-
Notifications
You must be signed in to change notification settings - Fork 15
/
Copy pathmodel_resnet.py
205 lines (161 loc) · 6.57 KB
/
model_resnet.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
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
import torch
import torch.nn as nn
import torch.nn.functional as F
import math
from torch.nn import init
from cbam import *
from bam import *
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, use_cbam=False):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
if use_cbam:
self.cbam = CBAM( planes, 16 )
else:
self.cbam = None
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
if not self.cbam is None:
out = self.cbam(out)
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, use_cbam=False):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, 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, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
if use_cbam:
self.cbam = CBAM( planes * 4, 16 )
else:
self.cbam = None
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
if not self.cbam is None:
out = self.cbam(out)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, network_type, num_classes, att_type=None):
self.inplanes = 64
super(ResNet, self).__init__()
self.network_type = network_type
# different model config between ImageNet and CIFAR
if network_type == "ImageNet":
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.avgpool = nn.AvgPool2d(7)
else:
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
if att_type=='BAM':
self.bam1 = BAM(64*block.expansion)
self.bam2 = BAM(128*block.expansion)
self.bam3 = BAM(256*block.expansion)
else:
self.bam1, self.bam2, self.bam3 = None, None, None
self.layer1 = self._make_layer(block, 64, layers[0], att_type=att_type)
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, att_type=att_type)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2, att_type=att_type)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2, att_type=att_type)
self.fc = nn.Linear(512 * block.expansion, num_classes)
init.kaiming_normal(self.fc.weight)
for key in self.state_dict():
if key.split('.')[-1]=="weight":
if "conv" in key:
init.kaiming_normal(self.state_dict()[key], mode='fan_out')
if "bn" in key:
if "SpatialGate" in key:
self.state_dict()[key][...] = 0
else:
self.state_dict()[key][...] = 1
elif key.split(".")[-1]=='bias':
self.state_dict()[key][...] = 0
def _make_layer(self, block, planes, blocks, stride=1, att_type=None):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, use_cbam=att_type=='CBAM'))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, use_cbam=att_type=='CBAM'))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
if self.network_type == "ImageNet":
x = self.maxpool(x)
x = self.layer1(x)
if not self.bam1 is None:
x = self.bam1(x)
x = self.layer2(x)
if not self.bam2 is None:
x = self.bam2(x)
x = self.layer3(x)
if not self.bam3 is None:
x = self.bam3(x)
x = self.layer4(x)
if self.network_type == "ImageNet":
x = self.avgpool(x)
else:
x = F.avg_pool2d(x, 4)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def ResidualNet(network_type, depth, num_classes, att_type):
assert network_type in ["ImageNet", "CIFAR10", "CIFAR100"], "network type should be ImageNet or CIFAR10 / CIFAR100"
assert depth in [18, 34, 50, 101], 'network depth should be 18, 34, 50 or 101'
if depth == 18:
model = ResNet(BasicBlock, [2, 2, 2, 2], network_type, num_classes, att_type)
elif depth == 34:
model = ResNet(BasicBlock, [3, 4, 6, 3], network_type, num_classes, att_type)
elif depth == 50:
model = ResNet(Bottleneck, [3, 4, 6, 3], network_type, num_classes, att_type)
elif depth == 101:
model = ResNet(Bottleneck, [3, 4, 23, 3], network_type, num_classes, att_type)
return model