-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathresnet.py
154 lines (128 loc) · 5.58 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
''' ref:
https://github.com/kuangliu/pytorch-cifar/blob/master/models/resnet.py
https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
'''
import torch
import torch.nn as nn
import torch.nn.functional as F
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1, wide=1):
super(BasicBlock, self).__init__()
planes = planes * wide
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_planes, planes, stride=1, wide=1):
super(Bottleneck, self).__init__()
mid_planes = planes * wide
self.conv1 = nn.Conv2d(in_planes, mid_planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(mid_planes)
self.conv2 = nn.Conv2d(mid_planes, mid_planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(mid_planes)
self.conv3 = nn.Conv2d(mid_planes, self.expansion*planes, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion*planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = F.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, num_blocks, in_dims, out_dims, wide=1):
super(ResNet, self).__init__()
self.wide = wide
self.in_planes = 64
self.conv1 = nn.Conv2d(in_dims, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1,1))
self.linear = nn.Linear(512*block.expansion, out_dims)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride, self.wide))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = self.avgpool(out)
out = torch.flatten(out, 1)
out = self.linear(out)
return out
def feature_extract(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = self.avgpool(out)
out = torch.flatten(out, 1)
return out
class WRN(nn.Module):
def __init__(self, num_blocks, in_dims, out_dims, wide=10):
super(WRN, self).__init__()
self.in_planes = 16
self.wide = wide
block = BasicBlock
self.conv1 = nn.Conv2d(in_dims, self.in_planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(16)
self.layer1 = self._make_layer(block, 16, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 32, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 64, num_blocks[2], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1,1))
self.linear = nn.Linear(64*wide, out_dims)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride, self.wide))
self.in_planes = planes * self.wide * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
# out = F.avg_pool2d(out, 8)
# out = out.view(out.shape[0], -1)
out = self.avgpool(out)
out = torch.flatten(out, 1)
out = self.linear(out)
return out
def resnet18(in_dims, out_dims):
return ResNet(BasicBlock, [2,2,2,2], in_dims, out_dims, 1)
def wrn34_10(in_dims, out_dims):
return WRN([5,5,5], in_dims, out_dims, wide=10)
def resnet50(in_dims, out_dims):
return ResNet(Bottleneck, [3,4,6,3], in_dims, out_dims, 1)