（超详细）7-YOLOV5改进-添加 CoTAttention注意力机制

1、在yolov5/models下面新建一个CoTAttention.py文件，在里面放入下面的代码

代码如下：

import numpy as np
import torch
from torch import flatten, nn
from torch.nn import init
from torch.nn.modules.activation import ReLU
from torch.nn.modules.batchnorm import BatchNorm2d
from torch.nn import functional as F


class CoTAttention(nn.Module):

    def __init__(self, dim=512, kernel_size=3):
        super().__init__()
        self.dim = dim
        self.kernel_size = kernel_size

        self.key_embed = nn.Sequential(
            nn.Conv2d(dim, dim, kernel_size=kernel_size, padding=kernel_size // 2, groups=4, bias=False),
            nn.BatchNorm2d(dim),
            nn.ReLU()
        )
        self.value_embed = nn.Sequential(
            nn.Conv2d(dim, dim, 1, bias=False),
            nn.BatchNorm2d(dim)
        )

        factor = 4
        self.attention_embed = nn.Sequential(
            nn.Conv2d(2 * dim, 2 * dim // factor, 1, bias=False),
            nn.BatchNorm2d(2 * dim // factor),
            nn.ReLU(),
            nn.Conv2d(2 * dim // factor, kernel_size * kernel_size * dim, 1)
        )

    def forward(self, x):
        bs, c, h, w = x.shape
        k1 = self.key_embed(x)  # bs,c,h,w
        v = self.value_embed(x).view(bs, c, -1)  # bs,c,h,w

        y = torch.cat([k1, x], dim=1)  # bs,2c,h,w
        att = self.attention_embed(y)  # bs,c*k*k,h,w
        att = att.reshape(bs, c, self.kernel_size * self.kernel_size, h, w)
        att = att.mean(2, keepdim=False).view(bs, c, -1)  # bs,c,h*w
        k2 = F.softmax(att, dim=-1) * v
        k2 = k2.view(bs, c, h, w)

        return k1 + k2

2、找到yolo.py文件，进行更改内容
在29行加一个from models.CoTAttention import CoTAttention, 保存即可

3、找到自己想要更改的yaml文件，我选择的yolov5s.yaml文件(你可以根据自己需求进行选择），将刚刚写好的模块CoTAttention加入到yolov5s.yaml里面，并更改一些内容。更改如下

4、在yolo.py里面加入两行代码（335-337）
保存即可！

运行

原文地址：https://blog.csdn.net/qq_44421796/article/details/135712195

免责声明：本站文章内容转载自网络资源，如本站内容侵犯了原著者的合法权益，可联系本站删除。更多内容请关注自学内容网（zxcms.com）！