-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbackbones.py
135 lines (116 loc) · 3.96 KB
/
backbones.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
import torch
import torch.nn as nn
from torchvision import models
import torch.nn.functional as F
import math
resnet_dict = {
"resnet18": models.resnet18,
"resnet34": models.resnet34,
"resnet50": models.resnet50,
"resnet101": models.resnet101,
"resnet152": models.resnet152,
}
weights = {
"resnet18": models.ResNet18_Weights.DEFAULT,
"resnet34": models.ResNet34_Weights.DEFAULT,
"resnet50": models.ResNet50_Weights.DEFAULT,
"resnet101": models.ResNet101_Weights.DEFAULT,
"resnet152": models.ResNet152_Weights.DEFAULT,
}
def get_backbone(name):
if "cbam" == name.lower():
return CBAMBackbone()
def __init__(self, network_type):
super(ResNetBackbone, self).__init__()
resnet = resnet_dict[network_type](weights=weights[network_type])
# resnet = resnet_dict[network_type]()
self.conv1 = resnet.conv1
self.bn1 = resnet.bn1
self.relu = resnet.relu
self.maxpool = resnet.maxpool
self.layer1 = resnet.layer1
self.layer2 = resnet.layer2
self.layer3 = resnet.layer3
self.layer4 = resnet.layer4
self.avgpool = resnet.avgpool
self._feature_dim = resnet.fc.in_features
del resnet
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
return x
def output_num(self):
return self._feature_dim
'''
CBAM
'''
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
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, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
out = avg_out + max_out
return self.sigmoid(out)
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, 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)
x = torch.cat([avg_out, max_out], dim=1)
x = self.conv1(x)
return self.sigmoid(x)
class CBAMBackbone(nn.Module):
def __init__(self, ):
super(CBAMBackbone, self).__init__()
resnet = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)
self.ca = ChannelAttention(64)
self.sa = SpatialAttention()
self.conv1 = resnet.conv1
self.bn1 = resnet.bn1
self.relu = resnet.relu
self.maxpool = resnet.maxpool
self.layer1 = resnet.layer1
self.layer2 = resnet.layer2
self.layer3 = resnet.layer3
self.layer4 = resnet.layer4
self.ca1 = ChannelAttention(512)
self.sa1 = SpatialAttention()
self.avgpool = resnet.avgpool
self._feature_dim = resnet.fc.in_features
del resnet
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.ca1(x) * x
x = self.sa1(x) * x
x = self.avgpool(x)
x = x.view(x.size(0), -1)
return x
def output_num(self):
return self._feature_dim