-
Notifications
You must be signed in to change notification settings - Fork 0
/
resnet.py
103 lines (78 loc) · 3.04 KB
/
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
import torch
import torch.nn as nn
import torch.nn.functional as F
def conv1x1(in_planes, planes, stride=1):
return nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride, bias=False)
def conv3x3(in_planes, planes, stride=1):
return nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
def _weights_init(m):
classname = m.__class__.__name__
print(classname)
if isinstance(m, nn.Linear) or isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight)
class LambdaLayer(nn.Module):
def __init__(self, lambd):
super(LambdaLayer, self).__init__()
self.lambd = lambd
def forward(self, x):
return self.lambd(x)
class Block(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1, option='A'):
super(Block, self).__init__()
self.conv1 = conv3x3(in_planes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = conv3x3(planes, planes, 1)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != planes:
if option == 'A':
self.shortcut = LambdaLayer(lambda x:
F.pad(x[:, :, ::2, ::2], (0, 0, 0, 0, planes//4, planes//4), "constant", 0))
elif option == 'B':
self.shortcut = nn.Sequential(
conv1x1(in_planes, self.expansion * planes, stride),
nn.BatchNorm2d(self.expansion * planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, num_blocks, num_classes=10):
super(ResNet, self).__init__()
self.in_planes = 16
self.conv1 = conv3x3(3, 16)
self.bn1 = nn.BatchNorm2d(16)
self.layer1 = self._make_layer(16, num_blocks[0], stride=1)
self.layer2 = self._make_layer(32, num_blocks[1], stride=2)
self.layer3 = self._make_layer(64, num_blocks[2], stride=2)
self.linear = nn.Linear(64, num_classes)
self.apply(_weights_init)
def _make_layer(self, planes, num_blocks, stride):
layers = [Block(self.in_planes, planes, stride)]
self.in_planes = planes * Block.expansion
for _ in range(1, num_blocks):
layers.append(Block(self.in_planes, planes))
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = F.avg_pool2d(out, out.size()[3])
out = out.view(out.size(0), -1)
out = self.linear(out)
return out
def ResNet20():
return ResNet([3, 3, 3])
def ResNet32():
return ResNet([5, 5, 5])
def ResNet44():
return ResNet([7, 7, 7])
def ResNet56():
return ResNet([9, 9, 9])
def ResNet110():
return ResNet([18, 18, 18])