common word pairings in english speech
with codecs.open(self.bigram_file, mode='r', encoding='utf-8') as f:
lines = f.readlines()
for line in lines:
if len(tmp_string_list) == self.num_words:
break
columns = line.lower().split()
word = columns[0] + ' ' + columns[1]
if is_valid_str(word) and _is_length_of_word_valid(word):
tmp_string_list.append(word)
if len(tmp_string_list) != self.num_words:
raise IOError('Could not pull enough words'
'from supplied monogram and bigram files.')
# interlace to mix up the easy and hard words
self.string_list[::2] = tmp_string_list[:self.num_words // 2]
self.string_list[1::2] = tmp_string_list[self.num_words // 2:]
for i, word in enumerate(self.string_list):
self.Y_len[i] = len(word)
self.Y_data[i, 0:len(word)] = text_to_labels(word)
self.X_text.append(word)
self.Y_len = np.expand_dims(np.array(self.Y_len), 1)
self.cur_val_index = self.val_split
self.cur_train_index = 0
# each time an image is requested from train/val/test, a new random
# painting of the text is performed
def get_batch(self, index, size, train):
# width and height are backwards from typical Keras convention
# because width is the time dimension when it gets fed into the RNN
if K.image_data_format() == 'channels_first':
X_data = np.ones([size, 1, self.img_w, self.img_h])
else:
X_data = np.ones([size, self.img_w, self.img_h, 1])
labels = np.ones([size, self.absolute_max_string_len])
input_length = np.zeros([size, 1])
label_length = np.zeros([size, 1])
source_str = []
for i in range(size):
# Mix in some blank inputs. This seems to be important for
# achieving translational invariance
if train and i > size - 4:
if K.image_data_format() == 'channels_first':
X_data[i, 0, 0:self.img_w, :] = self.paint_func('')[0, :, :].T
else:
X_data[i, 0:self.img_w, :, 0] = self.paint_func('',)[0, :, :].T
labels[i, 0] = self.blank_label
input_length[i] = self.img_w // self.downsample_factor - 2
label_length[i] = 1
source_str.append('')
else:
if K.image_data_format() == 'channels_first':
X_data[i, 0, 0:self.img_w, :] = (
self.paint_func(self.X_text[index + i])[0, :, :].T)
else:
X_data[i, 0:self.img_w, :, 0] = (
self.paint_func(self.X_text[index + i])[0, :, :].T)
labels[i, :] = self.Y_data[index + i]
input_length[i] = self.img_w // self.downsample_factor - 2
label_length[i] = self.Y_len[index + i]
source_str.append(self.X_text[index + i])
inputs = {'the_input': X_data,
'the_labels': labels,
'input_length': input_length,
'label_length': label_length,
'source_str': source_str # used for visualization only
}
outputs = {'ctc': np.zeros([size])} # dummy data for dummy loss function
return (inputs, outputs)
def next_train(self):
while 1:
ret = self.get_batch(self.cur_train_index,
self.minibatch_size, train=True)
self.cur_train_index += self.minibatch_size
if self.cur_train_index >= self.val_split:
self.cur_train_index = self.cur_train_index % 32
(self.X_text, self.Y_data, self.Y_len) = shuffle_mats_or_lists(
[self.X_text, self.Y_data, self.Y_len], self.val_split)
yield ret
def next_val(self):
while 1:
ret = self.get_batch(self.cur_val_index,
self.minibatch_size, train=False)
self.cur_val_index += self.minibatch_size
if self.cur_val_index >= self.num_words:
self.cur_val_index = self.val_split + self.cur_val_index % 32
yield ret
def on_train_begin(self, logs={}):
self.build_word_list(16000, 4, 1)
self.paint_func = lambda text: paint_text(
text, self.img_w, self.img_h,
rotate=False, ud=False, multi_fonts=False)
def on_epoch_begin(self, epoch, logs={}):
# rebind the paint function to implement curriculum learning
if 3 <= epoch < 6:
self.paint_func = lambda text: paint_text(
text, self.img_w, self.img_h,
rotate=False, ud=True, multi_fonts=False)
elif 6 <= epoch < 9:
self.paint_func = lambda text: paint_text(
text, self.img_w, self.img_h,
rotate=False, ud=True, multi_fonts=True)
elif epoch >= 9:
self.paint_func = lambda text: paint_text(
text, self.img_w, self.img_h,
rotate=True, ud=True, multi_fonts=True)
if epoch >= 21 and self.max_string_len < 12:
self.build_word_list(32000, 12, 0.5)
# the actual loss calc occurs here despite it not being
# an internal Keras loss function
def ctc_lambda_func(args):
y_pred, labels, input_length, label_length = args
# the 2 is critical here since the first couple outputs of the RNN
# tend to be garbage:
y_pred = y_pred[:, 2:, :]
return K.ctc_batch_cost(labels, y_pred, input_length, label_length)
