-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathresnet.py
177 lines (143 loc) · 6.16 KB
/
resnet.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
# Original code and checkpoints by Hang Zhang
# https://github.com/zhanghang1989/PyTorch-Encoding
import math
import torch
import os
import sys
import zipfile
import torch.utils.model_zoo as model_zoo
import torch.nn as nn
try:
from urllib import urlretrieve
except ImportError:
from urllib.request import urlretrieve
model_urls = {
'resnet50': 'https://s3.us-west-1.wasabisys.com/encoding/models/resnet50s-a75c83cf.zip',
}
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 Bottleneck(nn.Module):
"""
ResNet Bottleneck
"""
expansion = 4
def __init__(self, inplanes, planes, stride=1, dilation=1, downsample=None, previous_dilation=1, norm_layer=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = norm_layer(planes)
self.conv2 = nn.Conv2d(
planes, planes, kernel_size=3, stride=stride,
padding=dilation, dilation=dilation, bias=False)
self.bn2 = norm_layer(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = norm_layer(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.dilation = dilation
self.stride = stride
def _sum_each(self, x, y):
assert(len(x) == len(y))
z = []
for i in range(len(x)):
z.append(x[i]+y[i])
return z
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):
"""Dilated Pre-trained ResNet Model, which preduces the stride of 8 featuremaps at conv5.
Reference:
- He, Kaiming, et al. "Deep residual learning for image recognition." CVPR. 2016.
- Yu, Fisher, and Vladlen Koltun. "Multi-scale context aggregation by dilated convolutions."
"""
def __init__(self, block, layers, deep_base=True, norm_layer=nn.BatchNorm2d):
self.inplanes = 128 if deep_base else 64
super(ResNet, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False),
norm_layer(64),
nn.ReLU(inplace=True),
nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
norm_layer(64),
nn.ReLU(inplace=True),
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1, bias=False),
)
self.bn1 = norm_layer(self.inplanes)
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], norm_layer=norm_layer)
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, norm_layer=norm_layer)
self.layer3 = self._make_layer(block, 256, layers[2], stride=1, dilation=2, norm_layer=norm_layer)
self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation=4, norm_layer=norm_layer)
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, norm_layer):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1, dilation=1, norm_layer=None):
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),
norm_layer(planes * block.expansion),
)
layers = []
if dilation == 1 or dilation == 2:
layers.append(block(self.inplanes, planes, stride, dilation=1, downsample=downsample, previous_dilation=dilation, norm_layer=norm_layer))
elif dilation == 4:
layers.append(block(self.inplanes, planes, stride, dilation=2, downsample=downsample, previous_dilation=dilation, norm_layer=norm_layer))
else:
raise RuntimeError("=> unknown dilation size: {}".format(dilation))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, dilation=dilation, previous_dilation=dilation, norm_layer=norm_layer))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
layer1 = self.layer1(x)
layer2 = self.layer2(layer1)
layer3 = self.layer3(layer2)
layer4 = self.layer4(layer3)
return layer1, layer2, layer3, layer4
def resnet50(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']), strict=False)
return model
def load_url(url, model_dir='./pretrained', map_location=None):
if not os.path.exists(model_dir):
os.makedirs(model_dir)
filename = url.split('/')[-1].split('.')[0]
cached_file = os.path.join(model_dir, filename+'.pth')
if not os.path.exists(cached_file):
cached_file = os.path.join(model_dir, filename+'.zip')
sys.stderr.write('Downloading: "{}" to {}\n'.format(url, cached_file))
urlretrieve(url, cached_file)
zip_ref = zipfile.ZipFile(cached_file, 'r')
zip_ref.extractall(model_dir)
zip_ref.close()
os.remove(cached_file)
cached_file = os.path.join(model_dir, filename+'.pth')
return torch.load(cached_file, map_location=map_location)