-
Notifications
You must be signed in to change notification settings - Fork 1.4k
/
SSD.py
825 lines (745 loc) · 35.2 KB
/
SSD.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
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
"""Keras implementation of SSD."""
import cv2
import keras.backend as K
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from keras.applications.imagenet_utils import preprocess_input
from keras.engine.topology import InputSpec
from keras.engine.topology import Layer
from keras.layers import Activation
from keras.layers import AtrousConvolution2D
from keras.layers import Convolution2D
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import GlobalAveragePooling2D
from keras.layers import Input
from keras.layers import MaxPooling2D
from keras.layers import Reshape
from keras.layers import ZeroPadding2D
from keras.layers import merge
from keras.models import Model
from keras.preprocessing import image
from keras.utils.data_utils import get_file
from project_5_utils import Rectangle
WEIGHTS_URL = 'http://imagelab.ing.unimore.it/files/model_weights/SSD/weights_SSD300.hdf5'
voc_classes = ['Aeroplane', 'Bicycle', 'Bird', 'Boat', 'Bottle',
'Bus', 'Car', 'Cat', 'Chair', 'Cow', 'Diningtable',
'Dog', 'Horse', 'Motorbike', 'Person', 'Pottedplant',
'Sheep', 'Sofa', 'Train', 'Tvmonitor']
class BBoxUtility(object):
"""Utility class to do some stuff with bounding boxes and priors.
# Arguments
num_classes: Number of classes including background.
priors: Priors and variances, numpy tensor of shape (num_priors, 8),
priors[i] = [xmin, ymin, xmax, ymax, varxc, varyc, varw, varh].
overlap_threshold: Threshold to assign box to a prior.
nms_thresh: Nms threshold.
top_k: Number of total bboxes to be kept per image after nms step.
# References
https://arxiv.org/abs/1512.02325
"""
# TODO add setter methods for nms_thresh and top_K
def __init__(self, num_classes, priors=None, overlap_threshold=0.5,
nms_thresh=0.45, top_k=400):
self.num_classes = num_classes
self.priors = priors
self.num_priors = 0 if priors is None else len(priors)
self.overlap_threshold = overlap_threshold
self._nms_thresh = nms_thresh
self._top_k = top_k
self.boxes = tf.placeholder(dtype='float32', shape=(None, 4))
self.scores = tf.placeholder(dtype='float32', shape=(None,))
self.nms = tf.image.non_max_suppression(self.boxes, self.scores,
self._top_k,
iou_threshold=self._nms_thresh)
self.sess = tf.Session(config=tf.ConfigProto(device_count={'GPU': 0}))
@property
def nms_thresh(self):
return self._nms_thresh
@nms_thresh.setter
def nms_thresh(self, value):
self._nms_thresh = value
self.nms = tf.image.non_max_suppression(self.boxes, self.scores,
self._top_k,
iou_threshold=self._nms_thresh)
@property
def top_k(self):
return self._top_k
@top_k.setter
def top_k(self, value):
self._top_k = value
self.nms = tf.image.non_max_suppression(self.boxes, self.scores,
self._top_k,
iou_threshold=self._nms_thresh)
def iou(self, box):
"""Compute intersection over union for the box with all priors.
# Arguments
box: Box, numpy tensor of shape (4,).
# Return
iou: Intersection over union,
numpy tensor of shape (num_priors).
"""
# compute intersection
inter_upleft = np.maximum(self.priors[:, :2], box[:2])
inter_botright = np.minimum(self.priors[:, 2:4], box[2:])
inter_wh = inter_botright - inter_upleft
inter_wh = np.maximum(inter_wh, 0)
inter = inter_wh[:, 0] * inter_wh[:, 1]
# compute union
area_pred = (box[2] - box[0]) * (box[3] - box[1])
area_gt = (self.priors[:, 2] - self.priors[:, 0])
area_gt *= (self.priors[:, 3] - self.priors[:, 1])
union = area_pred + area_gt - inter
# compute iou
iou = inter / union
return iou
def encode_box(self, box, return_iou=True):
"""Encode box for training, do it only for assigned priors.
# Arguments
box: Box, numpy tensor of shape (4,).
return_iou: Whether to concat iou to encoded values.
# Return
encoded_box: Tensor with encoded box
numpy tensor of shape (num_priors, 4 + int(return_iou)).
