YOLO11改进|注意力机制篇|引入大核可分离卷积注意力块LSKA

在这里插入图片描述

一、【LSKA】注意力机制

1.1【LSKA】注意力介绍

在这里插入图片描述

下图是【LSKA】的结构图，让我们简单分析一下运行过程和优势

(a) LKA-trivial:
工作流程：这个模块使用一个 𝑘×𝑘的深度可分离卷积（DW-Conv）来提取局部空间信息，之后再通过 1×1的卷积进行通道融合。最后将输入特征与经过卷积操作后的特征进行加法操作（残差连接）。
优势：这种设计简单且高效，通过深度卷积提取局部特征，再通过 1×1卷积整合不同通道的信息，能够有效减少计算量，同时保持良好的局部特征提取能力。
(b) LSKA-trivial:
工作流程：使用两个深度卷积操作，分别是 1×(2𝑑−1)和 (2𝑑−1)×1的卷积。这些卷积核通过不对称的卷积来捕获更多的局部信息。同样，在卷积操作后通过 1×1的卷积来整合通道信息，并使用残差连接将输入特征与输出相加。
优势：通过不对称的卷积设计，LSKA-trivial 可以扩大感受野，并且以较低的计算代价捕获更多的局部特征。
相对于 LKA-trivial，LSKA-trivial 的不对称卷积增强了对不同方向信息的捕捉能力，适合处理具有方向性变化的特征图。
© LKA:
工作流程：首先使用 1×(2𝑑−1)和 (2𝑑−1)×1的不对称卷积，之后引入了两个深度动态卷积（DW-D-Conv），它们的卷积核大小基于 𝑘/𝑑的比例计算。最后同样使用 1×1卷积进行通道融合，并通过残差连接将输入与输出相加。
优势：相较于 LSKA-trivial，LKA 模块在引入动态卷积（DW-D-Conv）的基础上，使得卷积核的大小能够适应输入特征图的变化，从而在保持高效计算的同时，增强了特征提取的自适应性。这种设计特别适用于需要同时处理细节信息和全局上下文的任务。
(d) LSKA:
工作流程：这是最复杂的结构，首先使用 1×(2𝑑−1)和 (2𝑑−1)×1
卷积，接着引入了两层动态卷积（DW-D-Conv），它们分别根据 𝑘/𝑑和 𝑘/𝑑的比例对卷积核大小进行调整。最后通过 1×1卷积整合通道信息，并与输入特征进行残差连接。
优势：LSKA 模块通过更多层次的动态卷积，使得其感受野进一步扩大，同时能够自适应地调整卷积核大小。这种多层设计确保了该模块不仅能够捕获局部的细节特征，同时具备很强的全局建模能力。
适合处理多尺度信息丰富且具有复杂局部结构的任务。
在这里插入图片描述

