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
|
from typing import Union
import torch
import torch.nn as nn
import torch.nn.functional as F
class BasicConv2d(nn.Module):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int, int]],
**kwargs
):
super().__init__()
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size,
bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
return F.relu(x, inplace=True)
class VGGConv2d(BasicConv2d):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int, int]] = 3,
padding: int = 1,
**kwargs
):
super().__init__(in_channels, out_channels, kernel_size,
padding=padding, **kwargs)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
return F.leaky_relu(x, 0.2, inplace=True)
class BasicConvTranspose2d(nn.Module):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int, int]],
**kwargs
):
super().__init__()
self.trans_conv = nn.ConvTranspose2d(in_channels, out_channels,
kernel_size, bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels)
def forward(self, x):
x = self.trans_conv(x)
x = self.bn(x)
return F.relu(x, inplace=True)
class DCGANConvTranspose2d(BasicConvTranspose2d):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int, int]] = 4,
stride: int = 2,
padding: int = 1,
is_last_layer: bool = False,
**kwargs
):
super().__init__(in_channels, out_channels, kernel_size,
stride=stride, padding=padding, **kwargs)
self.is_last_layer = is_last_layer
def forward(self, x):
if self.is_last_layer:
return self.trans_conv(x)
else:
return super().forward(x)
class BasicLinear(nn.Module):
def __init__(
self,
in_features: int,
out_features: int,
):
super().__init__()
self.fc = nn.Linear(in_features, out_features, bias=False)
self.bn = nn.BatchNorm1d(out_features)
def forward(self, x):
x = self.fc(x)
x = self.bn(x)
return x
class FocalConv2d(BasicConv2d):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int, int]],
halving: int,
**kwargs
):
super().__init__(in_channels, out_channels, kernel_size, **kwargs)
self.halving = halving
def forward(self, x):
h = x.size(2)
split_size = h // 2 ** self.halving
z = x.split(split_size, dim=2)
z = torch.cat([self.conv(_) for _ in z], dim=2)
return F.leaky_relu(z, inplace=True)
class FocalConv2dBlock(nn.Module):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_sizes: tuple[int, int],
paddings: tuple[int, int],
halving: int,
use_pool: bool = True,
**kwargs
):
super().__init__()
self.use_pool = use_pool
self.fconv1 = FocalConv2d(in_channels, out_channels, kernel_sizes[0],
halving, padding=paddings[0], **kwargs)
self.fconv2 = FocalConv2d(out_channels, out_channels, kernel_sizes[1],
halving, padding=paddings[1], **kwargs)
self.max_pool = nn.MaxPool2d(2)
def forward(self, x):
x = self.fconv1(x)
x = self.fconv2(x)
if self.use_pool:
x = self.max_pool(x)
return x
class BasicConv1d(nn.Module):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int]],
**kwargs
):
super().__init__()
self.conv = nn.Conv1d(in_channels, out_channels, kernel_size,
bias=False, **kwargs)
def forward(self, x):
return self.conv(x)
class HorizontalPyramidPooling(BasicConv2d):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: Union[int, tuple[int, int]] = 1,
use_avg_pool: bool = True,
use_max_pool: bool = True,
**kwargs
):
super().__init__(in_channels, out_channels, kernel_size, **kwargs)
self.use_avg_pool = use_avg_pool
self.use_max_pool = use_max_pool
assert use_avg_pool or use_max_pool, 'Pooling layer(s) required.'
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
def forward(self, x):
if self.use_avg_pool and self.use_max_pool:
x = self.avg_pool(x) + self.max_pool(x)
elif self.use_avg_pool and not self.use_max_pool:
x = self.avg_pool(x)
elif not self.use_avg_pool and self.use_max_pool:
x = self.max_pool(x)
x = super().forward(x)
return x
|
