YOLOv13改进|注意力机制ParNetAttention深度解析：YOLOv13并行网络注意力机制的创新设计融合通道注意力、空间注意力和残差连接的优势-CSDN博客

本文链接：https://blog.csdn.net/FJN110/article/details/150790654

文章目录

源码手把手教程
YOLOv13添加注意力机制ParNetAttention深度解析：并行网络注意力机制的创新设计融合通道注意力、空间注意力和残差连接的优势

源码手把手教程

创建ultralytics\nn\ParNetAttention.py

import numpy as np
import torch
from torch import nn
from torch.nn import init

class ParNetAttention(nn.Module):

    def __init__(self, channel=512):
        super().__init__()
        self.sse = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(channel, channel, kernel_size=1),
            nn.Sigmoid()
        )

        self.conv1x1 = nn.Sequential(
            nn.Conv2d(channel, channel, kernel_size=1),
            nn.BatchNorm2d(channel)
        )
        self.conv3x3 = nn.Sequential(
            nn.Conv2