"""
iou = self.iou(box)
encoded_box = np.zeros((self.num_priors, 4 + return_iou))
assign_mask = iou > self.overlap_threshold
if not assign_mask.any():
assign_mask[iou.argmax()] = True
if return_iou:
encoded_box[:, -1][assign_mask] = iou[assign_mask]
assigned_priors = self.priors[assign_mask]
box_center = 0.5 * (box[:2] + box[2:])
box_wh = box[2:] - box[:2]
assigned_priors_center = 0.5 * (assigned_priors[:, :2] +
assigned_priors[:, 2:4])
assigned_priors_wh = (assigned_priors[:, 2:4] -
assigned_priors[:, :2])
# we encode variance
encoded_box[:, :2][assign_mask] = box_center - assigned_priors_center
encoded_box[:, :2][assign_mask] /= assigned_priors_wh
encoded_box[:, :2][assign_mask] /= assigned_priors[:, -4:-2]
encoded_box[:, 2:4][assign_mask] = np.log(box_wh /
assigned_priors_wh)
encoded_box[:, 2:4][assign_mask] /= assigned_priors[:, -2:]
return encoded_box.ravel()
def assign_boxes(self, boxes):
"""Assign boxes to priors for training.
# Arguments
boxes: Box, numpy tensor of shape (num_boxes, 4 + num_classes),
num_classes without background.
# Return
assignment: Tensor with assigned boxes,
numpy tensor of shape (num_boxes, 4 + num_classes + 8),
priors in ground truth are fictitious,
assignment[:, -8] has 1 if prior should be penalized
or in other words is assigned to some ground truth box,
assignment[:, -7:] are all 0. See loss for more details.
"""
assignment = np.zeros((self.num_priors, 4 + self.num_classes + 8))
assignment[:, 4] = 1.0
if len(boxes) == 0:
return assignment
encoded_boxes = np.apply_along_axis(self.encode_box, 1, boxes[:, :4])
encoded_boxes = encoded_boxes.reshape(-1, self.num_priors, 5)
best_iou = encoded_boxes[:, :, -1].max(axis=0)
best_iou_idx = encoded_boxes[:, :, -1].argmax(axis=0)
best_iou_mask = best_iou > 0
best_iou_idx = best_iou_idx[best_iou_mask]
assign_num = len(best_iou_idx)
encoded_boxes = encoded_boxes[:, best_iou_mask, :]
assignment[:, :4][best_iou_mask] = encoded_boxes[best_iou_idx,
np.arange(assign_num),
:4]
assignment[:, 4][best_iou_mask] = 0
assignment[:, 5:-8][best_iou_mask] = boxes[best_iou_idx, 4:]
assignment[:, -8][best_iou_mask] = 1
return assignment
def decode_boxes(self, mbox_loc, mbox_priorbox, variances):
"""Convert bboxes from local predictions to shifted priors.
# Arguments
mbox_loc: Numpy array of predicted locations.
mbox_priorbox: Numpy array of prior boxes.
variances: Numpy array of variances.
# Return
decode_bbox: Shifted priors.
"""
prior_width = mbox_priorbox[:, 2] - mbox_priorbox[:, 0]
prior_height = mbox_priorbox[:, 3] - mbox_priorbox[:, 1]
prior_center_x = 0.5 * (mbox_priorbox[:, 2] + mbox_priorbox[:, 0])
prior_center_y = 0.5 * (mbox_priorbox[:, 3] + mbox_priorbox[:, 1])
decode_bbox_center_x = mbox_loc[:, 0] * prior_width * variances[:, 0]
decode_bbox_center_x += prior_center_x
decode_bbox_center_y = mbox_loc[:, 1] * prior_width * variances[:, 1]
decode_bbox_center_y += prior_center_y
decode_bbox_width = np.exp(mbox_loc[:, 2] * variances[:, 2])
decode_bbox_width *= prior_width
decode_bbox_height = np.exp(mbox_loc[:, 3] * variances[:, 3])
decode_bbox_height *= prior_height
decode_bbox_xmin = decode_bbox_center_x - 0.5 * decode_bbox_width
decode_bbox_ymin = decode_bbox_center_y - 0.5 * decode_bbox_height
decode_bbox_xmax = decode_bbox_center_x + 0.5 * decode_bbox_width
decode_bbox_ymax = decode_bbox_center_y + 0.5 * decode_bbox_height
decode_bbox = np.concatenate((decode_bbox_xmin[:, None],
decode_bbox_ymin[:, None],
decode_bbox_xmax[:, None],
decode_bbox_ymax[:, None]), axis=-1)
decode_bbox = np.minimum(np.maximum(decode_bbox, 0.0), 1.0)
return decode_bbox
def detection_out(self, predictions, background_label_id=0, keep_top_k=200,
confidence_threshold=0.01):
"""Do non maximum suppression (nms) on prediction results.
