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
|
<!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/cifar10_resnet/">
<link rel="shortcut icon" href="../../img/favicon.ico">
<title>CIFAR-10 ResNet - 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 = "CIFAR-10 ResNet";
var mkdocs_page_input_path = "examples/cifar10_resnet.md";
var mkdocs_page_url = "/examples/cifar10_resnet/";
</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 current"><a class="reference internal current" href="./">CIFAR-10 ResNet</a>
<ul class="current">
</ul>
</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"><a class="reference internal" href="../image_ocr/">Image OCR</a>
</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>CIFAR-10 ResNet</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="trains-a-resnet-on-the-cifar10-dataset">Trains a ResNet on the CIFAR10 dataset.</h1>
<p>ResNet v1:
<a href="https://arxiv.org/pdf/1512.03385.pdf">Deep Residual Learning for Image Recognition
</a></p>
<p>ResNet v2:
<a href="https://arxiv.org/pdf/1603.05027.pdf">Identity Mappings in Deep Residual Networks
</a></p>
<table>
<thead>
<tr>
<th align="left">Model</th>
<th align="right">n</th>
<th align="right">200-epoch accuracy</th>
<th align="right">Original paper accuracy</th>
<th align="right">sec/epoch GTX1080Ti</th>
</tr>
</thead>
<tbody>
<tr>
<td align="left">ResNet20 v1</td>
<td align="right">3</td>
<td align="right">92.16 %</td>
<td align="right">91.25 %</td>
<td align="right">35</td>
</tr>
<tr>
<td align="left">ResNet32 v1</td>
<td align="right">5</td>
<td align="right">92.46 %</td>
<td align="right">92.49 %</td>
<td align="right">50</td>
</tr>
<tr>
<td align="left">ResNet44 v1</td>
<td align="right">7</td>
<td align="right">92.50 %</td>
<td align="right">92.83 %</td>
<td align="right">70</td>
</tr>
<tr>
<td align="left">ResNet56 v1</td>
<td align="right">9</td>
<td align="right">92.71 %</td>
<td align="right">93.03 %</td>
<td align="right">90</td>
</tr>
<tr>
<td align="left">ResNet110 v1</td>
<td align="right">18</td>
<td align="right">92.65 %</td>
<td align="right">93.39+-.16 %</td>
<td align="right">165</td>
</tr>
<tr>
<td align="left">ResNet164 v1</td>
<td align="right">27</td>
<td align="right">- %</td>
<td align="right">94.07 %</td>
<td align="right">-</td>
</tr>
<tr>
<td align="left">ResNet1001 v1</td>
<td align="right">N/A</td>
<td align="right">- %</td>
<td align="right">92.39 %</td>
<td align="right">-</td>
</tr>
</tbody>
</table>
<p> </p>
<table>
<thead>
<tr>
<th align="left">Model</th>
<th align="right">n</th>
<th align="right">200-epoch accuracy</th>
<th align="right">Original paper accuracy</th>
<th align="right">sec/epoch GTX1080Ti</th>
</tr>
</thead>
<tbody>
<tr>
<td align="left">ResNet20 v2</td>
<td align="right">2</td>
<td align="right">- %</td>
<td align="right">- %</td>
<td align="right">---</td>
</tr>
<tr>
<td align="left">ResNet32 v2</td>
<td align="right">N/A</td>
<td align="right">NA %</td>
<td align="right">NA %</td>
<td align="right">NA</td>
</tr>
<tr>
<td align="left">ResNet44 v2</td>
<td align="right">N/A</td>
<td align="right">NA %</td>
<td align="right">NA %</td>
<td align="right">NA</td>
</tr>
<tr>
<td align="left">ResNet56 v2</td>
<td align="right">6</td>
<td align="right">93.01 %</td>
<td align="right">NA %</td>
<td align="right">100</td>
</tr>
<tr>
<td align="left">ResNet110 v2</td>
<td align="right">12</td>
<td align="right">93.15 %</td>
<td align="right">93.63 %</td>
<td align="right">180</td>
</tr>
<tr>
<td align="left">ResNet164 v2</td>
<td align="right">18</td>
<td align="right">- %</td>
<td align="right">94.54 %</td>
<td align="right">-</td>
</tr>
<tr>
<td align="left">ResNet1001 v2</td>
<td align="right">111</td>
<td align="right">- %</td>
<td align="right">95.08+-.14 %</td>
<td align="right">-</td>
</tr>
</tbody>
</table>
<pre><code class="python">from __future__ import print_function
import keras
from keras.layers import Dense, Conv2D, BatchNormalization, Activation
