-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmodel.py
160 lines (119 loc) · 4.52 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
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from utils import reparameterize
# Models for tactile
class Reshape(nn.Module):
def __init__(self, *args):
super(Reshape, self).__init__()
self.shape = args
def forward(self, x):
return x.view((x.size(0),)+self.shape)
class Encoder(nn.Module):
def __init__(self, content_latent_size = 32):
super(Encoder, self).__init__()
self.content_latent_size = content_latent_size
self.main = nn.Sequential(
nn.Conv2d(in_channels=1, out_channels=8, kernel_size=3,stride=2,padding=1), ##64x64
nn.BatchNorm2d(8),
nn.LeakyReLU(),
nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3,stride=2,padding=1), ##32
nn.BatchNorm2d(16),
nn.LeakyReLU(),
nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3,stride=2,padding=1), ##16
nn.BatchNorm2d(32),
nn.LeakyReLU(),
nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3,stride=2,padding=1), ##8
nn.BatchNorm2d(64),
nn.LeakyReLU(),
nn.Flatten(),
nn.Linear(8*8*64, 1024)
)
self.fc_mean = nn.Linear(1024, content_latent_size) # 8*8*64
self.fc_logvar = nn.Linear(1024, content_latent_size) # 8*8*64
def forward(self, x):
x = self.main(x)
mean = self.fc_mean(x)
logvar = self.fc_logvar(x)
return mean, logvar
class Decoder(nn.Module):
def __init__(self, latent_size = 32):
super(Decoder, self).__init__()
self.main = nn.Sequential(
nn.Linear(latent_size, 1024), # 8*8*64
nn.Linear(1024, 8*8*64), # 8*8*64
Reshape(64,8,8), # 64，8，8
nn.ConvTranspose2d(in_channels=64, out_channels=32, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(32),
nn.LeakyReLU(),
nn.ConvTranspose2d(in_channels=32, out_channels=16, kernel_size=3,stride=2,output_padding=1),
nn.BatchNorm2d(16),
nn.LeakyReLU(),
nn.ConvTranspose2d(in_channels=16, out_channels=8, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(8),
nn.LeakyReLU(),
nn.ConvTranspose2d(in_channels=8, out_channels=1, kernel_size=3,stride=2,output_padding=1),
nn.BatchNorm2d(1),
nn.LeakyReLU(),
)
def forward(self, x):
x = self.main(x)
return x
class FeatureMapping(nn.Module):
def __init__(self, latent_size = 32):
super(FeatureMapping, self).__init__()
self.main = nn.Sequential(
nn.Linear(latent_size, 512),
nn.LeakyReLU(),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, latent_size),
)
def forward(self, x):
x = self.main(x)
return x
class Discriminator(nn.Module):
def __init__(self, latent_size = 32):
super(Discriminator,self).__init__()
self.main = nn.Sequential(
nn.Linear(latent_size, 512),
nn.LeakyReLU(),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 512),
nn.LeakyReLU(),
nn.Dropout(0.1),
nn.Linear(512, 1),
)
def forward(self, x):
x = self.main(x)
x = torch.sigmoid(x)
return x
class VAE(nn.Module):
def __init__(self, content_latent_size = 32):
super(VAE, self).__init__()
self.encoder = Encoder(content_latent_size)
self.decoder = Decoder(content_latent_size)
def forward(self, x):
mu, logsigma = self.encoder(x)
contentcode = reparameterize(mu, logsigma)
recon_x = self.decoder(contentcode)
return mu, logsigma, recon_x