-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathmodels.py
198 lines (158 loc) · 6.32 KB
/
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
'''ResNet in PyTorch.
For Pre-activation ResNet, see 'preact_resnet.py'.
Reference:
[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Deep Residual Learning for Image Recognition. arXiv:1512.03385
'''
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.nn.init as init
def _weights_init(m):
classname = m.__class__.__name__
if isinstance(m, nn.Linear) or isinstance(m, nn.Conv2d):
init.xavier_normal_(m.weight)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
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):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(in_planes, 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, 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 CMLP(nn.Module):
def __init__(self, num_classes=1, activation='tanh', dims=100, k=3):
super(CMLP, self).__init__()
self.neurons = min(dims,num_classes)
self.linear = nn.Linear(self.neurons, num_classes)
self.linear_1 = nn.Linear(dims, self.neurons)
self.linear_2 = nn.Linear(self.neurons, self.neurons)
self.apply(_weights_init)
self.activation = activation
self.k = k
def getHiddenDIM(self):
return self.neurons
def forward(self, x):
if self.activation == 'relu':
hidden=F.relu(self.linear_1(x))
for i in range(3):
hidden=F.relu(self.linear_2(hidden))
elif self.activation == 'tanh':
hidden=F.tanh(self.linear_1(x))
for i in range(self.k):
hidden=F.tanh(self.linear_2(hidden))
out = self.linear(hidden)
return out, hidden
class MLP(nn.Module):
def __init__(self, num_classes=1, activation='tanh', dims=100):
super(MLP, self).__init__()
self.neurons = min(dims,num_classes)
self.linear = nn.Linear(self.neurons, num_classes)
self.linear_1 = nn.Linear(dims, self.neurons)
self.linear_2 = nn.Linear(self.neurons, self.neurons)
self.apply(_weights_init)
self.activation = activation
def getHiddenDIM(self):
return self.neurons
def forward(self, x):
if self.activation == 'relu':
hidden=F.relu(self.linear_1(x))
hidden=F.relu(self.linear_2(hidden))
elif self.activation == 'tanh':
hidden=F.tanh(self.linear_1(x))
hidden=F.tanh(self.linear_2(hidden))
out = self.linear(hidden)
return out#, hidden
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=10, inchannels=3):
super(ResNet, self).__init__()
self.in_planes = 64
self.conv1 = nn.Conv2d(inchannels, 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.linear = nn.Linear(512*block.expansion, num_classes)
self.neurons = 512*block.expansion
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.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def getHiddenDIM(self):
return self.neurons
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 = F.avg_pool2d(out, 4)
out = out.view(out.size(0), -1)
hidden = out
out = self.linear(out)
return out#, hidden
def FFNN(**kwargs):
return MLP(**kwargs)
def CFFNN(**kwargs):
return CMLP(**kwargs)
def ResNet18(**kwargs):
return ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
def ResNet34(**kwargs):
return ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
def ResNet50(**kwargs):
return ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
def ResNet101(**kwargs):
return ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
def ResNet152(**kwargs):
return ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
def test():
net = ResNet18()
y = net(torch.randn(1, 3, 32, 32))
print(y.size())
# test()