YOLOv8改进 - 注意力篇 - 引入LSKA注意力机制

浪子L

已于 2024-09-29 17:17:21 修改

阅读量719

点赞数 18

分类专栏： YOLOv8分析与改进文章标签：深度学习人工智能计算机视觉 python 目标检测神经网络 pytorch

于 2024-09-29 17:16:49 首次发布

本文链接：https://blog.csdn.net/2301_79619145/article/details/142633045

版权

YOLOv8分析与改进专栏收录该内容

5 篇文章 0 订阅

订阅专栏

一、本文介绍

作为入门性篇章，这里介绍了LSKA注意力在YOLOv8中的使用。包含LSKA原理分析，LSKA的代码、LSKA的使用方法、以及添加以后的yaml文件及运行记录。

二、LSKA原理分析

LSKA官方论文地址：LSKA文章

LSKA注意力机制（大可分离内核注意力）:LSKA将深度卷积层的二维卷积核分解为级联的水平和垂直的1-D核。提出的分解允许在注意力模块中直接使用大核的深度卷积层，而不需要任何额外的模块。

在VAN中LSKA模块能够达到与标准LKA模块相当的性能，并降低了计算复杂性和内存占用。随着核尺寸的增加，LSKA设计使VAN更偏向于物体的形状而非纹理。

相关代码：

LSKA注意力的代码，如下。

class LSKA(nn.Module):
    # Large-Separable-Kernel-Attention
    def __init__(self, dim, k_size=7):
        super().__init__()

        self.k_size = k_size

        if 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 * attn

四、YOLOv8中LSKA使用方法

1.YOLOv8中添加LSKA模块：

首先在ultralytics/nn/modules/conv.py最后添加LSKA模块的代码。

2.在conv.py的开头__all__ = 内添加LSKA模块的类别名：

3.在同级文件夹下的__init__.py内添加LSKA的相关内容：（分别是from .conv import LSKA ；以及在__all__内添加LSKA）

4.在ultralytics/nn/tasks.py进行LSKA注意力机制的注册，以及在YOLOv8的yaml配置文件中添加LSKA即可。

首先打开task.py文件，按住Ctrl+F，输入parse_model进行搜索。找到parse_model函数。在其最后一个else前面添加以下注册代码：

        elif m in {LSKA}:
            args = [ch[f], *args]

然后，就是新建一个名为YOLOv8_LSKA.yaml的配置文件：（路径:ultralytics/cfg/models/v8/YOLOv8_LSKA.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 CPAM-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, LSKA, [7]]#11代表卷积核大小，可以填写7、11、23、35、41、53
  - [-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, 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)

其中参数中nc，由自己的数据集决定。本文测试，采用的coco8数据集，有80个类别。

在根目录新建一个train.py文件，内容如下

from ultralytics import YOLO

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
# 加载一个模型
    model = YOLO('ultralytics/cfg/models/v8/YOLOv8_LSKA.yaml')  # 从YAML建立一个新模型
# 训练模型
    results = model.train(data='ultralytics/cfg/datasets/coco8.yaml', epochs=1,imgsz=640,optimizer="SGD")

训练输出：