爆改YOLOv8 |利用 iAFF迭代注意力改进C2f,高效涨点

1，本文介绍

iAFF的核心思想是通过细致的注意力机制优化特征融合，从而提升卷积神经网络的性能。它不仅解决了因尺度和语义不一致导致的特征融合问题，还引入了多尺度通道注意力模块，提供了一个统一且通用的特征融合方案。此外，iAFF通过迭代应用注意力机制来解决特征图初步整合中的潜在瓶颈，使模型即使在层数或参数较少的情况下也能获得优良的效果。

iAFF的主要创新包括：

注意力特征融合：提出了利用注意力机制改进传统特征融合方法（如加和或串联）的新方式。
多尺度通道注意力模块：解决了在不同尺度上融合特征时，特别是处理语义和尺度不一致问题的挑战。
迭代注意力特征融合：通过迭代应用注意力机制，改善特征图的初步整合，克服了初步整合可能成为性能瓶颈的问题。

关于iAFF的详细介绍可以看论文:https://arxiv.org/pdf/2009.14082.pdf

本文将讲解如何将iAFF融合进yolov8

话不多说，上代码！

2，将iAFF融合进yolov8

2.1 步骤一

找到如下的目录'ultralytics/nn/modules'，然后在这个目录下创建一个iAFF.py文件，文件名字可以根据你自己的习惯起，然后将iAFF的核心代码复制进去

import torch
import torch.nn as nn
 
def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p
 
 
class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
    default_act = nn.SiLU()  # default activation
 
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
 
    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))
 
    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))
 
 
class iAFF(nn.Module):
    '''
    多特征融合 iAFF
    '''
 
    def __init__(self, channels=64, r=2):
        super(iAFF, self).__init__()
        inter_channels = int(channels // r)
 
        # 本地注意力
        self.local_att = nn.Sequential(
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
 
        # 全局注意力
        self.global_att = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
        )
 
        # 第二次本地注意力
        self.local_att2 = nn.Sequential(
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
        # 第二次全局注意力
        self.global_att2 = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
 
        self.sigmoid = nn.Sigmoid()
 
    def forward(self, x, residual):
 
        xa = x + residual
        xl = self.local_att(xa)
        xg = self.global_att(xa)
        xlg = xl + xg
        wei = self.sigmoid(xlg)
        xi = x * wei + residual * (1 - wei)
 
        xl2 = self.local_att2(xi)
        xg2 = self.global_att(xi)
        xlg2 = xl2 + xg2
        wei2 = self.sigmoid(xlg2)
        xo = x * wei2 + residual * (1 - wei2)
        return xo
 
 
class AFF(nn.Module):
    '''
    多特征融合 AFF
    '''
 
    def __init__(self, channels=64, r=4):
        super(AFF, self).__init__()
        inter_channels = int(channels // r)
 
        self.local_att = nn.Sequential(
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
 
        self.global_att = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
 
        self.sigmoid = nn.Sigmoid()
 
    def forward(self, x, residual):
        xa = x + residual
        xl = self.local_att(xa)
        xg = self.global_att(xa)
        xlg = xl + xg
        wei = self.sigmoid(xlg)
 
        xo = 2 * x * wei + 2 * residual * (1 - wei)
        return xo
 
 
 
class C2f_iAFF(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
 
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
        expansion.
        """
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))
 
    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
 
    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
 
class Bottleneck(nn.Module):
    """Standard bottleneck."""
 
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
        expansion.
        """
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2
        self.iAFF = iAFF(c2)
    def forward(self, x):
        """'forward()' applies the YOLO FPN to input data."""
        if self.add:
           results =  self.iAFF(x , self.cv2(self.cv1(x)))
        else:
            results = self.cv2(self.cv1(x))
        return results
 
 
if __name__ == '__main__':
    x = torch.ones(8, 64, 32, 32)
    channels = x.shape[1]
    model = C2f_iAFF(channels, channels, True)
    output = model(x)
    print(output.shape)

2.2 步骤二

在task.py中导入iAFF，如下图所示

2.3 步骤三

在task.py中注册C2f_iAFF,如下图所示，需要在两个位置添加

到此注册成功,复制后面的yaml文件直接运行即可

yaml文件

# 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 GFLOP
 
# 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_iAFF, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f_iAFF, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f_iAFF, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f_iAFF, [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)
 
 
  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

不知不觉已经看完了哦，动动小手留个点赞吧--_--