# Arguments
predictions: Numpy array of predicted values.
num_classes: Number of classes for prediction.
background_label_id: Label of background class.
keep_top_k: Number of total bboxes to be kept per image
after nms step.
confidence_threshold: Only consider detections,
whose confidences are larger than a threshold.
# Return
results: List of predictions for every picture. Each prediction is:
[label, confidence, xmin, ymin, xmax, ymax]
"""
mbox_loc = predictions[:, :, :4]
variances = predictions[:, :, -4:]
mbox_priorbox = predictions[:, :, -8:-4]
mbox_conf = predictions[:, :, 4:-8]
results = []
for i in range(len(mbox_loc)):
results.append([])
decode_bbox = self.decode_boxes(mbox_loc[i],
mbox_priorbox[i], variances[i])
for c in range(self.num_classes):
if c == background_label_id:
continue
c_confs = mbox_conf[i, :, c]
c_confs_m = c_confs > confidence_threshold
if len(c_confs[c_confs_m]) > 0:
boxes_to_process = decode_bbox[c_confs_m]
confs_to_process = c_confs[c_confs_m]
feed_dict = {self.boxes: boxes_to_process,
self.scores: confs_to_process}
idx = self.sess.run(self.nms, feed_dict=feed_dict)
good_boxes = boxes_to_process[idx]
confs = confs_to_process[idx][:, None]
labels = c * np.ones((len(idx), 1))
c_pred = np.concatenate((labels, confs, good_boxes),
axis=1)
results[-1].extend(c_pred)
if len(results[-1]) > 0:
results[-1] = np.array(results[-1])
argsort = np.argsort(results[-1][:, 1])[::-1]
results[-1] = results[-1][argsort]
results[-1] = results[-1][:keep_top_k]
return results
class Normalize(Layer):
"""Normalization layer as described in ParseNet paper.
# Arguments
scale: Default feature scale.
# Input shape
4D tensor with shape:
`(samples, channels, rows, cols)` if dim_ordering='th'
or 4D tensor with shape:
`(samples, rows, cols, channels)` if dim_ordering='tf'.
# Output shape
Same as input
# References
http://cs.unc.edu/~wliu/papers/parsenet.pdf
#TODO
Add possibility to have one scale for all features.
"""
def __init__(self, scale, **kwargs):
if K.image_dim_ordering() == 'tf':
self.axis = 3
else:
self.axis = 1
self.scale = scale
super(Normalize, self).__init__(**kwargs)
def build(self, input_shape):
self.input_spec = [InputSpec(shape=input_shape)]
shape = (input_shape[self.axis],)
init_gamma = self.scale * np.ones(shape)
self.gamma = K.variable(init_gamma, name='{}_gamma'.format(self.name))
self.trainable_weights = [self.gamma]
def call(self, x, mask=None):
output = K.l2_normalize(x, self.axis)
output *= self.gamma
return output
class PriorBox(Layer):
"""Generate the prior boxes of designated sizes and aspect ratios.
# Arguments
img_size: Size of the input image as tuple (w, h).
min_size: Minimum box size in pixels.
max_size: Maximum box size in pixels.
aspect_ratios: List of aspect ratios of boxes.
flip: Whether to consider reverse aspect ratios.
variances: List of variances for x, y, w, h.
clip: Whether to clip the prior's coordinates
such that they are within [0, 1].
# Input shape
4D tensor with shape:
`(samples, channels, rows, cols)` if dim_ordering='th'
or 4D tensor with shape:
`(samples, rows, cols, channels)` if dim_ordering='tf'.
# Output shape
3D tensor with shape:
(samples, num_boxes, 8)
# References
https://arxiv.org/abs/1512.02325
#TODO
Add possibility not to have variances.
Add Theano support
"""
def __init__(self, img_size, min_size, max_size=None, aspect_ratios=None,
flip=True, variances=[0.1], clip=True, **kwargs):
if K.image_dim_ordering() == 'tf':
self.waxis = 2
self.haxis = 1
else:
self.waxis = 3
self.haxis = 2
self.img_size = img_size
if min_size <= 0:
raise Exception('min_size must be positive.')
self.min_size = min_size
self.max_size = max_size
self.aspect_ratios = [1.0]
if max_size:
if max_size < min_size:
raise Exception('max_size must be greater than min_size.')
