关于Yolov5引入SEnet,CA,CBAM,SKA等注意力模块的方法

1.本文是基于5.0版本的yolov5，其他版本大同小异。（ps:本文仅作为经验总结，方便我日后复习回顾）

   以CoordAtt(CA)为例：下载好v5.0版本后，首先在主目录models文件下创建一个yolov5m_CA的yaml文件，文件代码如下：

# parameters
nc: 80  # number of classes
depth_multiple: 0.67  # model depth multiple
width_multiple: 0.75  # layer channel multiple

# anchors
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 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 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, 9, 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, 1, SPP, [1024, [5, 9, 13]]],
   [ -1, 1, CoordAtt, [ 1024 ] ],
   [-1, 3, C3, [1024, False]],  # 9
  ]

# YOLOv5 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)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

然后在models文件目录下的common.py文件末尾增加CA相应的代码段，代码如下：

#CA
class h_sigmoid(nn.Module):
    def __init__(self, inplace=True):
        super(h_sigmoid, self).__init__()
        self.relu = nn.ReLU6(inplace=inplace)

    def forward(self, x):
        return self.relu(x + 3) / 6

class h_swish(nn.Module):
    def __init__(self, inplace=True):
        super(h_swish, self).__init__()
        self.sigmoid = h_sigmoid(inplace=inplace)

    def forward(self, x):
        return x * self.sigmoid(x)

class CoordAtt(nn.Module):
    def __init__(self, inp, oup, reduction=32):
        super(CoordAtt, self).__init__()
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        self.pool_w = nn.AdaptiveAvgPool2d((1, None))
        mip = max(8, inp // reduction)
        self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(mip)
        self.act = h_swish()
        self.conv_h = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
        self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)

    def forward(self, x):
        identity = x
        n, c, h, w = x.size()
        # c*1*W
        x_h = self.pool_h(x)
        # c*H*1
        # C*1*h
        x_w = self.pool_w(x).permute(0, 1, 3, 2)
        y = torch.cat([x_h, x_w], dim=2)
        # C*1*(h+w)
        y = self.conv1(y)
        y = self.bn1(y)
        y = self.act(y)
        x_h, x_w = torch.split(y, [h, w], dim=2)
        x_w = x_w.permute(0, 1, 3, 2)
        a_h = self.conv_h(x_h).sigmoid()
        a_w = self.conv_w(x_w).sigmoid()
        out = identity * a_w * a_h
        return out

最后更改一下models目录下yolo.py中的代码，在其中找到函数parse_model，在如图红框中插入自己定义的注意力类名(和common.py中添加的保持一致)：

 

配置就基本完成了。

最后来到主目录下的train.py文件，找到主程序中的--cfg语句，将default改为如下：

 运行,可以看到CA已经被添加进入了。

 2.其他的操作都一样，在common.py加入注意力机制代码，将上文所发yolov5m_CA.yaml文件中注意力类名更改一下要替换的注意力类名，再在yolo.py中相同位置更换类名，最后在训练的cfg代码处添加相应yaml文件运行就可以。我把我自己收纳的注意力模块代码放在下方。

CBAM

#Cbam
import torch
from torch import nn
from torch.nn.modules.activation import ReLU

class channel_attention(nn.Module):
    def __init__(self,channel,ratio=16):
        super(channel_attention,self).__init__()
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        self.avg_pool = nn.AdaptiveMaxPool2d(1)

        self.fc       = nn.Sequential(
            nn.Linear(channel,channel//ratio,False),
            nn.ReLU(),
            nn.Linear(channel//ratio,channel,False)
        )
        self.sigmoid = nn.Sigmoid()

    def forward(self,x):
        b,c,h,w = x.size()
        max_pool_out = self.max_pool(x).view([b,c])
        avg_pool_out = self.avg_pool(x).view([b,c])

        max_fc_out = self.fc(max_pool_out)
        avg_fc_out = self.fc(avg_pool_out)

        out = max_fc_out + avg_fc_out
        out = self.sigmoid(out).view([b,c,1,1])

        return out * x

class spacial_attention(nn.Module):
    def __init__(self,kernel_size=7):
        super(spacial_attention,self).__init__()
        padding = 7//2
        self.conv = nn.Conv2d(2,1,kernel_size,1,padding,bias = False)
        self.sigmoid = nn.Sigmoid()

    def forward(self,x):
        max_pool_out,_ = torch.max(x,dim = 1,keepdim=True)
        mean_pool_out,_ = torch.mean(x,dim = 1,keepdim=True)
        pool_out = torch.cat([max_pool_out,mean_pool_out],dim=1)
        out = self.conv(pool_out)
        out = self.sigmoid(out)
        return out * x

class Cbam(nn.Module):
    def __init__(self,channel,ratio = 16, kernel_size=7):
        super(Cbam, self).__init__()
        self.channel_attention = channel_attention(channel,ratio)
        self.spacial_attention = spacial_attention(kernel_size)
    def forward(self, x):
        x = self.channel_attention(x)
        x = self.spacial_attention(x)
        return x

