-
Notifications
You must be signed in to change notification settings - Fork 4
/
model.py
128 lines (105 loc) · 4.85 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
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
class ResidualBlock(nn.Module):
"""Residual Block."""
def __init__(self, dim_in, dim_out):
super(ResidualBlock, self).__init__()
self.main = nn.Sequential(
nn.Conv2d(dim_in, dim_out, kernel_size=3, stride=1, padding=1, bias=False),
nn.InstanceNorm2d(dim_out, affine=True),
nn.ReLU(inplace=True),
nn.Conv2d(dim_out, dim_out, kernel_size=3, stride=1, padding=1, bias=False),
nn.InstanceNorm2d(dim_out, affine=True))
def forward(self, x):
return x + self.main(x)
class Generator(nn.Module):
"""Generator. Encoder-Decoder Architecture."""
def __init__(self, conv_dim=64, c_dim=5, s_dim=7, repeat_num=6):
super(Generator, self).__init__()
print('initializing generator')
print(c_dim)
print(s_dim)
layers = []
layers.append(nn.Conv2d(3+c_dim+s_dim, conv_dim, kernel_size=7, stride=1, padding=3, bias=False))
layers.append(nn.InstanceNorm2d(conv_dim, affine=True))
layers.append(nn.ReLU(inplace=True))
# Down-Sampling
curr_dim = conv_dim
for i in range(2):
layers.append(nn.Conv2d(curr_dim, curr_dim*2, kernel_size=4, stride=2, padding=1, bias=False))
layers.append(nn.InstanceNorm2d(curr_dim*2, affine=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = curr_dim * 2
# Bottleneck
for i in range(repeat_num):
layers.append(ResidualBlock(dim_in=curr_dim, dim_out=curr_dim))
# Up-Sampling
for i in range(2):
layers.append(nn.ConvTranspose2d(curr_dim, curr_dim//2, kernel_size=4, stride=2, padding=1, bias=False))
layers.append(nn.InstanceNorm2d(curr_dim//2, affine=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = curr_dim // 2
layers.append(nn.Conv2d(curr_dim, 3, kernel_size=7, stride=1, padding=3, bias=False))
layers.append(nn.Tanh())
self.main = nn.Sequential(*layers)
def forward(self, x, c, s):
# replicate spatially and concatenate domain information
c = c.unsqueeze(2).unsqueeze(3)
c = c.expand(c.size(0), c.size(1), x.size(2), x.size(3))
x = torch.cat([x, c], dim=1)
x = torch.cat([x,s], dim=1)
return self.main(x)
class Discriminator(nn.Module):
"""Discriminator. PatchGAN."""
def __init__(self, image_size=128, conv_dim=64, c_dim=5, repeat_num=6):
super(Discriminator, self).__init__()
c_dim=5
layers = []
layers.append(nn.Conv2d(3, conv_dim, kernel_size=4, stride=2, padding=1))
layers.append(nn.LeakyReLU(0.01, inplace=True))
curr_dim = conv_dim
for i in range(1, repeat_num):
layers.append(nn.Conv2d(curr_dim, curr_dim*2, kernel_size=4, stride=2, padding=1))
layers.append(nn.LeakyReLU(0.01, inplace=True))
curr_dim = curr_dim * 2
k_size = int(image_size / np.power(2, repeat_num))
self.main = nn.Sequential(*layers)
self.conv1 = nn.Conv2d(curr_dim, 1, kernel_size=3, stride=1, padding=1, bias=False)
self.conv2 = nn.Conv2d(curr_dim, c_dim, kernel_size=k_size, bias=False)
def forward(self, x):
h = self.main(x)
out_real = self.conv1(h)
out_aux = self.conv2(h)
return out_real.squeeze(), out_aux.squeeze()
class Segmentor(nn.Module):
"""Generator. Encoder-Decoder Architecture."""
def __init__(self, conv_dim=64, repeat_num=4):
super(Segmentor, self).__init__()
layers = []
layers.append(nn.Conv2d(3, conv_dim, kernel_size=7, stride=1, padding=3, bias=False))
layers.append(nn.InstanceNorm2d(conv_dim, affine=True))
layers.append(nn.ReLU(inplace=True))
# Down-Sampling
curr_dim = conv_dim
for i in range(2):
layers.append(nn.Conv2d(curr_dim, curr_dim*2, kernel_size=4, stride=2, padding=1, bias=False))
layers.append(nn.InstanceNorm2d(curr_dim*2, affine=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = curr_dim * 2
# Bottleneck
for i in range(repeat_num):
layers.append(ResidualBlock(dim_in=curr_dim, dim_out=curr_dim))
# Up-Sampling
for i in range(2):
layers.append(nn.ConvTranspose2d(curr_dim, curr_dim//2, kernel_size=4, stride=2, padding=1, bias=False))
layers.append(nn.InstanceNorm2d(curr_dim//2, affine=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = curr_dim // 2
layers.append(nn.Conv2d(curr_dim, 7, kernel_size=7, stride=1, padding=3, bias=False))
# layers.append(nn.LogSoftmax())
# layers.append(nn.Softmax2d())
self.main = nn.Sequential(*layers)
def forward(self, x):
return self.main(x)