YOLOv5改进---注意力机制：DoubleAttention注意力，SENet进阶版本

######################  DoubleAttention   ####     end   by  AI&CV  ###############################

import numpy as np
import torch
from torch import nn
from torch.nn import init
from torch.nn import functional as F



class DoubleAttention(nn.Module):

    def __init__(self, in_channels,c_m=128,c_n=128,reconstruct = True):
        super().__init__()
        self.in_channels=in_channels
        self.reconstruct = reconstruct
        self.c_m=c_m
        self.c_n=c_n
        self.convA=nn.Conv2d(in_channels,c_m,1)
        self.convB=nn.Conv2d(in_channels,c_n,1)
        self.convV=nn.Conv2d(in_channels,c_n,1)
        if self.reconstruct:
            self.conv_reconstruct = nn.Conv2d(c_m, in_channels, kernel_size = 1)
        self.init_weights()


    def init_weights(self):
        for m in self.modules():
            if isinstance(m, nn.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):
        b, c, h,w=x.shape
        assert c==self.in_channels
        A=self.convA(x) #b,c_m,h,w
        B=self.convB(x) #b,c_n,h,w
        V=self.convV(x) #b,c_n,h,w
        tmpA=A.view(b,self.c_m,-1)
        attention_maps=F.softmax(B.view(b,self.c_n,-1))
        attention_vectors=F.softmax(V.view(b,self.c_n,-1))
        # step 1: feature gating
        global_descriptors=torch.bmm(tmpA,attention_maps.permute(0,2,1)) #b.c_m,c_n
        # step 2: feature distribution
        tmpZ = global_descriptors.matmul(attention_vectors) #b,c_m,h*w
        tmpZ=tmpZ.view(b,self.c_m,h,w) #b,c_m,h,w
        if self.reconstruct:
            tmpZ=self.conv_reconstruct(tmpZ)

        return tmpZ
######################  DoubleAttention   ####     end   by  AI&CV  ###############################

        elif m is DoubleAttention:
            c1, c2 = ch[f], args[0]
            if c2 != no:
                c2 = make_divisible(c2 * gw, 8)
            args = [c1, *args[1:]]

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 1  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
   [-1, 1, DoubleAttention, [1024]],  # 24

   [[17, 20, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]