一、 导读
论文链接:https://arxiv.org/abs/2311.11587
代码链接:GitHub - CV-ZhangXin/AKConv
二、 C2f-CIB加入注意力机制
2.1 复制代码
打开ultralytics->nn->modules->block.py文件,复制SE注意力机制(也可以自行换成别的)代码,并创建C2fCIBAttention代码,如下图所示:
class SE(nn.Module):
def __init__(self, channel, reduction=16):
super().__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Sequential(
nn.Linear(channel, channel // reduction, bias=False),
nn.ReLU(inplace=True),
nn.Linear(channel // reduction, channel, bias=False),
nn.Sigmoid()
)
def forward(self, x):
b, c, _, _ = x.size()
y = self.avg_pool(x).view(b, c)
y = self.fc(y).view(b, c, 1, 1)
return x * y.expand_as(x)
class C2fCIBAttention(nn.Module):
"""Faster Implementation of CSP Bottleneck with 2 convolutions."""
def __init__(self, c1, c2, n=1, shortcut=False, lk=False, g=1, e=0.5):
"""Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
expansion.
"""
super().__init__()
self.c = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, 2 * self.c, 1, 1)
self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2)
self.m = nn.ModuleList(CIB(self.c, self.c, shortcut, e=1.0, lk=lk) for _ in range(n))
self.atten = SE(C2)
def forward(self, x):
"""Forward pass through C2f layer."""
y = list(self.cv1(x).chunk(2, 1))
y.extend(m(y[-1]) for m in self.m)
return self.atten(self.cv2(torch.cat(y, 1)))
def forward_split(self, x):
"""Forward pass using split() instead of chunk()."""
y = list(self.cv1(x).split((self.c, self.c), 1))
y.extend(m(y[-1]) for m in self.m)
return self.cv2(torch.cat(y, 1))
并在上方声明C2fCIBAttention类。
在nn.models.__init__.py中声明 C2fCIBAttention。
2.2 修改tasks.py
打开ultralytics->nn->tasks.py,如图所示操作。
2.3 修改yolov10n.yaml
将yolov10n.yaml文件中的C2fCIB替换为C2fCIBAttention。
# Ultralytics YOLO
标签:__,CIB,nn,C2fCIBAttention,self,C2f,YOLOv10,True
From: https://blog.csdn.net/StopAndGoyyy/article/details/140110212