当前位置： 首页 > article >正文

YOLOv8改进SPFF-LSKA大核可分离核注意力机制

article 2025/3/8 10:46:41

YOLOv8改进------------SPFF-LSKA

    • 1、LSAK.py代码
    • 2、添加YAML文件yolov8_SPPF_LSKA.yaml
    • 3、添加SPPF_LSKA代码
    • 4、ultralytics/nn/modules/__init__.py注册模块
    • 5、ultralytics/nn/tasks.py注册模块
    • 6、导入yaml文件训练

1、LSAK.py代码

论文
代码

LSKA.py添加到ultralytics/nn/modules中
在这里插入图片描述

import torch
import torch.nn as nn
 
 
class LSKA(nn.Module):
    def __init__(self, dim, k_size):
        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

2、添加YAML文件yolov8_SPPF_LSKA.yaml

添加到v8配置文件中ultralytics/cfg/models/v8/yolov8_SPPF_LSKA.yaml
在这里插入图片描述

# 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: 7  # 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_LSKA, [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)

3、添加SPPF_LSKA代码

(1)SPPF_LSKA代码添加到ultralytics/nn/modules/block.py
在这里插入图片描述

class SPPF_LSKA(nn.Module):
    """Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher."""
 
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
        self.lska = LSKA(c_ * 4, k_size=11)
 
    def forward(self, x):
        """Forward pass through Ghost Convolution block."""
        x = self.cv1(x)
        y1 = self.m(x)
        y2 = self.m(y1)
        return self.cv2(self.lska(torch.cat((x, y1, y2, self.m(y2)), 1)))

(2)block.py代码顶部__all__中添加’SPPF_LSKA’，并导入LSKA模块，添加时一定注意使用英文标点符号。

'SPPF_LSKA'

from .LSKA import LSKA

在这里插入图片描述

4、ultralytics/nn/modules/init.py注册模块

(1).block中导入SPPF_LSKA
在这里插入图片描述
(2)__all__中添加 ‘SPPF_LSKA’
在这里插入图片描述

5、ultralytics/nn/tasks.py注册模块

(2)在from ultralytics.nn.modules import导入SPPF_LSKA
在这里插入图片描述
(2)tasks.py中的def parse_model的if m in 语句中添加SPPF_LSKA

在这里插入图片描述

6、导入yaml文件训练

在这里插入图片描述

成功！！！！！！！
参考文章
https://blog.csdn.net/2301_78698967/article/details/139765522
https://blog.csdn.net/pope888/article/details/135536385


http://www.kler.cn/a/574203.html

相关文章：

  • linux上配置免密登录
  • react中的fiber和初次渲染
  • 爬虫逆向：脱壳工具Youpk的使用详解
  • rust笔记12：rust的泛型
  • 计网学习———网络安全
  • Uniapp使用wxml-to-canvas进行动态页面转图片
  • Better-SQLite3 参数绑定详解
  • 多模态模型在做选择题时，如何设置Prompt，如何精准定位我们需要的选项
  • 装饰器模式：灵活扩展对象功能的利器
  • 如何高效使用 Mybatis-Plus 的批量操作
  • CDH下配置Flume进行配置传输日志文件
  • 深入探究C++并发编程：信号 异步 原子
  • muduo库源码分析:TcpConnection 类
  • better-sqlite3之exec方法
  • 【深度学习】Adam（Adaptive Moment Estimation）优化算法
  • dify + ollama + deepseek-r1+ stable-diffusion 构建绘画智能体
  • 从零开始在Windows使用VMware虚拟机安装黑群晖7.2系统并实现远程访问
  • .keystore文件转成pkcs1.pem文件记录
  • 阿里云 DataWorks面试题集锦及参考答案
  • 产品需求分析-概览