注意力机制：DualAttention

**

Dual Attention Network for Scene Segmentation

**
能加入YOLOv5、YOLOv7\YOLOv8中，有涨点

论文链接：https://arxiv.org/pdf/1809.02983.pdf

import numpy as np
import torch
from torch import nn
from torch.nn import init
from torch.nn import Module,  Conv2d,Parameter, Softmax

class PAM_Module(Module):
    """ Position attention module"""
    def __init__(self, in_dim):
        super(PAM_Module, self).__init__()
        self.chanel_in = in_dim

        self.query_conv = Conv2d(in_channels=in_dim, out_channels=in_dim//8, kernel_size=1)
        self.key_conv = Conv2d(in_channels=in_dim, out_channels=in_dim//8, kernel_size=1)
        self.value_conv = Conv2d(in_channels=in_dim, out_channels=in_dim, kernel_size=1)
        self.gamma = Parameter(torch.zeros(1))

        self.softmax = Softmax(dim=-1)
    def forward(self, x):
        """
            inputs :
                x : input feature maps( B X C X H X W)
            returns :
                out : attention value + input feature
                attention: B X (HxW) X (HxW)
        """
        m_batchsize, C, height, width = x.size()
        proj_query = self.query_conv(x).view(m_batchsize, -1, width*height).permute(0, 2, 1)
        proj_key = self.key_conv(x).view(m_batchsize, -1, width*height)
        energy = torch.bmm(proj_query, proj_key)
        attention = self.softmax(energy)
        proj_value = self.value_conv(x).view(m_batchsize, -1, width*height)
        out = torch.bmm(proj_value, attention.permute(0, 2, 1))
        out = out.view(m_batchsize, C, height, width)

        out = self.gamma*out + x
        return out

class CAM_Module(Module):
    """ Channel attention module"""
    def __init__(self, in_dim):
        super(CAM_Module, self).__init__()
        self.chanel_in = in_dim
        self.gamma = Parameter(torch.zeros(1))
        self.softmax  = Softmax(dim=-1)
    def forward(self,x):
        m_batchsize, C, height, width = x.size()
        proj_query = x.view(m_batchsize, C, -1)
        proj_key = x.view(m_batchsize, C, -1).permute(0, 2, 1)
        energy = torch.bmm(proj_query, proj_key)
        energy_new = torch.max(energy, -1, keepdim=True)[0].expand_as(energy)-energy
        attention = self.softmax(energy_new)
        proj_value = x.view(m_batchsize, C, -1)

        out = torch.bmm(attention, proj_value)
        out = out.view(m_batchsize, C, height, width)

        out = self.gamma*out + x
        return out

class DualAttention(Module):
    def __init__(self, channel=512, reduction=16, kernel_size=3):
        super().__init__()
        self.ca = PAM_Module(in_dim=channel)
        self.sa = CAM_Module(in_dim=channel)

    def init_weights(self):
        for m in self.modules():
            if isinstance(m, Conv2d):
                init.kaiming_normal_(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant_(m.weight, 1)
                init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal_(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant_(m.bias, 0)

    def forward(self, x):
        out =  self.ca(x)
        out = out + self.sa(out)
        return out
        
if __name__ == '__main__':
    input = torch.randn(50, 512, 7, 7)
    cbam = DualAttention(512)
    output = cbam(input)
    print(output.shape)