from keras.layers import AveragePooling2D, Input, Flatten
from keras.optimizers import Adam
from keras.callbacks import ModelCheckpoint, LearningRateScheduler
from keras.callbacks import ReduceLROnPlateau
from keras.preprocessing.image import ImageDataGenerator
from keras.regularizers import l2
from keras import backend as K
from keras.models import Model
from keras.datasets import cifar10
import numpy as np
import os
# Training parameters
batch_size = 32 # orig paper trained all networks with batch_size=128
epochs = 200
data_augmentation = True
num_classes = 10
# Subtracting pixel mean improves accuracy
subtract_pixel_mean = True
# Model parameter
# ----------------------------------------------------------------------------
# | | 200-epoch | Orig Paper| 200-epoch | Orig Paper| sec/epoch
# Model | n | ResNet v1 | ResNet v1 | ResNet v2 | ResNet v2 | GTX1080Ti
# |v1(v2)| %Accuracy | %Accuracy | %Accuracy | %Accuracy | v1 (v2)
# ----------------------------------------------------------------------------
# ResNet20 | 3 (2)| 92.16 | 91.25 | ----- | ----- | 35 (---)
# ResNet32 | 5(NA)| 92.46 | 92.49 | NA | NA | 50 ( NA)
# ResNet44 | 7(NA)| 92.50 | 92.83 | NA | NA | 70 ( NA)
# ResNet56 | 9 (6)| 92.71 | 93.03 | 93.01 | NA | 90 (100)
# ResNet110 |18(12)| 92.65 | 93.39+-.16| 93.15 | 93.63 | 165(180)
# ResNet164 |27(18)| ----- | 94.07 | ----- | 94.54 | ---(---)
# ResNet1001| (111)| ----- | 92.39 | ----- | 95.08+-.14| ---(---)
# ---------------------------------------------------------------------------
n = 3
# Model version
# Orig paper: version = 1 (ResNet v1), Improved ResNet: version = 2 (ResNet v2)
version = 1
# Computed depth from supplied model parameter n
if version == 1:
depth = n * 6 + 2
elif version == 2:
depth = n * 9 + 2
# Model name, depth and version
model_type = 'ResNet%dv%d' % (depth, version)
# Load the CIFAR10 data.
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
# Input image dimensions.
input_shape = x_train.shape[1:]
# Normalize data.
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
# If subtract pixel mean is enabled
if subtract_pixel_mean:
x_train_mean = np.mean(x_train, axis=0)
x_train -= x_train_mean
x_test -= x_train_mean
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
print('y_train shape:', y_train.shape)
# Convert class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
def lr_schedule(epoch):
"""Learning Rate Schedule
Learning rate is scheduled to be reduced after 80, 120, 160, 180 epochs.
Called automatically every epoch as part of callbacks during training.
# Arguments
epoch (int): The number of epochs
# Returns
lr (float32): learning rate
"""
lr = 1e-3
if epoch > 180:
lr *= 0.5e-3
elif epoch > 160:
lr *= 1e-3
elif epoch > 120:
lr *= 1e-2
elif epoch > 80:
lr *= 1e-1
print('Learning rate: ', lr)
return lr
def resnet_layer(inputs,
num_filters=16,
kernel_size=3,
strides=1,
activation='relu',
batch_normalization=True,
conv_first=True):
"""2D Convolution-Batch Normalization-Activation stack builder
# Arguments
inputs (tensor): input tensor from input image or previous layer
num_filters (int): Conv2D number of filters
kernel_size (int): Conv2D square kernel dimensions
strides (int): Conv2D square stride dimensions
activation (string): activation name
batch_normalization (bool): whether to include batch normalization
conv_first (bool): conv-bn-activation (True) or
bn-activation-conv (False)
# Returns
x (tensor): tensor as input to the next layer
"""
conv = Conv2D(num_filters,
kernel_size=kernel_size,
strides=strides,
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(1e-4))
x = inputs
if conv_first:
x = conv(x)
if batch_normalization:
x = BatchNormalization()(x)
if activation is not None:
x = Activation(activation)(x)
else:
if batch_normalization:
x = BatchNormalization()(x)
if activation is not None:
x = Activation(activation)(x)
x = conv(x)
return x
def resnet_v1(input_shape, depth, num_classes=10):
"""ResNet Version 1 Model builder [a]
Stacks of 2 x (3 x 3) Conv2D-BN-ReLU
Last ReLU is after the shortcut connection.
