当前位置：首页 > news >正文

YOLOv8改进SPFF-LSKA大核可分离核注意力机制

news 2025/3/10 17:29:30

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 nnclass LSKA(nn.Module):def __init__(self, dim, k_size):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 * 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 GFLOPss: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPsm: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPsl: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [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 channelsself.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)))