-
Notifications
You must be signed in to change notification settings - Fork 37
/
vgg.py
160 lines (141 loc) · 4.49 KB
/
vgg.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
import oneflow as flow
import oneflow.nn as nn
from typing import Union, List, Dict, Any, cast
__all__ = [
"vgg16",
"vgg16_bn",
"vgg19_bn",
"vgg19",
]
class VGG(nn.Module):
def __init__(
self, features: nn.Module, num_classes: int = 1000, init_weights: bool = True
) -> None:
super(VGG, self).__init__()
self.features = features
self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
self.classifier = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x: flow.Tensor) -> flow.Tensor:
x = self.features(x)
x = self.avgpool(x)
x = flow.flatten(x, 1)
x = self.classifier(x)
return x
def _initialize_weights(self) -> None:
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
def make_layers(cfg: List[Union[str, int]], batch_norm: bool = False) -> nn.Sequential:
layers: List[nn.Module] = []
in_channels = 3
for v in cfg:
if v == "M":
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
v = cast(int, v)
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
cfgs: Dict[str, List[Union[str, int]]] = {
"A": [64, "M", 128, "M", 256, 256, "M", 512, 512, "M", 512, 512, "M"],
"B": [64, 64, "M", 128, 128, "M", 256, 256, "M", 512, 512, "M", 512, 512, "M"],
"D": [
64,
64,
"M",
128,
128,
"M",
256,
256,
256,
"M",
512,
512,
512,
"M",
512,
512,
512,
"M",
],
"E": [
64,
64,
"M",
128,
128,
"M",
256,
256,
256,
256,
"M",
512,
512,
512,
512,
"M",
512,
512,
512,
512,
"M",
],
}
def _vgg(arch: str, cfg: str, batch_norm: bool) -> VGG:
return VGG(make_layers(cfgs[cfg], batch_norm=batch_norm))
def vgg16() -> VGG:
r"""VGG 16-layer model (configuration "D")
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_.
The required minimum input size of the model is 32x32.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
return _vgg("vgg16", "D", False)
def vgg16_bn() -> VGG:
r"""VGG 16-layer model (configuration "D") with batch normalization
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_.
The required minimum input size of the model is 32x32.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
return _vgg("vgg16_bn", "D", True)
def vgg19() -> VGG:
r"""VGG 19-layer model (configuration "E")
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_.
The required minimum input size of the model is 32x32.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
return _vgg("vgg19", "E", False)
def vgg19_bn(pretrained: bool = False, **kwargs: Any) -> VGG:
r"""VGG 19-layer model (configuration 'E') with batch normalization
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_.
The required minimum input size of the model is 32x32.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
return _vgg("vgg19_bn", "E", True)