# For a real OCR application, this should be beam search with a dictionary
# and language model. For this example, best path is sufficient.
def decode_batch(test_func, word_batch):
out = test_func([word_batch])[0]
ret = []
for j in range(out.shape[0]):
out_best = list(np.argmax(out[j, 2:], 1))
out_best = [k for k, g in itertools.groupby(out_best)]
outstr = labels_to_text(out_best)
ret.append(outstr)
return ret
class VizCallback(keras.callbacks.Callback):
def __init__(self, run_name, test_func, text_img_gen, num_display_words=6):
self.test_func = test_func
self.output_dir = os.path.join(
OUTPUT_DIR, run_name)
self.text_img_gen = text_img_gen
self.num_display_words = num_display_words
if not os.path.exists(self.output_dir):
os.makedirs(self.output_dir)
def show_edit_distance(self, num):
num_left = num
mean_norm_ed = 0.0
mean_ed = 0.0
while num_left > 0:
word_batch = next(self.text_img_gen)[0]
num_proc = min(word_batch['the_input'].shape[0], num_left)
decoded_res = decode_batch(self.test_func,
word_batch['the_input'][0:num_proc])
for j in range(num_proc):
edit_dist = editdistance.eval(decoded_res[j],
word_batch['source_str'][j])
mean_ed += float(edit_dist)
mean_norm_ed += float(edit_dist) / len(word_batch['source_str'][j])
num_left -= num_proc
mean_norm_ed = mean_norm_ed / num
mean_ed = mean_ed / num
print('\nOut of %d samples: Mean edit distance:'
'%.3f Mean normalized edit distance: %0.3f'
% (num, mean_ed, mean_norm_ed))
def on_epoch_end(self, epoch, logs={}):
self.model.save_weights(
os.path.join(self.output_dir, 'weights%02d.h5' % (epoch)))
self.show_edit_distance(256)
word_batch = next(self.text_img_gen)[0]
res = decode_batch(self.test_func,
word_batch['the_input'][0:self.num_display_words])
if word_batch['the_input'][0].shape[0] < 256:
cols = 2
else:
cols = 1
for i in range(self.num_display_words):
pylab.subplot(self.num_display_words // cols, cols, i + 1)
if K.image_data_format() == 'channels_first':
the_input = word_batch['the_input'][i, 0, :, :]
else:
the_input = word_batch['the_input'][i, :, :, 0]
pylab.imshow(the_input.T, cmap='Greys_r')
pylab.xlabel(
'Truth = \'%s\'\nDecoded = \'%s\'' %
(word_batch['source_str'][i], res[i]))
fig = pylab.gcf()
fig.set_size_inches(10, 13)
pylab.savefig(os.path.join(self.output_dir, 'e%02d.png' % (epoch)))
pylab.close()
def train(run_name, start_epoch, stop_epoch, img_w):
# Input Parameters
img_h = 64
words_per_epoch = 16000
val_split = 0.2
val_words = int(words_per_epoch * (val_split))
# Network parameters
conv_filters = 16
kernel_size = (3, 3)
pool_size = 2
time_dense_size = 32
rnn_size = 512
minibatch_size = 32
if K.image_data_format() == 'channels_first':
input_shape = (1, img_w, img_h)
else:
input_shape = (img_w, img_h, 1)
fdir = os.path.dirname(
get_file('wordlists.tgz',
origin='http://www.mythic-ai.com/datasets/wordlists.tgz',
untar=True))
img_gen = TextImageGenerator(
monogram_file=os.path.join(fdir, 'wordlist_mono_clean.txt'),
bigram_file=os.path.join(fdir, 'wordlist_bi_clean.txt'),
minibatch_size=minibatch_size,
img_w=img_w,
img_h=img_h,
downsample_factor=(pool_size ** 2),
val_split=words_per_epoch - val_words)
act = 'relu'
input_data = Input(name='the_input', shape=input_shape, dtype='float32')
inner = Conv2D(conv_filters, kernel_size, padding='same',
activation=act, kernel_initializer='he_normal',
name='conv1')(input_data)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max1')(inner)
inner = Conv2D(conv_filters, kernel_size, padding='same',
activation=act, kernel_initializer='he_normal',
name='conv2')(inner)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max2')(inner)
conv_to_rnn_dims = (img_w // (pool_size ** 2),
(img_h // (pool_size ** 2)) * conv_filters)