self.aspect_ratios.append(1.0)
if aspect_ratios:
for ar in aspect_ratios:
if ar in self.aspect_ratios:
continue
self.aspect_ratios.append(ar)
if flip:
self.aspect_ratios.append(1.0 / ar)
self.variances = np.array(variances)
self.clip = True
super(PriorBox, self).__init__(**kwargs)
def get_output_shape_for(self, input_shape):
num_priors_ = len(self.aspect_ratios)
layer_width = input_shape[self.waxis]
layer_height = input_shape[self.haxis]
num_boxes = num_priors_ * layer_width * layer_height
return (input_shape[0], num_boxes, 8)
def call(self, x, mask=None):
if hasattr(x, '_keras_shape'):
input_shape = x._keras_shape
elif hasattr(K, 'int_shape'):
input_shape = K.int_shape(x)
layer_width = input_shape[self.waxis]
layer_height = input_shape[self.haxis]
img_width = self.img_size[0]
img_height = self.img_size[1]
# define prior boxes shapes
box_widths = []
box_heights = []
for ar in self.aspect_ratios:
if ar == 1 and len(box_widths) == 0:
box_widths.append(self.min_size)
box_heights.append(self.min_size)
elif ar == 1 and len(box_widths) > 0:
box_widths.append(np.sqrt(self.min_size * self.max_size))
box_heights.append(np.sqrt(self.min_size * self.max_size))
elif ar != 1:
box_widths.append(self.min_size * np.sqrt(ar))
box_heights.append(self.min_size / np.sqrt(ar))
box_widths = 0.5 * np.array(box_widths)
box_heights = 0.5 * np.array(box_heights)
# define centers of prior boxes
step_x = img_width / layer_width
step_y = img_height / layer_height
linx = np.linspace(0.5 * step_x, img_width - 0.5 * step_x,
layer_width)
liny = np.linspace(0.5 * step_y, img_height - 0.5 * step_y,
layer_height)
centers_x, centers_y = np.meshgrid(linx, liny)
centers_x = centers_x.reshape(-1, 1)
centers_y = centers_y.reshape(-1, 1)
# define xmin, ymin, xmax, ymax of prior boxes
num_priors_ = len(self.aspect_ratios)
prior_boxes = np.concatenate((centers_x, centers_y), axis=1)
prior_boxes = np.tile(prior_boxes, (1, 2 * num_priors_))
prior_boxes[:, ::4] -= box_widths
prior_boxes[:, 1::4] -= box_heights
prior_boxes[:, 2::4] += box_widths
prior_boxes[:, 3::4] += box_heights
prior_boxes[:, ::2] /= img_width
prior_boxes[:, 1::2] /= img_height
prior_boxes = prior_boxes.reshape(-1, 4)
if self.clip:
prior_boxes = np.minimum(np.maximum(prior_boxes, 0.0), 1.0)
# define variances
num_boxes = len(prior_boxes)
if len(self.variances) == 1:
variances = np.ones((num_boxes, 4)) * self.variances[0]
elif len(self.variances) == 4:
variances = np.tile(self.variances, (num_boxes, 1))
else:
raise Exception('Must provide one or four variances.')
prior_boxes = np.concatenate((prior_boxes, variances), axis=1)
prior_boxes_tensor = K.expand_dims(K.variable(prior_boxes), 0)
if K.backend() == 'tensorflow':
pattern = [tf.shape(x)[0], 1, 1]
prior_boxes_tensor = tf.tile(prior_boxes_tensor, pattern)
elif K.backend() == 'theano':
#TODO
pass
return prior_boxes_tensor
def SSD300(input_shape, num_classes=21, pretrained=True):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Convolution2D(128, 3, 3,
activation='relu',
border_mode='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Convolution2D(128, 3, 3,
activation='relu',
border_mode='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Convolution2D(256, 3, 3,
activation='relu',
border_mode='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Convolution2D(256, 3, 3,
activation='relu',
border_mode='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Convolution2D(256, 3, 3,
activation='relu',
border_mode='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3), strides=(1, 1), border_mode='same',
name='pool5')(net['conv5_3'])
# FC6
net['fc6'] = AtrousConvolution2D(1024, 3, 3, atrous_rate=(6, 6),
activation='relu', border_mode='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024, 1, 1, activation='relu',
border_mode='same', name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256, 1, 1, activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Convolution2D(512, 3, 3, subsample=(2, 2),
activation='relu', border_mode='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128, 1, 1, activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256, 3, 3, subsample=(2, 2),
activation='relu', border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128, 1, 1, activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Convolution2D(256, 3, 3, subsample=(2, 2),
activation='relu', border_mode='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size, 30.0, aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4, 3, 3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes, 3, 3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size, 60.0, max_size=114.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size, 114.0, max_size=168.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size, 168.0, max_size=222.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size, 222.0, max_size=276.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size, 276.0, max_size=330.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = merge([net['conv4_3_norm_mbox_loc_flat'],
net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'],
net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'],
net['pool6_mbox_loc_flat']],
mode='concat', concat_axis=1, name='mbox_loc')
net['mbox_conf'] = merge([net['conv4_3_norm_mbox_conf_flat'],
net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'],
net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'],
net['pool6_mbox_conf_flat']],
mode='concat', concat_axis=1, name='mbox_conf')
net['mbox_priorbox'] = merge([net['conv4_3_norm_mbox_priorbox'],
net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'],
net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'],
net['pool6_mbox_priorbox']],
mode='concat', concat_axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge([net['mbox_loc'],
net['mbox_conf'],
net['mbox_priorbox']],
mode='concat', concat_axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
if pretrained:
pretrained_weights = get_file('SSD_pretrained.h5', origin=WEIGHTS_URL)
model.load_weights(pretrained_weights, by_name=True)
return model
def process_frame_bgr_with_SSD(frame_bgr, ssd_model, bbox_helper, allow_classes=None, min_confidence=0.2):
"""
Perform detection on one BGR frame and return list of detected objects.
