YOLO算法改进1【中阶改进篇】: 添加SA-Net注意力机制

开源代码：https://github.com/wofmanaf/SA-Net
论文地址：https://arxiv.org/pdf/2102.00240.pdf

当前的 CNN 中的 attention 机制主要包括: channel attention 和 spatial attention，当前一些方法(GCNet、CBAM等) 通常将二者集成，容易产生 converging difficulty 和 heavy computationburden 的问题。尽管 ECANet和 SGE 提出了一些优化方案，但没有充分利用 channel和 spatial之间的关系。因此，作者提出一个问题“ Can one fuse diferent attention modules in a lighter but moreefficient way?"为解决这个问题，作者提出了 shufle attention，整体框架如下图所示。可以看出首先将输入的特征分为g组，然后每一组的特征进行split，分成两个分支，分别计算 channel attention 和 spatialattention，两种 attention 都使用全连接 + sigmoid 的方法计算。接着，两个分支的结果拼接到一起然后合并，得到和输入尺寸一致的 feature map。 最后，用一个shufie 层进行处理

1.增加shuffleAttention.yaml文件
添加至/models/文件中

# Parameters
nc: 80  # 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
  ]

# YOLOAir 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, ShuffleAttention, [1024]], # 修改

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

2.common.py配置
在./models/common.py文件中增加以下模板代码

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.(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

3.yolo.py配置
找到 models/yolo.py 文件中 parse_model() 函数的 for ,(f,n,m, args) in(258行上下) 并其循环内添加如下代码enumerate(dl"backbone"] + dl head"])

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

4.训练模型

python train.py --cfg ShuffleAttention.yaml

摘抄至K同学