-
Notifications
You must be signed in to change notification settings - Fork 161
/
mobilenet_v2.py
178 lines (134 loc) · 5.92 KB
/
mobilenet_v2.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
"""MobileNet v2 models for Keras.
# Reference
- [Inverted Residuals and Linear Bottlenecks Mobile Networks for
Classification, Detection and Segmentation]
(https://arxiv.org/abs/1801.04381)
"""
from keras.models import Model
from keras.layers import Input, Conv2D, GlobalAveragePooling2D, Dropout
from keras.layers import Activation, BatchNormalization, Add, Reshape, DepthwiseConv2D
from keras.utils.vis_utils import plot_model
from keras import backend as K
def _make_divisible(v, divisor, min_value=None):
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < 0.9 * v:
new_v += divisor
return new_v
def relu6(x):
"""Relu 6
"""
return K.relu(x, max_value=6.0)
def _conv_block(inputs, filters, kernel, strides):
"""Convolution Block
This function defines a 2D convolution operation with BN and relu6.
# Arguments
inputs: Tensor, input tensor of conv layer.
filters: Integer, the dimensionality of the output space.
kernel: An integer or tuple/list of 2 integers, specifying the
width and height of the 2D convolution window.
strides: An integer or tuple/list of 2 integers,
specifying the strides of the convolution along the width and height.
Can be a single integer to specify the same value for
all spatial dimensions.
# Returns
Output tensor.
"""
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = Conv2D(filters, kernel, padding='same', strides=strides)(inputs)
x = BatchNormalization(axis=channel_axis)(x)
return Activation(relu6)(x)
def _bottleneck(inputs, filters, kernel, t, alpha, s, r=False):
"""Bottleneck
This function defines a basic bottleneck structure.
# Arguments
inputs: Tensor, input tensor of conv layer.
filters: Integer, the dimensionality of the output space.
kernel: An integer or tuple/list of 2 integers, specifying the
width and height of the 2D convolution window.
t: Integer, expansion factor.
t is always applied to the input size.
s: An integer or tuple/list of 2 integers,specifying the strides
of the convolution along the width and height.Can be a single
integer to specify the same value for all spatial dimensions.
alpha: Integer, width multiplier.
r: Boolean, Whether to use the residuals.
# Returns
Output tensor.
"""
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
# Depth
tchannel = K.int_shape(inputs)[channel_axis] * t
# Width
cchannel = int(filters * alpha)
x = _conv_block(inputs, tchannel, (1, 1), (1, 1))
x = DepthwiseConv2D(kernel, strides=(s, s), depth_multiplier=1, padding='same')(x)
x = BatchNormalization(axis=channel_axis)(x)
x = Activation(relu6)(x)
x = Conv2D(cchannel, (1, 1), strides=(1, 1), padding='same')(x)
x = BatchNormalization(axis=channel_axis)(x)
if r:
x = Add()([x, inputs])
return x
def _inverted_residual_block(inputs, filters, kernel, t, alpha, strides, n):
"""Inverted Residual Block
This function defines a sequence of 1 or more identical layers.
# Arguments
inputs: Tensor, input tensor of conv layer.
filters: Integer, the dimensionality of the output space.
kernel: An integer or tuple/list of 2 integers, specifying the
width and height of the 2D convolution window.
t: Integer, expansion factor.
t is always applied to the input size.
alpha: Integer, width multiplier.
s: An integer or tuple/list of 2 integers,specifying the strides
of the convolution along the width and height.Can be a single
integer to specify the same value for all spatial dimensions.
n: Integer, layer repeat times.
# Returns
Output tensor.
"""
x = _bottleneck(inputs, filters, kernel, t, alpha, strides)
for i in range(1, n):
x = _bottleneck(x, filters, kernel, t, alpha, 1, True)
return x
def MobileNetv2(input_shape, k, alpha=1.0):
"""MobileNetv2
This function defines a MobileNetv2 architectures.
# Arguments
input_shape: An integer or tuple/list of 3 integers, shape
of input tensor.
k: Integer, number of classes.
alpha: Integer, width multiplier, better in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4].
# Returns
MobileNetv2 model.
"""
inputs = Input(shape=input_shape)
first_filters = _make_divisible(32 * alpha, 8)
x = _conv_block(inputs, first_filters, (3, 3), strides=(2, 2))
x = _inverted_residual_block(x, 16, (3, 3), t=1, alpha=alpha, strides=1, n=1)
x = _inverted_residual_block(x, 24, (3, 3), t=6, alpha=alpha, strides=2, n=2)
x = _inverted_residual_block(x, 32, (3, 3), t=6, alpha=alpha, strides=2, n=3)
x = _inverted_residual_block(x, 64, (3, 3), t=6, alpha=alpha, strides=2, n=4)
x = _inverted_residual_block(x, 96, (3, 3), t=6, alpha=alpha, strides=1, n=3)
x = _inverted_residual_block(x, 160, (3, 3), t=6, alpha=alpha, strides=2, n=3)
x = _inverted_residual_block(x, 320, (3, 3), t=6, alpha=alpha, strides=1, n=1)
if alpha > 1.0:
last_filters = _make_divisible(1280 * alpha, 8)
else:
last_filters = 1280
x = _conv_block(x, last_filters, (1, 1), strides=(1, 1))
x = GlobalAveragePooling2D()(x)
x = Reshape((1, 1, last_filters))(x)
x = Dropout(0.3, name='Dropout')(x)
x = Conv2D(k, (1, 1), padding='same')(x)
x = Activation('softmax', name='softmax')(x)
output = Reshape((k,))(x)
model = Model(inputs, output)
# plot_model(model, to_file='images/MobileNetv2.png', show_shapes=True)
return model
if __name__ == '__main__':
model = MobileNetv2((224, 224, 3), 100, 1.0)
print(model.summary())