YOLOv8添加CBAM注意力机制

运行成功界面

1.在ultralytics/nn/modules中添加CBAM.py

import numpy as np
import torch
from torch import nn

from torch.nn import init
 
 
class ChannelAttentionModule(nn.Module):
    def __init__(self, c1, reduction=16):
        super(ChannelAttentionModule, self).__init__()
        mid_channel = c1 // reduction
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)

        self.shared_MLP = nn.Sequential(
            nn.Linear(in_features=c1, out_features=mid_channel),
            nn.LeakyReLU(0.1, inplace=True),
            nn.Linear(in_features=mid_channel, out_features=c1)
        )
        self.act = nn.Sigmoid()
        #self.act=nn.SiLU()
    def forward(self, x):
        avgout = self.shared_MLP(self.avg_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
        maxout = self.shared_MLP(self.max_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
        return self.act(avgout + maxout)
        
class SpatialAttentionModule(nn.Module):
    def __init__(self):
        super(SpatialAttentionModule, self).__init__()
        self.conv2d = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=7, stride=1, padding=3)
        self.act = nn.Sigmoid()
    def forward(self, x):
        avgout = torch.mean(x, dim=1, keepdim=True)
        maxout, _ = torch.max(x, dim=1, keepdim=True)
        out = torch.cat([avgout, maxout], dim=1)
        out = self.act(self.conv2d(out))
        return out


class CBAM(nn.Module):
    def __init__(self, c1,c2):
        super(CBAM, self).__init__()
        self.channel_attention = ChannelAttentionModule(c1)
        self.spatial_attention = SpatialAttentionModule()

    def forward(self, x):
        out = self.channel_attention(x) * x
        out = self.spatial_attention(out) * out
        return out

2.在ultralytics/nn/modules/__init__.py中添加

from ultralytics.nn.modules.CBAM import CBAM

之后在__all__ = （    ）中添加"CBAM"，注意不要遗漏逗号

 3.在ultralytics/nn/tasks.py添加

from ultralytics.nn.modules.CBAM import CBAM

 之后在def parse_model(d, ch, verbose=True):函数中的添加CBAM

        if m in (
            Classify,
            Conv,C2f_SCConv,
            ODConv,VoVGSCSP, VoVGSCSPC,GSConv,
            C2f_iRMB,SwinTransformer,
            ConvTranspose,
            GhostConv,
            Bottleneck,EVCBlock,
            GhostBottleneck,C2f_LSKA_Attention,LSKA_Attention,LSKA,
            SPP,CSPStage,
            MobileOneBlock,
            SPPF, C2f_Faster,
            DWConv,
            Focus,SEAM,MultiSEAM,
            BottleneckCSP,
            C1,SAConv2d,C2f_SAConv,Bottleneck_SAConv,
            C2,
            C2f,
            RepNCSPELAN4,
            ADown,
            SPPELAN,
            C2fAttn,
            C3,CondConv2D,
            C3TR,
            C3Ghost,
            nn.ConvTranspose2d,
            DWConvTranspose2d,
            C3x,CSPPC,
            CBAM,
            EMA_attention,
            RepC3,
        ):
            c1, c2 = ch[f], args[0]
            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
                c2 = make_divisible(min(c2, max_channels) * width, 8)

4.在ultralytics/cfg/models/v8新建yolov8-CBAM.yaml

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]]  # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)
  - [-1, 1, CBAM, [1024]]  # 21 (P5/32-large)

  - [[15, 18, 22], 1, Detect, [nc]]  # Detect(P3, P4, P5)