-
Notifications
You must be signed in to change notification settings - Fork 35
/
xresnet2.py
198 lines (153 loc) · 6.74 KB
/
xresnet2.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
#from https://github.com/fastai/fastai/blob/master/fastai/vision/models/xresnet2.py
import torch.nn as nn
import torch
import math
import torch.utils.model_zoo as model_zoo
from torch.nn import Module #changed from torch_core
__all__ = ['XResNet', 'xresnet18', 'xresnet34_2', 'xresnet50_2', 'xresnet101', 'xresnet152']
def conv3x3(in_planes, out_planes, stride=1):
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)
class BasicBlock(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):
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)
out += residual
out = self.relu(out)
return out
class Bottleneck(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 * self.expansion, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
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)
out += residual
out = self.relu(out)
return out
def conv2d(ni, nf, stride):
return nn.Sequential(nn.Conv2d(ni, nf, kernel_size=3, stride=stride, padding=1, bias=False),
nn.BatchNorm2d(nf), nn.ReLU(inplace=True))
class XResNet(Module):
def __init__(self, block, layers, c_out=1000):
self.inplanes = 64
super(XResNet, self).__init__()
self.conv1 = conv2d(3, 32, 2)
self.conv2 = conv2d(32, 32, 1)
self.conv3 = conv2d(32, 64, 1)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Linear(512 * block.expansion, c_out)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
for m in self.modules():
if isinstance(m, BasicBlock): m.bn2.weight = nn.Parameter(torch.zeros_like(m.bn2.weight))
if isinstance(m, Bottleneck): m.bn3.weight = nn.Parameter(torch.zeros_like(m.bn3.weight))
if isinstance(m, nn.Linear): m.weight.data.normal_(0, 0.01)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
layers = []
if stride==2: layers.append(nn.AvgPool2d(kernel_size=2, stride=2))
layers += [
nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(planes * block.expansion) ]
downsample = nn.Sequential(*layers)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks): layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.conv3(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def xresnet18(pretrained=False, **kwargs):
"""Constructs a XResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = XResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['xresnet18']))
return model
def xresnet34_2(pretrained=False, **kwargs):
"""Constructs a XResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = XResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['xresnet34']))
return model
def xresnet50_2(pretrained=False, **kwargs):
"""Constructs a XResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = XResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['xresnet50']))
return model
def xresnet101(pretrained=False, **kwargs):
"""Constructs a XResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = XResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['xresnet101']))
return model
def xresnet152(pretrained=False, **kwargs):
"""Constructs a XResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = XResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['xresnet152']))
return model