-
Notifications
You must be signed in to change notification settings - Fork 1
/
ResNetmid.py
199 lines (164 loc) · 6.6 KB
/
ResNetmid.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
199
from __future__ import absolute_import
from __future__ import division
import torch
from torch import nn
from torch.nn import functional as F
import torchvision
import torch.utils.model_zoo as model_zoo
model_urls = {
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
}
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 * 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
class ResNet(nn.Module):
"""
Residual network + mid-level features.
Reference:
Yu et al. The Devil is in the Middle: Exploiting Mid-level Representations for
Cross-Domain Instance Matching. arXiv:1711.08106.
"""
def __init__(self, block, layers,
last_stride=1,
fc_dims=None,
**kwargs):
self.inplanes = 64
super(ResNet, self).__init__()
self.feature_dim = 512 * block.expansion
# backbone network
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
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=last_stride)
self.global_avgpool = nn.AdaptiveAvgPool2d(1)
assert fc_dims is not None
self.fc_fusion = self._construct_fc_layer(fc_dims, 512 * block.expansion * 2)
self.feature_dim += 512 * block.expansion
self._init_params()
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 i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
"""
Construct fully connected layer
- fc_dims (list or tuple): dimensions of fc layers, if None,
no fc layers are constructed
- input_dim (int): input dimension
- dropout_p (float): dropout probability, if None, dropout is unused
"""
if fc_dims is None:
self.feature_dim = input_dim
return None
assert isinstance(fc_dims, (list, tuple)), "fc_dims must be either list or tuple, but got {}".format(type(fc_dims))
layers = []
for dim in fc_dims:
layers.append(nn.Linear(input_dim, dim))
layers.append(nn.BatchNorm1d(dim))
layers.append(nn.ReLU(inplace=True))
if dropout_p is not None:
layers.append(nn.Dropout(p=dropout_p))
input_dim = dim
self.feature_dim = fc_dims[-1]
return nn.Sequential(*layers)
def _init_params(self):
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.BatchNorm1d):
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)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
def featuremaps(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x4a = self.layer4[0](x)
x4b = self.layer4[1](x4a)
x4c = self.layer4[2](x4b)
return x4a, x4b, x4c
def forward(self, x):
x4a, x4b, x4c = self.featuremaps(x)
v4a = self.global_avgpool(x4a)
v4b = self.global_avgpool(x4b)
v4c = self.global_avgpool(x4c)
v4ab = torch.cat([v4a, v4b], 1)
v4ab = v4ab.view(v4ab.size(0), -1)
v4ab = self.fc_fusion(v4ab)
v4c = v4c.view(v4c.size(0), -1)
v = torch.cat([v4ab, v4c], 1)
return v
def init_pretrained_weights(model, model_url):
"""
Initialize model with pretrained weights.
Layers that don't match with pretrained layers in name or size are kept unchanged.
"""
pretrain_dict = model_zoo.load_url(model_url)
model_dict = model.state_dict()
pretrain_dict = {k: v for k, v in pretrain_dict.items() if k in model_dict and model_dict[k].size() == v.size()}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
print("Initialized model with pretrained weights from {}".format(model_url))
def resnet50mid(pretrained=True, **kwargs):
model = ResNet(
block=Bottleneck,
layers=[3, 4, 6, 3],
last_stride=1,
fc_dims=[1024],
**kwargs
)
if pretrained:
init_pretrained_weights(model, model_urls['resnet50'])
return model