改进YOLOv5、YOLOv8系列:18.添加SOCA注意力机制

最新创新点改进推荐

-💡统一使用 YOLO 代码框架,结合不同模块来构建不同的YOLO目标检测模型。

🔥 《芒果书》系列改进专栏内的改进文章,均包含多种模型改进方式,均适用于YOLOv3YOLOv4YOLORYOLOXYOLOv5YOLOv7YOLOv8 改进(重点)!!!

🔥 专栏创新点教程 均有不少同学反应和我说已经在自己的数据集上有效涨点啦!! 包括COCO数据集也能涨点

所有文章博客均包含 改进源代码部分,一键训练即可

🔥 对应专栏订阅的越早,就可以越早使用原创创新点去改进模型,抢先一步

YOLOv8 + 改进注意力机制

详细内容
参考这篇博客:点击查看详情:YOLOv5改进、YOLOv7、YOLOv8改进|YOLO改进超过多种注意力机制,全篇共计30万字(内附改进源代码),原创改进多种Attention注意力机制和Transformer自注意力机制


YOLOv5、YOLOv7、YOLOv8 模型全系列最新改进方式教程(内附原代码)

🔥 《芒果书》系列改进专栏内的改进文章

专栏地址:独家全网首发专栏《芒果YOLOv8深度改进教程》🍊

专栏地址:独家全网首发专栏《芒果YOLOv5深度改进教程》🥝

专栏地址:独家全网首发专栏《芒果YOLOv7深度改进教程》🍉


YOLOv5、YOLOv7 + 注意力机制一览

YOLOv5、YOLOv7 + 注意力机制一览

YOLOv5 + ShuffleAttention注意力机制
博客链接🔗🌟:改进YOLOv5系列:12.添加ShuffleAttention注意力机制
YOLOv5 + CrissCrossAttention注意力机制
博客链接🔗🌟:改进YOLOv5系列:13.添加CrissCrossAttention注意力机制
YOLOv5 + S2-MLPv2注意力机制
博客链接🔗🌟:改进YOLOv5系列:14.添加S2-MLPv2注意力机制
YOLOv5 + SimAM注意力机制
博客链接🔗🌟:改进YOLOv5系列:15.添加SimAM注意力机制
YOLOv5 + SKAttention注意力机制
博客链接🔗🌟:改进YOLOv5系列:16.添加SKAttention注意力机制
YOLOv5 + NAMAttention注意力机制
博客链接🔗🌟:改进YOLOv5系列:17.添加NAMAttention注意力机制
YOLOv5 + SOCA注意力机制
博客链接🔗🌟:改进YOLOv5系列:18.添加SOCA注意力机制
YOLOv5 + CBAM注意力机制
博客链接🔗🌟:改进YOLOv5系列:18.添加CBAM注意力机制
YOLOv5 + SEAttention注意力机制
博客链接🔗🌟:改进YOLOv5系列:19.添加SEAttention注意力机制
YOLOv5 + GAMAttention注意力机制
博客链接🔗🌟:改进YOLOv5系列:20.添加GAMAttention注意力机制
YOLOv5 + CA注意力机制
博客链接🔗🌟:github
YOLOv5 + ECA注意力机制 博客链接🔗🌟:github
更多模块详细解释持续更新中。。。

之后继续更新🔥🔥🔥

第一种、YOLOv5使用SOCA注意力机制

SOCA注意力机制原理图

请添加图片描述

1.1增加以下SOCA.yaml文件

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# 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
  ]