#代表输入有512个channel
model = Cbam(512)
print(model)
#2代表的是batchsize
inputs  = torch.ones([2,512,26,26])
outputs = model(inputs)

CrissCrissAttention

'''
This code is borrowed from Serge-weihao/CCNet-Pure-Pytorch
'''

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import Softmax


def INF(B, H, W):
    return -torch.diag(torch.tensor(float("inf")).repeat(H), 0).unsqueeze(0).repeat(B * W, 1, 1)


class CrissCrossAttention(nn.Module):
    """ Criss-Cross Attention Module"""

    def __init__(self, in_dim):
        super(CrissCrossAttention, self).__init__()
        self.query_conv = nn.Conv2d(in_channels=in_dim, out_channels=in_dim // 8, kernel_size=1)
        self.key_conv = nn.Conv2d(in_channels=in_dim, out_channels=in_dim // 8, kernel_size=1)
        self.value_conv = nn.Conv2d(in_channels=in_dim, out_channels=in_dim, kernel_size=1)
        self.softmax = Softmax(dim=3)
        self.INF = INF
        self.gamma = nn.Parameter(torch.zeros(1))

    def forward(self, x):
        m_batchsize, _, height, width = x.size()
        proj_query = self.query_conv(x)
        proj_query_H = proj_query.permute(0, 3, 1, 2).contiguous().view(m_batchsize * width, -1, height).permute(0, 2,
                                                                                                                 1)
        proj_query_W = proj_query.permute(0, 2, 1, 3).contiguous().view(m_batchsize * height, -1, width).permute(0, 2,
                                                                                                                 1)
        proj_key = self.key_conv(x)
        proj_key_H = proj_key.permute(0, 3, 1, 2).contiguous().view(m_batchsize * width, -1, height)
        proj_key_W = proj_key.permute(0, 2, 1, 3).contiguous().view(m_batchsize * height, -1, width)
        proj_value = self.value_conv(x)
        proj_value_H = proj_value.permute(0, 3, 1, 2).contiguous().view(m_batchsize * width, -1, height)
        proj_value_W = proj_value.permute(0, 2, 1, 3).contiguous().view(m_batchsize * height, -1, width)
        energy_H = (torch.bmm(proj_query_H, proj_key_H) + self.INF(m_batchsize, height, width)).view(m_batchsize, width,
                                                                                                     height,
                                                                                                     height).permute(0,
                                                                                                                     2,
                                                                                                                     1,
                                                                                                                     3)
        energy_W = torch.bmm(proj_query_W, proj_key_W).view(m_batchsize, height, width, width)
        concate = self.softmax(torch.cat([energy_H, energy_W], 3))

        att_H = concate[:, :, :, 0:height].permute(0, 2, 1, 3).contiguous().view(m_batchsize * width, height, height)
        # print(concate)
        # print(att_H)
        att_W = concate[:, :, :, height:height + width].contiguous().view(m_batchsize * height, width, width)
        out_H = torch.bmm(proj_value_H, att_H.permute(0, 2, 1)).view(m_batchsize, width, -1, height).permute(0, 2, 3, 1)
        out_W = torch.bmm(proj_value_W, att_W.permute(0, 2, 1)).view(m_batchsize, height, -1, width).permute(0, 2, 1, 3)
        # print(out_H.size(),out_W.size())
        return self.gamma * (out_H + out_W) + x

ECA

import torch
from torch import nn

import math

class eca_block(nn.Module):
    def __init__(self,channel,gamma = 2,b = 1):
        super(eca_block, self).__init__()
        kernel_size = int(abs((math.log(channel,2)+b)/gamma))
        kernel_size = kernel_size if kernel_size % 2 else kernel_size +1
        padding = kernel_size // 2

