forked from ai-dawang/PlugNPlay-Modules
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path(CVPR 2024)PKIBlock.py
168 lines (148 loc) · 7.51 KB
/
(CVPR 2024)PKIBlock.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
from typing import Optional, Sequence
import torch.nn as nn
import torch
# 论文地址：https://arxiv.org/pdf/2403.06258
# 论文：Poly Kernel Inception Network for Remote Sensing Detection(CVPR 2024)
# Github地址：https://github.com/NUST-Machine-Intelligence-Laboratory/PKINet
# 全网最全100➕即插即用模块GitHub地址：https://github.com/ai-dawang/PlugNPlay-Modules
# Poly Kernel Inception Block(PKIBlock)
def autopad(kernel_size: int, padding: Optional[int] = None, dilation: int = 1) -> int:
"""Calculate the padding size based on kernel size and dilation."""
if padding is None:
padding = (kernel_size - 1) * dilation // 2
return padding
def make_divisible(value: int, divisor: int = 8) -> int:
"""Make a value divisible by a certain divisor."""
return int((value + divisor // 2) // divisor * divisor)
class ConvModule(nn.Module):
def __init__(
self,
in_channels: int,
out_channels: int,
kernel_size: int,
stride: int = 1,
padding: int = 0,
dilation: int = 1,
groups: int = 1,
norm_cfg: Optional[dict] = None,
act_cfg: Optional[dict] = None):
super().__init__()
layers = []
layers.append(nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation=dilation, groups=groups, bias=(norm_cfg is None)))
if norm_cfg:
norm_layer = self._get_norm_layer(out_channels, norm_cfg)
layers.append(norm_layer)
if act_cfg:
act_layer = self._get_act_layer(act_cfg)
layers.append(act_layer)
self.block = nn.Sequential(*layers)
def forward(self, x):
return self.block(x)
def _get_norm_layer(self, num_features, norm_cfg):
if norm_cfg['type'] == 'BN':
return nn.BatchNorm2d(num_features, momentum=norm_cfg.get('momentum', 0.1), eps=norm_cfg.get('eps', 1e-5))
# Add more normalization types if needed
raise NotImplementedError(f"Normalization layer '{norm_cfg['type']}' is not implemented.")
def _get_act_layer(self, act_cfg):
if act_cfg['type'] == 'ReLU':
return nn.ReLU(inplace=True)
if act_cfg['type'] == 'SiLU':
return nn.SiLU(inplace=True)
# Add more activation types if needed
raise NotImplementedError(f"Activation layer '{act_cfg['type']}' is not implemented.")
# Update InceptionBottleneck's constructor call to avoid conflicts
class InceptionBottleneck(nn.Module):
"""Bottleneck with Inception module"""
def __init__(
self,
in_channels: int,
out_channels: Optional[int] = None,
kernel_sizes: Sequence[int] = (3, 5, 7, 9, 11),
dilations: Sequence[int] = (1, 1, 1, 1, 1),
expansion: float = 1.0,
add_identity: bool = True,
with_caa: bool = True,
caa_kernel_size: int = 11,
norm_cfg: Optional[dict] = dict(type='BN', momentum=0.03, eps=0.001),
act_cfg: Optional[dict] = dict(type='SiLU')):
super().__init__()
out_channels = out_channels or in_channels
hidden_channels = make_divisible(int(out_channels * expansion), 8)
self.pre_conv = ConvModule(in_channels, hidden_channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
self.dw_conv = ConvModule(hidden_channels, hidden_channels, kernel_sizes[0], 1,
autopad(kernel_sizes[0], None, dilations[0]),
dilation=dilations[0], groups=hidden_channels,
norm_cfg=None, act_cfg=None)
self.dw_conv1 = ConvModule(hidden_channels, hidden_channels, kernel_sizes[1], 1,
autopad(kernel_sizes[1], None, dilations[1]),
dilation=dilations[1], groups=hidden_channels,
norm_cfg=None, act_cfg=None)
self.dw_conv2 = ConvModule(hidden_channels, hidden_channels, kernel_sizes[2], 1,
autopad(kernel_sizes[2], None, dilations[2]),
dilation=dilations[2], groups=hidden_channels,
norm_cfg=None, act_cfg=None)
self.dw_conv3 = ConvModule(hidden_channels, hidden_channels, kernel_sizes[3], 1,
autopad(kernel_sizes[3], None, dilations[3]),
dilation=dilations[3], groups=hidden_channels,
norm_cfg=None, act_cfg=None)
self.dw_conv4 = ConvModule(hidden_channels, hidden_channels, kernel_sizes[4], 1,
autopad(kernel_sizes[4], None, dilations[4]),
dilation=dilations[4], groups=hidden_channels,
norm_cfg=None, act_cfg=None)
self.pw_conv = ConvModule(hidden_channels, hidden_channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
if with_caa:
self.caa_factor = CAA(hidden_channels, caa_kernel_size, caa_kernel_size, None, None)
else:
self.caa_factor = None
self.add_identity = add_identity and in_channels == out_channels
self.post_conv = ConvModule(hidden_channels, out_channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
def forward(self, x):
x = self.pre_conv(x)
y = x
x = self.dw_conv(x)
x = x + self.dw_conv1(x) + self.dw_conv2(x) + self.dw_conv3(x) + self.dw_conv4(x)
x = self.pw_conv(x)
if self.caa_factor is not None:
y = self.caa_factor(y)
if self.add_identity:
y = x * y
x = x + y
else:
x = x * y
x = self.post_conv(x)
return x
class CAA(nn.Module):
"""Context Anchor Attention"""
def __init__(
self,
channels: int,
h_kernel_size: int = 11,
v_kernel_size: int = 11,
norm_cfg: Optional[dict] = dict(type='BN', momentum=0.03, eps=0.001),
act_cfg: Optional[dict] = dict(type='SiLU')):
super().__init__()
self.avg_pool = nn.AvgPool2d(7, 1, 3)
self.conv1 = ConvModule(channels, channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
self.h_conv = ConvModule(channels, channels, (1, h_kernel_size), 1,
(0, h_kernel_size // 2), groups=channels,
norm_cfg=None, act_cfg=None)
self.v_conv = ConvModule(channels, channels, (v_kernel_size, 1), 1,
(v_kernel_size // 2, 0), groups=channels,
norm_cfg=None, act_cfg=None)
self.conv2 = ConvModule(channels, channels, 1, 1, 0,
norm_cfg=norm_cfg, act_cfg=act_cfg)
self.act = nn.Sigmoid()
def forward(self, x):
attn_factor = self.act(self.conv2(self.v_conv(self.h_conv(self.conv1(self.avg_pool(x))))))
return attn_factor
# Testing the InceptionBottleneck
if __name__ == "__main__":
input = torch.randn(1, 64, 128, 128) #输入B C H W
block = InceptionBottleneck(in_channels=64, out_channels=128)
output = block(input)
print(input.size())
print(output.size())