# 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, SOCA, [1024]],

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

1.2common.py配置

./models/common.py文件增加以下模块

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

from torch.autograd import Function

class Covpool(Function):
     @staticmethod
     def forward(ctx, input):
         x = input
         batchSize = x.data.shape[0]
         dim = x.data.shape[1]
         h = x.data.shape[2]
         w = x.data.shape[3]
         M = h*w
         x = x.reshape(batchSize,dim,M)
         I_hat = (-1./M/M)*torch.ones(M,M,device = x.device) + (1./M)*torch.eye(M,M,device = x.device)
         I_hat = I_hat.view(1,M,M).repeat(batchSize,1,1).type(x.dtype)
         y = x.bmm(I_hat).bmm(x.transpose(1,2))
         ctx.save_for_backward(input,I_hat)
         return y
     @staticmethod
     def backward(ctx, grad_output):
         input,I_hat = ctx.saved_tensors
         x = input
         batchSize = x.data.shape[0]
         dim = x.data.shape[1]
         h = x.data.shape[2]
         w = x.data.shape[3]
         M = h*w
         x = x.reshape(batchSize,dim,M)
         grad_input = grad_output + grad_output.transpose(1,2)
         grad_input = grad_input.bmm(x).bmm(I_hat)
         grad_input = grad_input.reshape(batchSize,dim,h,w)
         return grad_input

class Sqrtm(Function):
     @staticmethod
     def forward(ctx, input, iterN):
         x = input
         batchSize = x.data.shape[0]
         dim = x.data.shape[1]
         dtype = x.dtype
         I3 = 3.0*torch.eye(dim,dim,device = x.device).view(1, dim, dim).repeat(batchSize,1,1).type(dtype)
         normA = (1.0/3.0)*x.mul(I3).sum(dim=1).sum(dim=1)
         A = x.div(normA.view(batchSize,1,1).expand_as(x))
         Y = torch.zeros(batchSize, iterN, dim, dim, requires_grad = False, device = x.device)
         Z = torch.eye(dim,dim,device = x.device).view(1,dim,dim).repeat(batchSize,iterN,1,1)
         if iterN < 2:
            ZY = 0.5*(I3 - A)
            Y[:,0,:,:] = A.bmm(ZY)
         else:
            ZY = 0.5*(I3 - A)
            Y[:,0,:,:] = A.bmm(ZY)
            Z[:,0,:,:] = ZY
            for i in range(1, iterN-1):
               ZY = 0.5*(I3 - Z[:,i-1,:,:].bmm(Y[:,i-1,:,:]))
               Y[:,i,:,:] = Y[:,i-1,:,:].bmm(ZY)
               Z[:,i,:,:] = ZY.bmm(Z[:,i-1,:,:])
            ZY = 0.5*Y[:,iterN-2,:,:].bmm(I3 - Z[:,iterN-2,:,:].bmm(Y[:,iterN-2,:,:]))
         y = ZY*torch.sqrt(normA).view(batchSize, 1, 1).expand_as(x)
         ctx.save_for_backward(input, A, ZY, normA, Y, Z)
         ctx.iterN = iterN
         return y
     @staticmethod
     def backward(ctx, grad_output):
         input, A, ZY, normA, Y, Z = ctx.saved_tensors
         iterN = ctx.iterN
         x = input
         batchSize = x.data.shape[0]
         dim = x.data.shape[1]
         dtype = x.dtype
         der_postCom = grad_output*torch.sqrt(normA).view(batchSize, 1, 1).expand_as(x)
         der_postComAux = (grad_output*ZY).sum(dim=1).sum(dim=1).div(2*torch.sqrt(normA))
         I3 = 3.0*torch.eye(dim,dim,device = x.device).view(1, dim, dim).repeat(batchSize,1,1).type(dtype)
         if iterN < 2:
            der_NSiter = 0.5*(der_postCom.bmm(I3 - A) - A.bmm(der_sacleTrace))
         else:
            dldY = 0.5*(der_postCom.bmm(I3 - Y[:,iterN-2,:,:].bmm(Z[:,iterN-2,:,:])) -
                          Z[:,iterN-2,:,:].bmm(Y[:,iterN-2,:,:]).bmm(der_postCom))
            dldZ = -0.5*Y[:,iterN-2,:,:].bmm(der_postCom).bmm(Y[:,iterN-2,:,:])
            for i in range(iterN-3, -1, -1):
               YZ = I3 - Y[:,i,:,:].bmm(Z[:,i,:,:])
               ZY = Z[:,i,:,:].bmm(Y[:,i,:,:])
               dldY_ = 0.5*(dldY.bmm(YZ) - 
                         Z[:,i,:,:].bmm(dldZ).bmm(Z[:,i,:,:]) - 
                             ZY.bmm(dldY))
               dldZ_ = 0.5*(YZ.bmm(dldZ) - 
                         Y[:,i,:,:].bmm(dldY).bmm(Y[:,i,:,:]) -
                            dldZ.bmm(ZY))
               dldY = dldY_
               dldZ = dldZ_
            der_NSiter = 0.5*(dldY.bmm(I3 - A) - dldZ - A.bmm(dldY))
         grad_input = der_NSiter.div(normA.view(batchSize,1,1).expand_as(x))
         grad_aux = der_NSiter.mul(x).sum(dim=1).sum(dim=1)
         for i in range(batchSize):
             grad_input[i,:,:] += (der_postComAux[i] \
                                   - grad_aux[i] / (normA[i] * normA[i])) \
                                   *torch.ones(dim,device = x.device).diag()
         return grad_input, None

