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
| """senet in pytorch
[1] Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu
Squeeze-and-Excitation Networks
https://arxiv.org/abs/1709.01507
"""
import torch
import torch.nn as nn
import torch.nn.functional as F
class BasicResidualSEBlock(nn.Module):
expansion = 1
def __init__(self, in_channels, out_channels, stride, r=16):
super().__init__()
self.residual = nn.Sequential(
nn.Conv2d(in_channels, out_channels, 3, stride=stride, padding=1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Conv2d(out_channels, out_channels * self.expansion, 3, padding=1),
nn.BatchNorm2d(out_channels * self.expansion),
nn.ReLU(inplace=True)
)
self.shortcut = nn.Sequential()
if stride != 1 or in_channels != out_channels * self.expansion:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels, out_channels * self.expansion, 1, stride=stride),
nn.BatchNorm2d(out_channels * self.expansion)
)
self.squeeze = nn.AdaptiveAvgPool2d(1)
self.excitation = nn.Sequential(
nn.Linear(out_channels * self.expansion, out_channels * self.expansion // r),
nn.ReLU(inplace=True),
nn.Linear(out_channels * self.expansion // r, out_channels * self.expansion),
nn.Sigmoid()
)
def forward(self, x):
shortcut = self.shortcut(x)
residual = self.residual(x)
squeeze = self.squeeze(residual)
squeeze = squeeze.view(squeeze.size(0), -1)
excitation = self.excitation(squeeze)
excitation = excitation.view(residual.size(0), residual.size(1), 1, 1)
x = residual * excitation.expand_as(residual) + shortcut
return F.relu(x)
class BottleneckResidualSEBlock(nn.Module):
expansion = 4
def __init__(self, in_channels, out_channels, stride, r=16):
super().__init__()
self.residual = nn.Sequential(
nn.Conv2d(in_channels, out_channels, 1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Conv2d(out_channels, out_channels, 3, stride=stride, padding=1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Conv2d(out_channels, out_channels * self.expansion, 1),
nn.BatchNorm2d(out_channels * self.expansion),
nn.ReLU(inplace=True)
)
self.squeeze = nn.AdaptiveAvgPool2d(1)
self.excitation = nn.Sequential(
nn.Linear(out_channels * self.expansion, out_channels * self.expansion // r),
nn.ReLU(inplace=True),
nn.Linear(out_channels * self.expansion // r, out_channels * self.expansion),
nn.Sigmoid()
)
self.shortcut = nn.Sequential()
if stride != 1 or in_channels != out_channels * self.expansion:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels, out_channels * self.expansion, 1, stride=stride),
nn.BatchNorm2d(out_channels * self.expansion)
)
def forward(self, x):
shortcut = self.shortcut(x)
residual = self.residual(x)
squeeze = self.squeeze(residual)
squeeze = squeeze.view(squeeze.size(0), -1)
excitation = self.excitation(squeeze)
excitation = excitation.view(residual.size(0), residual.size(1), 1, 1)
x = residual * excitation.expand_as(residual) + shortcut
return F.relu(x)
class SEResNet(nn.Module):
def __init__(self, block, block_num, class_num=100):
super().__init__()
self.in_channels = 64
self.pre = nn.Sequential(
nn.Conv2d(3, 64, 3, padding=1),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True)
)
self.stage1 = self._make_stage(block, block_num[0], 64, 1)
self.stage2 = self._make_stage(block, block_num[1], 128, 2)
self.stage3 = self._make_stage(block, block_num[2], 256, 2)
self.stage4 = self._make_stage(block, block_num[3], 512, 2)
self.linear = nn.Linear(self.in_channels, class_num)
def forward(self, x):
x = self.pre(x)
x = self.stage1(x)
x = self.stage2(x)
x = self.stage3(x)
x = self.stage4(x)
x = F.adaptive_avg_pool2d(x, 1)
x = x.view(x.size(0), -1)
x = self.linear(x)
return x
def _make_stage(self, block, num, out_channels, stride):
layers = []
layers.append(block(self.in_channels, out_channels, stride))
self.in_channels = out_channels * block.expansion
while num - 1:
layers.append(block(self.in_channels, out_channels, 1))
num -= 1
return nn.Sequential(*layers)
def seresnet18():
return SEResNet(BasicResidualSEBlock, [2, 2, 2, 2])
def seresnet34():
return SEResNet(BasicResidualSEBlock, [3, 4, 6, 3])
def seresnet50():
return SEResNet(BottleneckResidualSEBlock, [3, 4, 6, 3])
def seresnet101():
return SEResNet(BottleneckResidualSEBlock, [3, 4, 23, 3])
def seresnet152():
return SEResNet(BottleneckResidualSEBlock, [3, 8, 36, 3])
|
