-
Notifications
You must be signed in to change notification settings - Fork 1
/
imagenet_models.py
219 lines (168 loc) · 7.04 KB
/
imagenet_models.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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
# Borrowed and modified torchvision/models/resnet.py
# See comments starting from "Dmitrii Khizbullin:"
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
from torch.nn.parameter import Parameter
__all__ = ['resnet18_backbone', 'resnet34_backbone', 'resnet50_backbone']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
}
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.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(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 * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
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 ResNetBackbone(nn.Module):
def __init__(self, block, layers, channel_config=(1, 2, 4, 8), channel_multiplier=64):
assert len(channel_config) == 4
self.inplanes = channel_multiplier
super().__init__()
self.conv1 = nn.Conv2d(3, channel_multiplier, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(channel_multiplier)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, channel_multiplier*channel_config[0], layers[0])
self.layer2 = self._make_layer(block, channel_multiplier*channel_config[1], layers[1], stride=2)
self.layer3 = self._make_layer(block, channel_multiplier*channel_config[2], layers[2], stride=2)
self.layer4 = self._make_layer(block, channel_multiplier*channel_config[3], layers[3], stride=2)
# Dmitrii Khizbullin: remove classification head
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 forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
branches = []
x = self.layer1(x)
branches.append(x)
x = self.layer2(x)
branches.append(x)
x = self.layer3(x)
branches.append(x)
x = self.layer4(x)
branches.append(x)
return branches
def load_state_dict(self, state_dict):
"""Copies parameters and buffers from :attr:`state_dict` into
this module and its descendants. The keys of :attr:`state_dict` must
exactly match the keys returned by this module's :func:`state_dict()`
function.
Arguments:
state_dict (dict): A dict containing parameters and
persistent buffers.
"""
own_state = self.state_dict()
for name, param in state_dict.items():
if name not in own_state:
raise KeyError('unexpected key "{}" in state_dict'
.format(name))
if isinstance(param, Parameter):
# backwards compatibility for serialized parameters
param = param.data
try:
own_state[name].copy_(param)
except:
# Dmitrii Khizbullin: skip weights if they cannot be loaded
#print('While copying the parameter named {}, whose dimensions in the model are'
# ' {} and whose dimensions in the checkpoint are {}, ...'.format(
# name, own_state[name].size(), param.size()))
#raise CustomException
pass
missing = set(own_state.keys()) - set(state_dict.keys())
if len(missing) > 0:
raise KeyError('missing keys in state_dict: "{}"'.format(missing))
def resnet18_backbone(pretrained=False, **kwargs):
"""Constructs a ResNet-18 backbone.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNetBackbone(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']), strict=False)
return model
def resnet34_backbone(pretrained=False, **kwargs):
"""Constructs a ResNet-34 backbone.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNetBackbone(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']), strict=False)
return model
def resnet50_backbone(pretrained=False, **kwargs):
"""Constructs a ResNet-50 backbone.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNetBackbone(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']), strict=False)
return model