Parameters
----------
frame_bgr : ndarray
Input frame give to be processed.
ssd_model : Keras Model
Pretrained model of SSD network.
bbox_helper : BBoxUtility
Helper for handling detection results.
allow_classes : list, default
If present, return only detections that belong to these classes.
min_confidence : float, default
Only detections whose confidence is greater than min_confidence are returned.
Returns
-------
results : list
List of detection results [class, confidence, x_min, y_min, x_max, y_max]
"""
frame_bgr = cv2.cvtColor(frame_bgr, cv2.COLOR_BGR2RGB)
inputs = []
img = image.img_to_array(cv2.resize(frame_bgr, (300, 300)))
inputs.append(img.copy())
inputs = preprocess_input(np.array(inputs))
preds = ssd_model.predict(inputs, batch_size=1, verbose=1)
results = bbox_helper.detection_out(preds, confidence_threshold=min_confidence)
results = results[0] # processing one frame, so remove batchsize
# eventually filter results keeping only certain classes
if allow_classes:
results = [r for r in results if int(r[0]) in allow_classes]
return results
def show_SSD_results(results, frame, color_palette, thickness=3):
"""
Show results of SSD detector drawing rectangles on the image.
"""
h, w = frame.shape[:2]
for row in results:
# parse row
label, confidence, x_min, y_min, x_max, y_max = row
# convert coordinates that belong to range (0, 1) back to image space (h, w)
x_min = int(round(x_min * w))
y_min = int(round(y_min * h))
x_max = int(round(x_max * w))
y_max = int(round(y_max * h))
label_text = voc_classes[int(label)-1]
bbox = Rectangle(x_min, y_min, x_max, y_max, label=label_text)
bbox.draw(frame, draw_label=True, color=color_palette[int(label)], thickness=thickness)
# cv2.rectangle(frame, (x_min, y_min), (x_max, y_max), color=color_palette[int(label)], thickness=thickness)
def get_SSD_model():
"""
Get SSD detection network pre-trained on Pascal VOC classes.
Parameters
----------
Returns
------
ssd_model : Keras Model
Pretrained model of SSD network.
bbox_helper : BBoxUtility
Helper for handling detection results.
colors_converted : list
Color palette to visualize detection results (21 colors such as Pascal VOC classes)
"""
voc_classes = ['Aeroplane', 'Bicycle', 'Bird', 'Boat', 'Bottle',
'Bus', 'Car', 'Cat', 'Chair', 'Cow', 'Diningtable',
'Dog', 'Horse', 'Motorbike', 'Person', 'Pottedplant',
'Sheep', 'Sofa', 'Train', 'Tvmonitor']
NUM_CLASSES = len(voc_classes) + 1
bbox_helper = BBoxUtility(NUM_CLASSES)
model_ssd = SSD300(input_shape=(300, 300, 3), num_classes=NUM_CLASSES, pretrained=True)
# load color palette and convert to BGR
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()
colors_converted = []
for i in range(len(colors)):
color_plt = colors[i]
color_cv2 = [c * 255 for c in color_plt]
color_cv2 = [color_cv2[2], color_cv2[1], color_cv2[0], color_cv2[3]]
colors_converted.append(color_cv2)
return model_ssd, bbox_helper, colors_converted
if __name__ == '__main__':
pass