1.2【LSKA】核心代码

import torch
import torch.nn as nnclass LSKA(nn.Module):def __init__(self, dim, k_size=7):super().__init__()self.k_size = k_sizeif k_size == 7:self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 3), stride=(1,1), padding=(0,(3-1)//2), groups=dim)self.conv0v = nn.Conv2d(dim, dim, kernel_size=(3, 1), stride=(1,1), padding=((3-1)//2,0), groups=dim)self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 3), stride=(1,1), padding=(0,2), groups=dim, dilation=2)self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(3, 1), stride=(1,1), padding=(2,0), groups=dim, dilation=2)elif k_size == 11:self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 3), stride=(1,1), padding=(0,(3-1)//2), groups=dim)self.conv0v = nn.Conv2d(dim, dim, kernel_size=(3, 1), stride=(1,1), padding=((3-1)//2,0), groups=dim)self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,4), groups=dim, dilation=2)self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=(4,0), groups=dim, dilation=2)elif k_size == 23:self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 7), stride=(1,1), padding=(0,9), groups=dim, dilation=3)self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(7, 1), stride=(1,1), padding=(9,0), groups=dim, dilation=3)elif k_size == 35:self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 11), stride=(1,1), padding=(0,15), groups=dim, dilation=3)self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(11, 1), stride=(1,1), padding=(15,0), groups=dim, dilation=3)elif k_size == 41:self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 13), stride=(1,1), padding=(0,18), groups=dim, dilation=3)self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(13, 1), stride=(1,1), padding=(18,0), groups=dim, dilation=3)elif k_size == 53:self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 17), stride=(1,1), padding=(0,24), groups=dim, dilation=3)self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(17, 1), stride=(1,1), padding=(24,0), groups=dim, dilation=3)self.conv1 = nn.Conv2d(dim, dim, 1)def forward(self, x):u = x.clone()attn = self.conv0h(x)attn = self.conv0v(attn)attn = self.conv_spatial_h(attn)attn = self.conv_spatial_v(attn)attn = self.conv1(attn)return u * attndef 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-sizeif p is None:p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-padreturn pclass Conv(nn.Module):"""Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""default_act = nn.SiLU()  # default activationdef __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 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, andexpansion."""super().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, k[0], 1)self.cv2 = Conv(c_, c2, k[1], 1, g=g)self.add = shortcut and c1 == c2def forward(self, x):"""'forward()' applies the YOLO FPN to input data."""return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))class C2f_LSKA(nn.Module):"""CSP Bottleneck with 2 convolutions followed by LSKA attention."""def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):"""Initialize CSP bottleneck layer with two convolutions with LSKA attention."""super().__init__()self.c = int(c2 * e)  # hidden channelsself.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))self.lska = LSKA(c2)def forward(self, x):"""Forward pass through C2f layer followed by LSKA attention."""y = list(self.cv1(x).chunk(2, 1))y.extend(m(y[-1]) for m in self.m)out = self.cv2(torch.cat(y, 1))return self.lska(out)def forward_split(self, x):"""Forward pass using split() instead of chunk() followed by LSKA attention."""y = list(self.cv1(x).split((self.c, self.c), 1))y.extend(m(y[-1]) for m in self.m)out = self.cv2(torch.cat(y, 1))return self.lska(out)

二、添加【LSKA】注意力机制

2.1STEP1

首先找到ultralytics/nn文件路径下新建一个Add-module的python文件包【这里注意一定是python文件包，新建后会自动生成_init_.py】，如果已经跟着我的教程建立过一次了可以省略此步骤，随后新建一个LSKA.py文件并将上文中提到的注意力机制的代码全部粘贴到此文件中，如下图所示在这里插入图片描述

2.2STEP2

在STEP1中新建的_init_.py文件中导入增加改进模块的代码包如下图所示在这里插入图片描述

2.3STEP3

找到ultralytics/nn文件夹中的task.py文件，在其中按照下图添加在这里插入图片描述

2.4STEP4

定位到ultralytics/nn文件夹中的task.py文件中的def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)函数添加如图代码,【如果不好定位可以直接ctrl+f搜索定位】

在这里插入图片描述

三、yaml文件与运行

3.1yaml文件

以下是添加【LSKA】注意力机制在Backbone中的yaml文件，大家可以注释自行调节，效果以自己的数据集结果为准

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 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=yolo11n.yaml' will call yolo11.yaml with scale 'n'# [depth, width, max_channels]n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs# YOLO11n 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, 2, C3k2, [256, False, 0.25]]- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8- [-1, 2, C3k2, [512, False, 0.25]]- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16- [-1, 2, C3k2, [512, True]]- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32- [-1, 2, C3k2, [1024, True]]- [-1, 1, SPPF, [1024, 5]] # 9- [-1, 1, LSKA, []]- [-1, 2, C2PSA, [1024]] # 10# YOLO11n head
head:- [-1, 1, nn.Upsample, [None, 2, "nearest"]]- [[-1, 6], 1, Concat, [1]] # cat backbone P4- [-1, 2, C3k2, [512, False]] # 13- [-1, 1, nn.Upsample, [None, 2, "nearest"]]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1, 14], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 11], 1, Concat, [1]] # cat head P5- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)- [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)