YOLOV8的改进——使用LSKA注意力机制改进SPPF

 一、LSKA相关代码

1、LSKA.py

代码链接：https://gitcode.com/StevenLauHKHK/Large-Separable-Kernel-Attention/overview

相关代码在Large-Separable-Kernel-Attention/blob/main/models/van.py中。

论文链接：https://arxiv.org/pdf/2309.01439.pdf

import torch
import torch.nn as nn
import torch.nn.functional as F
from functools import partial

from timm.models.layers import DropPath, to_2tuple, trunc_normal_
from timm.models.registry import register_model
from timm.models.vision_transformer import _cfg
import math

class Mlp(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Conv2d(in_features, hidden_features, 1)
        self.dwconv = DWConv(hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Conv2d(hidden_features, out_features, 1)
        self.drop = nn.Dropout(drop)
        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)
        elif isinstance(m, nn.Conv2d):
            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
            fan_out //= m.groups
            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
            if m.bias is not None:
                m.bias.data.zero_()

    def forward(self, x):
        x = self.fc1(x)
        x = self.dwconv(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x




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_si