-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathCaT.py
152 lines (116 loc) · 5.72 KB
/
CaT.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
## https://github.com/xiaochen925/CAF-YOLO
import sys
import torch
import torch.nn as nn
import torch.nn.functional as F
from pdb import set_trace as stx
import numbers
from einops import rearrange
import os
sys.path.append(os.getcwd())
def to_3d(x):
return rearrange(x, 'b c h w -> b (h w) c')
def to_4d(x,h,w):
return rearrange(x, 'b (h w) c -> b c h w',h=h,w=w)
class BiasFree_LayerNorm(nn.Module):
def __init__(self, normalized_shape):
super(BiasFree_LayerNorm, self).__init__()
if isinstance(normalized_shape, numbers.Integral):
normalized_shape = (normalized_shape,)
normalized_shape = torch.Size(normalized_shape)
assert len(normalized_shape) == 1
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.normalized_shape = normalized_shape
def forward(self, x):
sigma = x.var(-1, keepdim=True, unbiased=False)
return x / torch.sqrt(sigma+1e-5) * self.weight
class WithBias_LayerNorm(nn.Module):
def __init__(self, normalized_shape):
super(WithBias_LayerNorm, self).__init__()
if isinstance(normalized_shape, numbers.Integral):
normalized_shape = (normalized_shape,)
normalized_shape = torch.Size(normalized_shape)
assert len(normalized_shape) == 1
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.bias = nn.Parameter(torch.zeros(normalized_shape))
self.normalized_shape = normalized_shape
def forward(self, x):
mu = x.mean(-1, keepdim=True)
sigma = x.var(-1, keepdim=True, unbiased=False)
return (x - mu) / torch.sqrt(sigma+1e-5) * self.weight + self.bias
class LayerNorm(nn.Module):
def __init__(self, dim, LayerNorm_type):
super(LayerNorm, self).__init__()
if LayerNorm_type =='BiasFree':
self.body = BiasFree_LayerNorm(dim)
else:
self.body = WithBias_LayerNorm(dim)
def forward(self, x):
h, w = x.shape[-2:]
return to_4d(self.body(to_3d(x)), h, w)
class MSFN(nn.Module):
def __init__(self, dim, ffn_expansion_factor=2.66, bias=False):
super(MSFN, self).__init__()
hidden_features = int(dim*ffn_expansion_factor)
self.project_in = nn.Conv3d(dim, hidden_features*3, kernel_size=(1,1,1), bias=bias)
self.dwconv1 = nn.Conv3d(hidden_features, hidden_features, kernel_size=(3,3,3), stride=1, dilation=1, padding=1, groups=hidden_features, bias=bias)
# self.dwconv2 = nn.Conv3d(hidden_features, hidden_features, kernel_size=(3,3,3), stride=1, dilation=2, padding=2, groups=hidden_features, bias=bias)
# self.dwconv3 = nn.Conv3d(hidden_features, hidden_features, kernel_size=(3,3,3), stride=1, dilation=3, padding=3, groups=hidden_features, bias=bias)
self.dwconv2 = nn.Conv2d(hidden_features, hidden_features, kernel_size=(3,3), stride=1, dilation=2, padding=2, groups=hidden_features, bias=bias)
self.dwconv3 = nn.Conv2d(hidden_features, hidden_features, kernel_size=(3,3), stride=1, dilation=3, padding=3, groups=hidden_features, bias=bias)
self.project_out = nn.Conv3d(hidden_features, dim, kernel_size=(1,1,1), bias=bias)
def forward(self, x):
x = x.unsqueeze(2)
x = self.project_in(x)
x1,x2,x3 = x.chunk(3, dim=1)
x1 = self.dwconv1(x1).squeeze(2)
x2 = self.dwconv2(x2.squeeze(2))
x3 = self.dwconv3(x3.squeeze(2))
# x1 = self.dwconv1(x1)
# x2 = self.dwconv2(x2)
# x3 = self.dwconv3(x3)
x = F.gelu(x1)*x2*x3
x = x.unsqueeze(2)
x = self.project_out(x)
x = x.squeeze(2)
return x
class CAFMAttention(nn.Module):
def __init__(self, dim, num_heads=2, bias=False):
super(CAFMAttention, self).__init__()
self.num_heads = num_heads
self.temperature = nn.Parameter(torch.ones(num_heads, 1, 1))
self.qkv = nn.Conv3d(dim, dim*3, kernel_size=(1,1,1), bias=bias)
self.qkv_dwconv = nn.Conv3d(dim*3, dim*3, kernel_size=(3,3,3), stride=1, padding=1, groups=dim*3, bias=bias)
self.project_out = nn.Conv3d(dim, dim, kernel_size=(1,1,1), bias=bias)
self.fc = nn.Conv3d(3*self.num_heads, 9, kernel_size=(1,1,1), bias=True)
self.dep_conv = nn.Conv3d(9*dim//self.num_heads, dim, kernel_size=(3,3,3), bias=True, groups=dim//self.num_heads, padding=1)
def forward(self, x):
b,c,h,w = x.shape
x = x.unsqueeze(2)
qkv = self.qkv_dwconv(self.qkv(x))
qkv = qkv.squeeze(2)
f_conv = qkv.permute(0,2,3,1)
f_all = qkv.reshape(f_conv.shape[0], h*w, 3*self.num_heads, -1).permute(0, 2, 1, 3)
f_all = self.fc(f_all.unsqueeze(2))
f_all = f_all.squeeze(2)
#local conv
f_conv = f_all.permute(0, 3, 1, 2).reshape(x.shape[0], 9*x.shape[1]//self.num_heads, h, w)
f_conv = f_conv.unsqueeze(2)
out_conv = self.dep_conv(f_conv) # B, C, H, W
out_conv = out_conv.squeeze(2)
# global SA
q,k,v = qkv.chunk(3, dim=1)
q = rearrange(q, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
k = rearrange(k, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
v = rearrange(v, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
q = torch.nn.functional.normalize(q, dim=-1)
k = torch.nn.functional.normalize(k, dim=-1)
attn = (q @ k.transpose(-2, -1)) * self.temperature
attn = attn.softmax(dim=-1)
out = (attn @ v)
out = rearrange(out, 'b head c (h w) -> b (head c) h w', head=self.num_heads, h=h, w=w)
out = out.unsqueeze(2)
out = self.project_out(out)
out = out.squeeze(2)
output = out + out_conv
return output