inner = Reshape(target_shape=conv_to_rnn_dims, name='reshape')(inner)
# cuts down input size going into RNN:
inner = Dense(time_dense_size, activation=act, name='dense1')(inner)
# Two layers of bidirectional GRUs
# GRU seems to work as well, if not better than LSTM:
gru_1 = GRU(rnn_size, return_sequences=True,
kernel_initializer='he_normal', name='gru1')(inner)
gru_1b = GRU(rnn_size, return_sequences=True,
go_backwards=True, kernel_initializer='he_normal',
name='gru1_b')(inner)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(rnn_size, return_sequences=True,
kernel_initializer='he_normal', name='gru2')(gru1_merged)
gru_2b = GRU(rnn_size, return_sequences=True, go_backwards=True,
kernel_initializer='he_normal', name='gru2_b')(gru1_merged)
# transforms RNN output to character activations:
inner = Dense(img_gen.get_output_size(), kernel_initializer='he_normal',
name='dense2')(concatenate([gru_2, gru_2b]))
y_pred = Activation('softmax', name='softmax')(inner)
Model(inputs=input_data, outputs=y_pred).summary()
labels = Input(name='the_labels',
shape=[img_gen.absolute_max_string_len], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
# Keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
loss_out = Lambda(
ctc_lambda_func, output_shape=(1,),
name='ctc')([y_pred, labels, input_length, label_length])
# clipnorm seems to speeds up convergence
sgd = SGD(learning_rate=0.02,
decay=1e-6,
momentum=0.9,
nesterov=True)
model = Model(inputs=[input_data, labels, input_length, label_length],
outputs=loss_out)
# the loss calc occurs elsewhere, so use a dummy lambda func for the loss
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd)
if start_epoch > 0:
weight_file = os.path.join(
OUTPUT_DIR,
os.path.join(run_name, 'weights%02d.h5' % (start_epoch - 1)))
model.load_weights(weight_file)
# captures output of softmax so we can decode the output during visualization
test_func = K.function([input_data], [y_pred])
viz_cb = VizCallback(run_name, test_func, img_gen.next_val())
model.fit_generator(
generator=img_gen.next_train(),
steps_per_epoch=(words_per_epoch - val_words) // minibatch_size,
epochs=stop_epoch,
validation_data=img_gen.next_val(),
validation_steps=val_words // minibatch_size,
callbacks=[viz_cb, img_gen],
initial_epoch=start_epoch)
if __name__ == '__main__':
run_name = datetime.datetime.now().strftime('%Y:%m:%d:%H:%M:%S')
train(run_name, 0, 20, 128)
# increase to wider images and start at epoch 20.
# The learned weights are reloaded
train(run_name, 20, 25, 512)
</code></pre>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../imdb_bidirectional_lstm/" class="btn btn-neutral float-right" title="Bidirectional LSTM">Next <span class="icon icon-circle-arrow-right"></span></a>
<a href="../deep_dream/" class="btn btn-neutral" title="Deep Dream"><span class="icon icon-circle-arrow-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<!-- Copyright etc -->
</div>
Built with <a href="https://www.mkdocs.org/">MkDocs</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<div class="rst-versions" role="note" aria-label="versions">
<span class="rst-current-version" data-toggle="rst-current-version">
<a href="http://github.com/keras-team/keras/" class="fa fa-github" style="float: left; color: #fcfcfc"> GitHub</a>
<span><a href="../deep_dream/" style="color: #fcfcfc;">« Previous</a></span>
<span style="margin-left: 15px"><a href="../imdb_bidirectional_lstm/" style="color: #fcfcfc">Next »</a></span>
</span>
</div>
<script>var base_url = '../..';</script>
<script src="../../js/theme.js" defer></script>
<script src="../../search/main.js" defer></script>
<script type="text/javascript" defer>
window.onload = function () {
SphinxRtdTheme.Navigation.enable(true);
};
</script>
</body>
</html>
|
