YOLOv8添加GAM注意力机制

运行成功界面

paper：https://arxiv.org/pdf/2112.05561v1.pdf

文章引入了3D-permutation 与多层感知器的通道注意力和卷积空间注意力子模块。在CIFAR-100和ImageNet-1K上对所提出的图像分类机制的评估表明，此注意力机制优于最近的几个注意力机制，包括ResNet和轻量级的MobileNet。GAM全称为Global Attention Mechanism.

1.在ultralytics/nn/modules中添加GAM_Attention.py

 
import torch
import torch.nn as nn
from torch.nn import functional as F
 
class ChannelAttention(nn.Module):
    # Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet
    def __init__(self, channels: int) -> None:
        super().__init__()
        self.pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)
        self.act = nn.Sigmoid()
 
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        return x * self.act(self.fc(self.pool(x)))
 
 
class SpatialAttention(nn.Module):
    # Spatial-attention module
    def __init__(self, kernel_size=7):
        super().__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.act = nn.Sigmoid()
 
    def forward(self, x):
        return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))
 
 
def channel_shuffle(x, groups=2):  ##shuffle channel
    # RESHAPE----->transpose------->Flatten
    B, C, H, W = x.size()
    out = x.view(B, groups, C // groups, H, W).permute(0, 2, 1, 3, 4).contiguous()
    out = out.view(B, C, H, W)
    return out
 
 
class GAM_Attention(nn.Module):
   
    def __init__(self, c1, c2, group=True, rate=4):
        super(GAM_Attention, self).__init__()
 
        self.channel_attention = nn.Sequential(
            nn.Linear(c1, int(c1 / rate)),
            nn.ReLU(inplace=True),
            nn.Linear(int(c1 / rate), c1)
        )
 
        self.spatial_attention = nn.Sequential(
 
            nn.Conv2d(c1, c1 // rate, kernel_size=7, padding=3, groups=rate) if group else nn.Conv2d(c1, int(c1 / rate),
                                                                                                     kernel_size=7,
                                                                                                     padding=3),
            nn.BatchNorm2d(int(c1 / rate)),
            nn.ReLU(inplace=True),
            nn.Conv2d(c1 // rate, c2, kernel_size=7, padding=3, groups=rate) if group else nn.Conv2d(int(c1 / rate), c2,
                                                                                                     kernel_size=7,
                                                                                                     padding=3),
            nn.BatchNorm2d(c2)
        )
 
    def forward(self, x):
        b, c, h, w = x.shape
        x_permute = x.permute(0, 2, 3, 1).view(b, -1, c)
        x_att_permute = self.channel_attention(x_permute).view(b, h, w, c)
        x_channel_att = x_att_permute.permute(0, 3, 1, 2)
        # x_channel_att=channel_shuffle(x_channel_att,4) #last shuffle
        x = x * x_channel_att
 
        x_spatial_att = self.spatial_attention(x).sigmoid()
        x_spatial_att = channel_shuffle(x_spatial_att, 4)  # last shuffle
        out = x * x_spatial_att
        # out=channel_shuffle(out,4) #last shuffle
        return out
 

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

from ultralytics.nn.modules.GAM_attention import GAM_Attention

之后在__all__ = （    ）中添加"GMA_Attention"，注意不要遗漏逗号

 3.在ultralytics/nn/tasks.py添加

from ultralytics.nn.modules.GAM_attention import GAM_Attention

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

        if m in (
            Classify,
            Conv,C2f_SCConv,
            ODConv,VoVGSCSP, VoVGSCSPC,GSConv,
            C2f_iRMB,SwinTransformer,
            ConvTranspose,GAM_Attention,
            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-GAM.yaml

添加一层注意力机制后，检测头部分的相应层数要调整。

#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
  - [-1, 1, GAM_Attention, [1024]]

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, 13], 1, Concat, [1]] # cat head P4
  - [-1, 3, C2f, [512]] # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 3, C2f, [1024]] # 21 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)