def CovpoolLayer(var):
    return Covpool.apply(var)

def SqrtmLayer(var, iterN):
    return Sqrtm.apply(var, iterN)

class SOCA(nn.Module):
    # second-order Channel attention
    def __init__(self, channel, reduction=8):
        super(SOCA, self).__init__()
        self.max_pool = nn.MaxPool2d(kernel_size=2)

        self.conv_du = nn.Sequential(
            nn.Conv2d(channel, channel // reduction, 1, padding=0, bias=True),
            nn.ReLU(inplace=True),
            nn.Conv2d(channel // reduction, channel, 1, padding=0, bias=True),
            nn.Sigmoid()
        )

    def forward(self, x):
        batch_size, C, h, w = x.shape  # x: NxCxHxW
        N = int(h * w)
        min_h = min(h, w)
        h1 = 1000
        w1 = 1000
        if h < h1 and w < w1:
            x_sub = x
        elif h < h1 and w > w1:
            W = (w - w1) // 2
            x_sub = x[:, :, :, W:(W + w1)]
        elif w < w1 and h > h1:
            H = (h - h1) // 2
            x_sub = x[:, :, H:H + h1, :]
        else:
            H = (h - h1) // 2
            W = (w - w1) // 2
            x_sub = x[:, :, H:(H + h1), W:(W + w1)]
        cov_mat = CovpoolLayer(x_sub) # Global Covariance pooling layer
        cov_mat_sqrt = SqrtmLayer(cov_mat,5) # Matrix square root layer( including pre-norm,Newton-Schulz iter. and post-com. with 5 iteration)
        cov_mat_sum = torch.mean(cov_mat_sqrt,1)
        cov_mat_sum = cov_mat_sum.view(batch_size,C,1,1)
        y_cov = self.conv_du(cov_mat_sum)
        return y_cov*x

  

1.3yolo.py配置

在 models/yolo.py文件夹下

  • 定位到parse_model函数中
  • for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):内部
  • 对应位置 下方只需要新增以下代码
elif m is SOCA:
    c1, c2 = ch[f], args[0]
    if c2 != no:
        c2 = make_divisible(c2 * gw, 8)
    args = [c1, *args[1:]]

1.4训练模型

python train.py --cfg yolov5_SOCA.yaml

往期YOLO改进教程导航

11.改进YOLOv5系列:11.ConvNeXt结合YOLO | CVPR2022 多种搭配,即插即用 | Backbone主干CNN模型

10.改进YOLOv5系列:10.最新HorNet结合YOLO应用首发! | ECCV2022出品,多种搭配,即插即用 | Backbone主干、递归门控卷积的高效高阶空间交互

9.改进YOLOv5系列:9.BoTNet Transformer结构的修改

8.改进YOLOv5系列:8.增加ACmix结构的修改,自注意力和卷积集成

7.改进YOLOv5系列:7.修改DIoU-NMS,SIoU-NMS,EIoU-NMS,CIoU-NMS,GIoU-NMS

6.改进YOLOv5系列:6.修改Soft-NMS,Soft-CIoUNMS,Soft-SIoUNMS

5.改进YOLOv5系列:5.CotNet Transformer结构的修改

4.改进YOLOv5系列:4.YOLOv5_最新MobileOne结构换Backbone修改

3.改进YOLOv5系列:3.Swin Transformer结构的修改

2.改进YOLOv5系列:2.PicoDet结构的修改

1.改进YOLOv5系列:1.多种注意力机制修改

评论 12
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

芒果汁没有芒果

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值