        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv     = nn.Conv1d(1,1,kernel_size,padding = padding,bias=False)

    def forward(self,x):
        b,c,h,w = x.size()

        avg = self.avg_pool(x).view([b,1,c])
        out = self.conv(avg)
        out = self.sigmoid(out).view([b,c,1,1])
        return out * x

model   = eca_block(512)
print(model)
inputs  = torch.ones([2,512,26,26])
outputs = model(inputs)

ShuffleAttention

import numpy as np
import torch
from torch import nn
from torch.nn import init
from torch.nn.parameter import Parameter


# https://arxiv.org/pdf/2102.00240.pdf
class ShuffleAttention(nn.Module):

    def __init__(self, channel=512, reduction=16, G=8):
        super().__init__()
        self.G = G
        self.channel = channel
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.gn = nn.GroupNorm(channel // (2 * G), channel // (2 * G))
        self.cweight = Parameter(torch.zeros(1, channel // (2 * G), 1, 1))
        self.cbias = Parameter(torch.ones(1, channel // (2 * G), 1, 1))
        self.sweight = Parameter(torch.zeros(1, channel // (2 * G), 1, 1))
        self.sbias = Parameter(torch.ones(1, channel // (2 * G), 1, 1))
        self.sigmoid = nn.Sigmoid()

    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)

    @staticmethod
    def channel_shuffle(x, groups):
        b, c, h, w = x.shape
        x = x.reshape(b, groups, -1, h, w)
        x = x.permute(0, 2, 1, 3, 4)

        # flatten
        x = x.reshape(b, -1, h, w)

        return x

    def forward(self, x):
        b, c, h, w = x.size()
        # group into subfeatures
        x = x.view(b * self.G, -1, h, w)  # bs*G,c//G,h,w

        # channel_split
        x_0, x_1 = x.chunk(2, dim=1)  # bs*G,c//(2*G),h,w

        # channel attention
        x_channel = self.avg_pool(x_0)  # bs*G,c//(2*G),1,1
        x_channel = self.cweight * x_channel + self.cbias  # bs*G,c//(2*G),1,1
        x_channel = x_0 * self.sigmoid(x_channel)

        # spatial attention
        x_spatial = self.gn(x_1)  # bs*G,c//(2*G),h,w
        x_spatial = self.sweight * x_spatial + self.sbias  # bs*G,c//(2*G),h,w
        x_spatial = x_1 * self.sigmoid(x_spatial)  # bs*G,c//(2*G),h,w

        # concatenate along channel axis
        out = torch.cat([x_channel, x_spatial], dim=1)  # bs*G,c//G,h,w
        out = out.contiguous().view(b, -1, h, w)

        # channel shuffle
        out = self.channel_shuffle(out, 2)
        return out

SKAttention

from collections import OrderedDict

import torch
from torch import nn


class SKAttention(nn.Module):

    def __init__(self, channel=512, kernels=[1, 3, 5, 7], reduction=16, group=1, L=32):
        super().__init__()
        self.d = max(L, channel // reduction)
        self.convs = nn.ModuleList([])
        for k in kernels:
            self.convs.append(
                nn.Sequential(OrderedDict([
                    ('conv', nn.Conv2d(channel, channel, kernel_size=k, padding=k // 2, groups=group)),
                    ('bn', nn.BatchNorm2d(channel)),
                    ('relu', nn.ReLU())
                ]))
            )
        self.fc = nn.Linear(channel, self.d)
        self.fcs = nn.ModuleList([])
        for i in range(len(kernels)):
            self.fcs.append(nn.Linear(self.d, channel))
        self.softmax = nn.Softmax(dim=0)

    def forward(self, x):
        bs, c, _, _ = x.size()
        conv_outs = []
        ### split
        for conv in self.convs:
            conv_outs.append(conv(x))
        feats = torch.stack(conv_outs, 0)  # k,bs,channel,h,w

        ### fuse
        U = sum(conv_outs)  # bs,c,h,w

        ### reduction channel
        S = U.mean(-1).mean(-1)  # bs,c
        Z = self.fc(S)  # bs,d

        ### calculate attention weight
        weights = []
        for fc in self.fcs:
            weight = fc(Z)
            weights.append(weight.view(bs, c, 1, 1))  # bs,channel
        attention_weughts = torch.stack(weights, 0)  # k,bs,channel,1,1
        attention_weughts = self.softmax(attention_weughts)  # k,bs,channel,1,1

        ### fuse
        V = (attention_weughts * feats).sum(0)
        return V

我学术浅薄如果这篇文章有错误的话欢迎大家指正！