-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathres_model.py
205 lines (143 loc) · 6.11 KB
/
res_model.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
from collections import OrderedDict
import math
import torch
import torch.nn as nn
from torch.utils import model_zoo
def load_weights_add_extra_dim(target, source_state, extra_dim=1):
new_dict = OrderedDict()
for k1, v1 in target.state_dict().items():
if not 'num_batches_tracked' in k1:
if k1 in source_state:
tar_v = source_state[k1]
if v1.shape != tar_v.shape:
# Init the new segmentation channel with zeros
# print(v1.shape, tar_v.shape)
c, _, w, h = v1.shape
pads = torch.zeros((c,extra_dim,w,h), device=tar_v.device)
nn.init.orthogonal_(pads)
tar_v = torch.cat([tar_v, pads], 1)
new_dict[k1] = tar_v
target.load_state_dict(new_dict)
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
}
def conv3x3(in_planes, out_planes, stride=1, dilation=1):
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=dilation, dilation=dilation, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, dilation=1):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride=stride, dilation=dilation)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes, stride=1, dilation=dilation)
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, dilation=1):
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, dilation=dilation,
padding=dilation, 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 ResNet(nn.Module):
def __init__(self, block, layers=(3, 4, 23, 3), extra_dim=0):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3+extra_dim, 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=2)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1, dilation=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 = [block(self.inplanes, planes, stride, downsample)]
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, dilation=dilation))
return nn.Sequential(*layers)
def resnet18(pretrained=True, extra_dim=0):
model = ResNet(BasicBlock, [2, 2, 2, 2], extra_dim)
nor3mr3m = True
r3m = torch.load('xxx/resnet18.pt')
filtered_dict = {}
for key, value in r3m['r3m'].items():
if key.startswith("module.convnet"):
new_key = key.replace("module.convnet.", "")
filtered_dict[new_key] = value
if pretrained:
if nor3mr3m:
load_weights_add_extra_dim(model, model_zoo.load_url(model_urls['resnet18']), extra_dim)
else:
load_weights_add_extra_dim(model, filtered_dict, extra_dim)
return model
def resnet50(pretrained=True, extra_dim=0):
model = ResNet(Bottleneck, [3, 4, 6, 3], extra_dim)
#nor3mr3m = False
#pretrained = False
nor3mr3m = True
r3m = torch.load('xxxx/resnet50.pt')
filtered_dict = {}
for key, value in r3m['r3m'].items():
if key.startswith("module.convnet"):
new_key = key.replace("module.convnet.", "")
filtered_dict[new_key] = value
if pretrained:
if nor3mr3m:
load_weights_add_extra_dim(model, model_zoo.load_url(model_urls['resnet50']), extra_dim)
else:
load_weights_add_extra_dim(model, filtered_dict, extra_dim)
return model