-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathresnet_rpn_loss_layer.py
170 lines (125 loc) · 6.4 KB
/
resnet_rpn_loss_layer.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
# -*- coding: utf-8 -*-
"""
Created on 2018/11/19 15:32
@author: royce.mao
# 把loss写进resnet_rpn网络的layer，原第1阶段
"""
# -*- coding: utf-8 -*-
'''ResNet50 model for Keras.
# Reference:
- [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
Adapted from code contributed by BigMoyan.
'''
from keras.layers import Input, Add, Dense, Activation, Flatten, Convolution2D, MaxPooling2D, ZeroPadding2D, \
AveragePooling2D, TimeDistributed, Lambda
from keras import backend as K
from losses_loss_layer import rpn_loss_cls, rpn_loss_regr
from roi_pooling_conv import RoiPoolingConv
from fixed_batch_normalization import FixedBatchNormalization
def get_weight_path():
if K.image_dim_ordering() == 'th':
return 'resnet50_weights_th_dim_ordering_th_kernels_notop.h5'
else:
return 'resnet50_weights_tf_dim_ordering_tf_kernels.h5'
def get_img_output_length(width, height):
def get_output_length(input_length):
# zero_pad
input_length += 6
# apply 4 strided convolutions
filter_sizes = [7, 3, 1, 1]
stride = 2
for filter_size in filter_sizes:
input_length = (input_length - filter_size + stride) // stride
return input_length
return get_output_length(width), get_output_length(height)
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):
nb_filter1, nb_filter2, nb_filter3 = filters
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Convolution2D(nb_filter1, (1, 1), name=conv_name_base + '2a', trainable=trainable)(input_tensor)
x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b',
trainable=trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
x = Add()([x, input_tensor])
x = Activation('relu')(x)
return x
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):
nb_filter1, nb_filter2, nb_filter3 = filters
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(
input_tensor)
x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b',
trainable=trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(
input_tensor)
shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)
x = Add()([x, shortcut])
x = Activation('relu')(x)
return x
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, (7, 7), strides=(2, 2), name='conv1', trainable=trainable)(x)
# NOTE: this code only support to keras 2.0.3, newest version this line will got errors.
x = FixedBatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), trainable=trainable)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', trainable=trainable)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', trainable=trainable)
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', trainable=trainable)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', trainable=trainable)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', trainable=trainable)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', trainable=trainable)
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', trainable=trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b', trainable=trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c', trainable=trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d', trainable=trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e', trainable=trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f', trainable=trainable)
return x
def rpn(base_layers, num_anchors, x_target_cls, x_target_regr):
x = Convolution2D(512, (3, 3), padding='same', activation='relu', kernel_initializer='normal', name='rpn_conv1')(
base_layers)
x_class = Convolution2D(num_anchors, (1, 1), activation='sigmoid', kernel_initializer='uniform',
name='rpn_out_class')(x)
x_regr = Convolution2D(num_anchors * 4, (1, 1), activation='linear', kernel_initializer='zero',
name='rpn_out_regress')(x)
x_loss_cls = Lambda(lambda x: rpn_loss_cls(*x), name='x_cls_loss')([x_target_cls, x_class])
x_loss_regr = Lambda(lambda x: rpn_loss_regr(*x), name='x_regr_loss')([x_target_regr, x_regr])
return [x_class, x_regr], [x_loss_cls, x_loss_regr]