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
| """mobilenet in pytorch
[1] Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
https://arxiv.org/abs/1704.04861
"""
import torch
import torch.nn as nn
class DepthSeperabelConv2d(nn.Module):
def __init__(self, input_channels, output_channels, kernel_size, **kwargs):
super().__init__()
self.depthwise = nn.Sequential(
nn.Conv2d(
input_channels,
input_channels,
kernel_size,
groups=input_channels,
**kwargs),
nn.BatchNorm2d(input_channels),
nn.ReLU(inplace=True)
)
self.pointwise = nn.Sequential(
nn.Conv2d(input_channels, output_channels, 1),
nn.BatchNorm2d(output_channels),
nn.ReLU(inplace=True)
)
def forward(self, x):
x = self.depthwise(x)
x = self.pointwise(x)
return x
class BasicConv2d(nn.Module):
def __init__(self, input_channels, output_channels, kernel_size, **kwargs):
super().__init__()
self.conv = nn.Conv2d(
input_channels, output_channels, kernel_size, **kwargs)
self.bn = nn.BatchNorm2d(output_channels)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
x = self.relu(x)
return x
class MobileNet(nn.Module):
"""
Args:
width multipler: The role of the width multiplier α is to thin
a network uniformly at each layer. For a given
layer and width multiplier α, the number of
input channels M becomes αM and the number of
output channels N becomes αN.
"""
def __init__(self, width_multiplier=1, class_num=100):
super().__init__()
alpha = width_multiplier
self.stem = nn.Sequential(
BasicConv2d(3, int(32 * alpha), 3, padding=1, bias=False),
DepthSeperabelConv2d(
int(32 * alpha),
int(64 * alpha),
3,
padding=1,
bias=False
)
)
self.conv1 = nn.Sequential(
DepthSeperabelConv2d(
int(64 * alpha),
int(128 * alpha),
3,
stride=2,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(128 * alpha),
int(128 * alpha),
3,
padding=1,
bias=False
)
)
self.conv2 = nn.Sequential(
DepthSeperabelConv2d(
int(128 * alpha),
int(256 * alpha),
3,
stride=2,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(256 * alpha),
int(256 * alpha),
3,
padding=1,
bias=False
)
)
self.conv3 = nn.Sequential(
DepthSeperabelConv2d(
int(256 * alpha),
int(512 * alpha),
3,
stride=2,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(512 * alpha),
int(512 * alpha),
3,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(512 * alpha),
int(512 * alpha),
3,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(512 * alpha),
int(512 * alpha),
3,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(512 * alpha),
int(512 * alpha),
3,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(512 * alpha),
int(512 * alpha),
3,
padding=1,
bias=False
)
)
self.conv4 = nn.Sequential(
DepthSeperabelConv2d(
int(512 * alpha),
int(1024 * alpha),
3,
stride=2,
padding=1,
bias=False
),
DepthSeperabelConv2d(
int(1024 * alpha),
int(1024 * alpha),
3,
padding=1,
bias=False
)
)
self.fc = nn.Linear(int(1024 * alpha), class_num)
self.avg = nn.AdaptiveAvgPool2d(1)
def forward(self, x):
x = self.stem(x)
x = self.conv1(x)
x = self.conv2(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.avg(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def mobilenet(alpha=1, class_num=100):
return MobileNet(alpha, class_num)
|
