迪虎科技网站建设,dw网站首页制作,深圳有没有做网站的,白云区网络推广添加SE注意力机制 1. SE注意力机制论文#xff12;. SE注意力机制原理#xff13;. SE注意力机制的配置#xff13;.#xff11;common.py配置#xff13;.#xff12;yolo.py配置#xff13;.#xff13;yaml文件配置 1. SE注意力机制论文
论文题目#xff1a;Squee… 添加SE注意力机制 1. SE注意力机制论文. SE注意力机制原理. SE注意力机制的配置.common.py配置.yolo.py配置.yaml文件配置 1. SE注意力机制论文
论文题目Squeeze-and-Excitation Networks 论文链接Squeeze-and-Excitation Networks
. SE注意力机制原理 . SE注意力机制的配置
.common.py配置
./models/common.py文件增加以下模块 在最后添加如下代码块 import numpy as np
import torch
from torch import nn
from torch.nn import initclass SEAttention(nn.Module):def __init__(self, channel512,reduction16):super().__init__()self.avg_pool nn.AdaptiveAvgPool2d(1)self.fc nn.Sequential(nn.Linear(channel, channel // reduction, biasFalse),nn.ReLU(inplaceTrue),nn.Linear(channel // reduction, channel, biasFalse),nn.Sigmoid())def init_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d):init.kaiming_normal_(m.weight, modefan_out)if m.bias is not None:init.constant_(m.bias, 0)elif isinstance(m, nn.BatchNorm2d):init.constant_(m.weight, 1)init.constant_(m.bias, 0)elif isinstance(m, nn.Linear):init.normal_(m.weight, std0.001)if m.bias is not None:init.constant_(m.bias, 0)def forward(self, x):b, c, _, _ x.size()# # AIEAGNYy self.avg_pool(x).view(b, c)y self.fc(y).view(b, c, 1, 1)return x * y.expand_as(x)
.yolo.py配置
在 models/yolo.py文件夹下加入SEAttention
首先定位到parse_model函数中 for i, (f, n, m, args) in enumerate(d[‘backbone’] d[‘head’])模块 插入如下代码
elif m is SEAttention:c1, c2 ch[f], args[0]if c2 ! no:c2 make_divisible(c2 * gw, 8)
如图为
.yaml文件配置
这里以YOLOv5的6.0版本为例 可以在骨架网络当中添加
# YOLOv5 v6.0 backbone
backbone:[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2[-1, 1, Conv, [128, 3, 2]], # 1-P2/4[-1, 3, C3, [128]],[-1, 1, Conv, [256, 3, 2]], # 3-P3/8[-1, 6, C3, [256]],[-1, 1, Conv, [512, 3, 2]], # 5-P4/16[-1, 9, C3, [512]],[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32[-1, 3, C3, [1024]],[-1, 1, SEAttention,[1024]], #add SEAttention[-1, 1, SPPF, [1024, 5]], # 9]可以在head当中添加
# YOLOv5 v6.0 head
head:[[-1, 1, Conv, [512, 1, 1]],[-1, 1, nn.Upsample, [None, 2, nearest]],[[-1, 6], 1, Concat, [1]], # cat backbone P4[-1, 3, C3, [512, False]], # 13[-1, 1, Conv, [256, 1, 1]],[-1, 1, nn.Upsample, [None, 2, nearest]],[[-1, 4], 1, Concat, [1]], # cat backbone P3[-1, 3, C3, [256, False]], # 17 (P3/8-small)[-1, 1, Conv, [256, 3, 2]],[[-1, 14], 1, Concat, [1]], # cat head P4[-1, 3, C3, [512, False]], # 20 (P4/16-medium)[-1, 1, Conv, [512, 3, 2]],[[-1, 10], 1, Concat, [1]], # cat head P5[-1, 3, C3, [1024, False]], # 23 (P5/32-large)[-1, 1, SEAttention, [1024]],[[17, 20, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)]添加的位置可以任意就像搭积木一样但是要注意通道数是否正确。
持续更新