At the beginning of each stage, the feature map size is halved (downsampled)
by a convolutional layer with strides=2, while the number of filters is
doubled. Within each stage, the layers have the same number filters and the
same number of filters.
Features maps sizes:
stage 0: 32x32, 16
stage 1: 16x16, 32
stage 2: 8x8, 64
The Number of parameters is approx the same as Table 6 of [a]:
ResNet20 0.27M
ResNet32 0.46M
ResNet44 0.66M
ResNet56 0.85M
ResNet110 1.7M
# Arguments
input_shape (tensor): shape of input image tensor
depth (int): number of core convolutional layers
num_classes (int): number of classes (CIFAR10 has 10)
# Returns
model (Model): Keras model instance
"""
if (depth - 2) % 6 != 0:
raise ValueError('depth should be 6n+2 (eg 20, 32, 44 in [a])')
# Start model definition.
num_filters = 16
num_res_blocks = int((depth - 2) / 6)
inputs = Input(shape=input_shape)
x = resnet_layer(inputs=inputs)
# Instantiate the stack of residual units
for stack in range(3):
for res_block in range(num_res_blocks):
strides = 1
if stack > 0 and res_block == 0: # first layer but not first stack
strides = 2 # downsample
y = resnet_layer(inputs=x,
num_filters=num_filters,
strides=strides)
y = resnet_layer(inputs=y,
num_filters=num_filters,
activation=None)
if stack > 0 and res_block == 0: # first layer but not first stack
# linear projection residual shortcut connection to match
# changed dims
x = resnet_layer(inputs=x,
num_filters=num_filters,
kernel_size=1,
strides=strides,
activation=None,
batch_normalization=False)
x = keras.layers.add([x, y])
x = Activation('relu')(x)
num_filters *= 2
# Add classifier on top.
# v1 does not use BN after last shortcut connection-ReLU
x = AveragePooling2D(pool_size=8)(x)
y = Flatten()(x)
outputs = Dense(num_classes,
activation='softmax',
kernel_initializer='he_normal')(y)
# Instantiate model.
model = Model(inputs=inputs, outputs=outputs)
return model
def resnet_v2(input_shape, depth, num_classes=10):
"""ResNet Version 2 Model builder [b]
Stacks of (1 x 1)-(3 x 3)-(1 x 1) BN-ReLU-Conv2D or also known as
bottleneck layer
First shortcut connection per layer is 1 x 1 Conv2D.
Second and onwards shortcut connection is identity.
At the beginning of each stage, the feature map size is halved (downsampled)
by a convolutional layer with strides=2, while the number of filter maps is
doubled. Within each stage, the layers have the same number filters and the
same filter map sizes.
Features maps sizes:
conv1 : 32x32, 16
stage 0: 32x32, 64
stage 1: 16x16, 128
stage 2: 8x8, 256
# Arguments
input_shape (tensor): shape of input image tensor
depth (int): number of core convolutional layers
num_classes (int): number of classes (CIFAR10 has 10)
# Returns
model (Model): Keras model instance
"""
if (depth - 2) % 9 != 0:
raise ValueError('depth should be 9n+2 (eg 56 or 110 in [b])')
# Start model definition.
num_filters_in = 16
num_res_blocks = int((depth - 2) / 9)
inputs = Input(shape=input_shape)
# v2 performs Conv2D with BN-ReLU on input before splitting into 2 paths
x = resnet_layer(inputs=inputs,
num_filters=num_filters_in,
conv_first=True)
# Instantiate the stack of residual units
for stage in range(3):
for res_block in range(num_res_blocks):
activation = 'relu'
batch_normalization = True
strides = 1
if stage == 0:
num_filters_out = num_filters_in * 4
if res_block == 0: # first layer and first stage
activation = None
batch_normalization = False
else:
num_filters_out = num_filters_in * 2
if res_block == 0: # first layer but not first stage
strides = 2 # downsample
# bottleneck residual unit
y = resnet_layer(inputs=x,
num_filters=num_filters_in,
kernel_size=1,
strides=strides,
activation=activation,
batch_normalization=batch_normalization,
conv_first=False)
y = resnet_layer(inputs=y,
num_filters=num_filters_in,
conv_first=False)
y = resnet_layer(inputs=y,
num_filters=num_filters_out,
kernel_size=1,
conv_first=False)
if res_block == 0:
# linear projection residual shortcut connection to match
# changed dims
x = resnet_layer(inputs=x,
num_filters=num_filters_out,
kernel_size=1,
strides=strides,
activation=None,
batch_normalization=False)
x = keras.layers.add([x, y])
