-
Notifications
You must be signed in to change notification settings - Fork 124
/
model.py
171 lines (140 loc) · 5.36 KB
/
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
"""model.py"""
import torch
import torch.nn as nn
#import torch.nn.functional as F
import torch.nn.init as init
from torch.autograd import Variable
def reparametrize(mu, logvar):
std = logvar.div(2).exp()
eps = Variable(std.data.new(std.size()).normal_())
return mu + std*eps
class View(nn.Module):
def __init__(self, size):
super(View, self).__init__()
self.size = size
def forward(self, tensor):
return tensor.view(self.size)
class BetaVAE_H(nn.Module):
"""Model proposed in original beta-VAE paper(Higgins et al, ICLR, 2017)."""
def __init__(self, z_dim=10, nc=3):
super(BetaVAE_H, self).__init__()
self.z_dim = z_dim
self.nc = nc
self.encoder = nn.Sequential(
nn.Conv2d(nc, 32, 4, 2, 1), # B, 32, 32, 32
nn.ReLU(True),
nn.Conv2d(32, 32, 4, 2, 1), # B, 32, 16, 16
nn.ReLU(True),
nn.Conv2d(32, 64, 4, 2, 1), # B, 64, 8, 8
nn.ReLU(True),
nn.Conv2d(64, 64, 4, 2, 1), # B, 64, 4, 4
nn.ReLU(True),
nn.Conv2d(64, 256, 4, 1), # B, 256, 1, 1
nn.ReLU(True),
View((-1, 256*1*1)), # B, 256
nn.Linear(256, z_dim*2), # B, z_dim*2
)
self.decoder = nn.Sequential(
nn.Linear(z_dim, 256), # B, 256
View((-1, 256, 1, 1)), # B, 256, 1, 1
nn.ReLU(True),
nn.ConvTranspose2d(256, 64, 4), # B, 64, 4, 4
nn.ReLU(True),
nn.ConvTranspose2d(64, 64, 4, 2, 1), # B, 64, 8, 8
nn.ReLU(True),
nn.ConvTranspose2d(64, 32, 4, 2, 1), # B, 32, 16, 16
nn.ReLU(True),
nn.ConvTranspose2d(32, 32, 4, 2, 1), # B, 32, 32, 32
nn.ReLU(True),
nn.ConvTranspose2d(32, nc, 4, 2, 1), # B, nc, 64, 64
)
self.weight_init()
def weight_init(self):
for block in self._modules:
for m in self._modules[block]:
kaiming_init(m)
def forward(self, x):
distributions = self._encode(x)
mu = distributions[:, :self.z_dim]
logvar = distributions[:, self.z_dim:]
z = reparametrize(mu, logvar)
x_recon = self._decode(z)
return x_recon, mu, logvar
def _encode(self, x):
return self.encoder(x)
def _decode(self, z):
return self.decoder(z)
class BetaVAE_B(BetaVAE_H):
"""Model proposed in understanding beta-VAE paper(Burgess et al, arxiv:1804.03599, 2018)."""
def __init__(self, z_dim=10, nc=1):
super(BetaVAE_B, self).__init__()
self.nc = nc
self.z_dim = z_dim
self.encoder = nn.Sequential(
nn.Conv2d(nc, 32, 4, 2, 1), # B, 32, 32, 32
nn.ReLU(True),
nn.Conv2d(32, 32, 4, 2, 1), # B, 32, 16, 16
nn.ReLU(True),
nn.Conv2d(32, 32, 4, 2, 1), # B, 32, 8, 8
nn.ReLU(True),
nn.Conv2d(32, 32, 4, 2, 1), # B, 32, 4, 4
nn.ReLU(True),
View((-1, 32*4*4)), # B, 512
nn.Linear(32*4*4, 256), # B, 256
nn.ReLU(True),
nn.Linear(256, 256), # B, 256
nn.ReLU(True),
nn.Linear(256, z_dim*2), # B, z_dim*2
)
self.decoder = nn.Sequential(
nn.Linear(z_dim, 256), # B, 256
nn.ReLU(True),
nn.Linear(256, 256), # B, 256
nn.ReLU(True),
nn.Linear(256, 32*4*4), # B, 512
nn.ReLU(True),
View((-1, 32, 4, 4)), # B, 32, 4, 4
nn.ConvTranspose2d(32, 32, 4, 2, 1), # B, 32, 8, 8
nn.ReLU(True),
nn.ConvTranspose2d(32, 32, 4, 2, 1), # B, 32, 16, 16
nn.ReLU(True),
nn.ConvTranspose2d(32, 32, 4, 2, 1), # B, 32, 32, 32
nn.ReLU(True),
nn.ConvTranspose2d(32, nc, 4, 2, 1), # B, nc, 64, 64
)
self.weight_init()
def weight_init(self):
for block in self._modules:
for m in self._modules[block]:
kaiming_init(m)
def forward(self, x):
distributions = self._encode(x)
mu = distributions[:, :self.z_dim]
logvar = distributions[:, self.z_dim:]
z = reparametrize(mu, logvar)
x_recon = self._decode(z).view(x.size())
return x_recon, mu, logvar
def _encode(self, x):
return self.encoder(x)
def _decode(self, z):
return self.decoder(z)
def kaiming_init(m):
if isinstance(m, (nn.Linear, nn.Conv2d)):
init.kaiming_normal(m.weight)
if m.bias is not None:
m.bias.data.fill_(0)
elif isinstance(m, (nn.BatchNorm1d, nn.BatchNorm2d)):
m.weight.data.fill_(1)
if m.bias is not None:
m.bias.data.fill_(0)
def normal_init(m, mean, std):
if isinstance(m, (nn.Linear, nn.Conv2d)):
m.weight.data.normal_(mean, std)
if m.bias.data is not None:
m.bias.data.zero_()
elif isinstance(m, (nn.BatchNorm2d, nn.BatchNorm1d)):
m.weight.data.fill_(1)
if m.bias.data is not None:
m.bias.data.zero_()
if __name__ == '__main__':
pass