-
Notifications
You must be signed in to change notification settings - Fork 24
/
resnet_small.py
175 lines (131 loc) · 5.09 KB
/
resnet_small.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
import torch
import torch.nn as nn
import math
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):
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
def forward(self, 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)
else:
residual = x
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion=4
def __init__(self, inplanes, planes, stride=1, downsample=None):
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
def forward(self, 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)
else:
residual = x
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, channels=[16, 32, 64], flatten=True):
super(ResNet, self).__init__()
self.name = "resnet"
self.flatten = flatten
self.channels = channels
self.inplanes = channels[0]
self.conv1 = nn.Conv2d(3, channels[0], kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(channels[0])
self.relu = nn.ReLU(inplace=True)
self.layer1 = self._make_layer(block, channels[0], layers[0])
self.layer2 = self._make_layer(block, channels[1], layers[1], stride=2)
self.layer3 = self._make_layer(block, channels[2], layers[2], stride=2)
#self.avgpool = nn.AvgPool2d(8, stride=1)
self.avgpool = nn.AdaptiveAvgPool2d(1) #global pooling
if(flatten): self.feature_size = channels[2]*block.expansion
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1):
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))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
if(self.flatten):
x = self.avgpool(x)
x = x.view(x.size(0), -1)
#x = self.fc(x)
return x
def resnet20_cifar(**kwargs):
model = ResNet_Cifar(BasicBlock, [3, 3, 3], **kwargs)
return model
def resnet32_cifar(**kwargs):
model = ResNet_Cifar(BasicBlock, [5, 5, 5], **kwargs)
return model
def resnet44_cifar(**kwargs):
model = ResNet_Cifar(BasicBlock, [7, 7, 7], **kwargs)
return model
def resnet56_cifar(**kwargs):
model = ResNet_Cifar(BasicBlock, [9, 9, 9], **kwargs)
return model
def resnet110_cifar(**kwargs):
model = ResNet_Cifar(BasicBlock, [18, 18, 18], **kwargs)
return model
def resnet1202_cifar(**kwargs):
model = ResNet_Cifar(BasicBlock, [200, 200, 200], **kwargs)
return model
def resnet164_cifar(**kwargs):
model = ResNet_Cifar(Bottleneck, [18, 18, 18], **kwargs)
return model
def resnet1001_cifar(**kwargs):
model = ResNet_Cifar(Bottleneck, [111, 111, 111], **kwargs)
return model