-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathcbam.py
170 lines (138 loc) · 6.55 KB
/
cbam.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
#本文件定义了CBAM-ResNet18模型
import torch
import torch.nn as nn
import torch.nn.functional as F
class ChannelAttention(nn.Module): # Channel Attention Module
def __init__(self, in_planes):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.fc1 = nn.Conv2d(in_planes, in_planes // 16, kernel_size=1, bias=False)
self.relu = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, kernel_size=1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.avg_pool(x)
avg_out = self.fc1(avg_out)
avg_out = self.relu(avg_out)
avg_out = self.fc2(avg_out)
max_out = self.max_pool(x)
max_out = self.fc1(max_out)
max_out = self.relu(max_out)
max_out = self.fc2(max_out)
out = avg_out + max_out
out = self.sigmoid(out)
return out
class SpatialAttention(nn.Module): # Spatial Attention Module
def __init__(self):
super(SpatialAttention, self).__init__()
self.conv1 = nn.Conv2d(2, 1, kernel_size=7, padding=3, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
out = torch.cat([avg_out, max_out], dim=1)
out = self.conv1(out)
out = self.sigmoid(out)
return out
class BasicBlock(nn.Module): # 左侧的 residual block 结构（18-layer、34-layer）
expansion = 1
def __init__(self, in_planes, planes, stride=1): # 两层卷积 Conv2d + Shutcuts
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3,
stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3,
stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.channel = ChannelAttention(self.expansion*planes) # Channel Attention Module
self.spatial = SpatialAttention() # Spatial Attention Module
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes: # Shutcuts用于构建 Conv Block 和 Identity Block
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
CBAM_Cout = self.channel(out)
out = out * CBAM_Cout
CBAM_Sout = self.spatial(out)
out = out * CBAM_Sout
out += self.shortcut(x)
out = F.relu(out)
return out
class Bottleneck(nn.Module): # 右侧的 residual block 结构（50-layer、101-layer、152-layer）
expansion = 4
def __init__(self, in_planes, planes, stride=1): # 三层卷积 Conv2d + Shutcuts
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3,
stride=stride, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, self.expansion*planes,
kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion*planes)
self.channel = ChannelAttention(self.expansion*planes) # Channel Attention Module
self.spatial = SpatialAttention() # Spatial Attention Module
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes: # Shutcuts用于构建 Conv Block 和 Identity Block
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = F.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
CBAM_Cout = self.channel(out)
out = out * CBAM_Cout
CBAM_Sout = self.spatial(out)
out = out * CBAM_Sout
out += self.shortcut(x)
out = F.relu(out)
return out
class CBAM_ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=len(most_represented_birds)):
super(CBAM_ResNet, self).__init__()
self.in_planes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3,
stride=1, padding=1, bias=False) # conv1
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1) # conv2_x
self.dropout1 = nn.Dropout(p=0.2)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2) # conv3_x
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2) # conv4_x
self.dropout2 = nn.Dropout(p=0.2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2) # conv5_x
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout3 = nn.Dropout(p=0.5)
self.linear = nn.Linear(512 * block.expansion, num_classes)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x)))
x = self.layer1(x)
x = self.dropout1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.dropout2(x)
x = self.layer4(x)
x = self.avgpool(x)
x = self.dropout3(x)
x = torch.flatten(x, 1)
out = self.linear(x)
return out
def CBAM_ResNet18():
return CBAM_ResNet(BasicBlock, [2, 2, 2, 2])
def CBAM_ResNet34():
return CBAM_ResNet(BasicBlock, [3, 4, 6, 3])