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
|
import torch
import torch.nn as nn
import torch.nn.init as init
class Fire(nn.Module):
def __init__(self, inplanes, squeeze_planes, expand1x1_planes, expand3x3_planes):
super().__init__()
self.inplanes = inplanes
self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
self.squeeze_activation = nn.ReLU(inplace=True)
self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes, kernel_size=1)
self.expand1x1_activation = nn.ReLU(inplace=True)
self.expand3x3 = nn.Conv2d(
squeeze_planes, expand3x3_planes, kernel_size=3, padding=1
)
self.expand3x3_activation = nn.ReLU(inplace=True)
def forward(self, x):
x = self.squeeze_activation(self.squeeze(x))
return torch.cat(
[
self.expand1x1_activation(self.expand1x1(x)),
self.expand3x3_activation(self.expand3x3(x)),
],
1,
)
class SqueezeNet(nn.Module):
def __init__(self, version=1.0, num_classes=1000, ceil_mode=False):
super().__init__()
if version not in [1.0, 1.1]:
raise ValueError(
"Unsupported SqueezeNet version {version}:"
"1.0 or 1.1 expected".format(version=version)
)
self.num_classes = num_classes
if version == 1.0:
self.features = nn.Sequential(
nn.Conv2d(3, 96, kernel_size=7, stride=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=ceil_mode),
Fire(96, 16, 64, 64),
Fire(128, 16, 64, 64),
Fire(128, 32, 128, 128),
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=ceil_mode),
Fire(256, 32, 128, 128),
Fire(256, 48, 192, 192),
Fire(384, 48, 192, 192),
Fire(384, 64, 256, 256),
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=ceil_mode),
Fire(512, 64, 256, 256),
)
else:
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, stride=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=ceil_mode),
Fire(64, 16, 64, 64),
Fire(128, 16, 64, 64),
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=ceil_mode),
Fire(128, 32, 128, 128),
Fire(256, 32, 128, 128),
nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=ceil_mode),
Fire(256, 48, 192, 192),
Fire(384, 48, 192, 192),
Fire(384, 64, 256, 256),
Fire(512, 64, 256, 256),
)
# Final convolution is initialized differently from the rest
final_conv = nn.Conv2d(512, self.num_classes, kernel_size=1)
self.classifier = nn.Sequential(
nn.Dropout(p=0.5), final_conv, nn.ReLU(inplace=True), nn.AvgPool2d(13)
)
for m in self.modules():
if isinstance(m, nn.Conv2d):
if m is final_conv:
init.normal_(m.weight.data, mean=0.0, std=0.01)
else:
init.kaiming_uniform_(m.weight.data)
if m.bias is not None:
m.bias.data.zero_()
def forward(self, x):
x = self.features(x)
x = self.classifier(x)
return x.view(x.size(0), self.num_classes)
|