num_filters_in = num_filters_out
# Add classifier on top.
# v2 has BN-ReLU before Pooling
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=8)(x)
y = Flatten()(x)
outputs = Dense(num_classes,
activation='softmax',
kernel_initializer='he_normal')(y)
# Instantiate model.
model = Model(inputs=inputs, outputs=outputs)
return model
if version == 2:
model = resnet_v2(input_shape=input_shape, depth=depth)
else:
model = resnet_v1(input_shape=input_shape, depth=depth)
model.compile(loss='categorical_crossentropy',
optimizer=Adam(learning_rate=lr_schedule(0)),
metrics=['accuracy'])
model.summary()
print(model_type)
# Prepare model model saving directory.
save_dir = os.path.join(os.getcwd(), 'saved_models')
model_name = 'cifar10_%s_model.{epoch:03d}.h5' % model_type
if not os.path.isdir(save_dir):
os.makedirs(save_dir)
filepath = os.path.join(save_dir, model_name)
# Prepare callbacks for model saving and for learning rate adjustment.
checkpoint = ModelCheckpoint(filepath=filepath,
monitor='val_acc',
verbose=1,
save_best_only=True)
lr_scheduler = LearningRateScheduler(lr_schedule)
lr_reducer = ReduceLROnPlateau(factor=np.sqrt(0.1),
cooldown=0,
patience=5,
min_lr=0.5e-6)
callbacks = [checkpoint, lr_reducer, lr_scheduler]
# Run training, with or without data augmentation.
if not data_augmentation:
print('Not using data augmentation.')
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test, y_test),
shuffle=True,
callbacks=callbacks)
else:
print('Using real-time data augmentation.')
# This will do preprocessing and realtime data augmentation:
datagen = ImageDataGenerator(
# set input mean to 0 over the dataset
featurewise_center=False,
# set each sample mean to 0
samplewise_center=False,
# divide inputs by std of dataset
featurewise_std_normalization=False,
# divide each input by its std
samplewise_std_normalization=False,
# apply ZCA whitening
zca_whitening=False,
# epsilon for ZCA whitening
zca_epsilon=1e-06,
# randomly rotate images in the range (deg 0 to 180)
rotation_range=0,
# randomly shift images horizontally
width_shift_range=0.1,
# randomly shift images vertically
height_shift_range=0.1,
# set range for random shear
shear_range=0.,
# set range for random zoom
zoom_range=0.,
# set range for random channel shifts
channel_shift_range=0.,
# set mode for filling points outside the input boundaries
fill_mode='nearest',
# value used for fill_mode = "constant"
cval=0.,
# randomly flip images
horizontal_flip=True,
# randomly flip images
vertical_flip=False,
# set rescaling factor (applied before any other transformation)
rescale=None,
# set function that will be applied on each input
preprocessing_function=None,
# image data format, either "channels_first" or "channels_last"
data_format=None,
# fraction of images reserved for validation (strictly between 0 and 1)
validation_split=0.0)
# Compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied).
datagen.fit(x_train)
# Fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(x_train, y_train, batch_size=batch_size),
validation_data=(x_test, y_test),
epochs=epochs, verbose=1, workers=4,
callbacks=callbacks)
# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
</code></pre>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../conv_filter_visualization/" class="btn btn-neutral float-right" title="Convolution filter visualization">Next <span class="icon icon-circle-arrow-right"></span></a>
<a href="../cifar10_cnn/" class="btn btn-neutral" title="CIFAR-10 CNN"><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="../cifar10_cnn/" style="color: #fcfcfc;">« Previous</a></span>
<span style="margin-left: 15px"><a href="../conv_filter_visualization/" 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>
|
