算法改进NO.4]添加ECA通道注意力机制"/>
[YOLOv7/YOLOv5系列算法改进NO.4]添加ECA通道注意力机制
前 言
作为当前先进的深度学习目标检测算法YOLOv5,已经集合了大量的trick,但是在处理一些复杂背景问题的时候,还是容易出现错漏检的问题。此后的系列文章,将重点对YOLOv5的如何改进进行详细的介绍,目的是为了给那些搞科研的同学需要创新点或者搞工程项目的朋友需要达到更好的效果提供自己的微薄帮助和参考。
一、解决问题
加入ECA注意力机制,可以让网络更加关注待检测目标,提高检测效果。该注意力机制为一篇CVPR2020上对通道注意力进行改进的文章---ECANet,ECANet主要对SENet模块进行了一些改进,提出了一种不降维的局部跨信道交互策略(ECA模块)和自适应选择一维卷积核大小的方法,从而实现了性能上的提优。
二、YOLOv7添加方法
第一步:确定添加的位置,作为即插即用的注意力模块,可以添加到YOLOv7网络中的任何地方。
第二步:common.py构建 Eca_layer模块。
class Eca_layer(nn.Module):"""Constructs a ECA module.Args:channel: Number of channels of the input feature mapk_size: Adaptive selection of kernel size"""def __init__(self, channel, k_size=3):super(Eca_layer, self).__init__()self.avg_pool = nn.AdaptiveAvgPool2d(1)self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False)self.sigmoid = nn.Sigmoid()def forward(self, x):# x: input features with shape [b, c, h, w]b, c, h, w = x.size()# feature descriptor on the global spatial informationy = self.avg_pool(x)# Two different branches of ECA moduley = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)# Multi-scale information fusiony = self.sigmoid(y)return x * y.expand_as(x)
第三步:yolo.py中注册Eca_layer模块
elif m is Eca_layer:channel,k_size=args[0],args[1]channel = make_divisible(channel * gw, 8) if channel != no else channelargs = [channel, k_size]
第四步:修改YOLOv7.yaml文件,本文以修改backbone为例。
# parameters
nc: 1 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple# anchors
anchors:- [12,16, 19,36, 40,28] # P3/8- [36,75, 76,55, 72,146] # P4/16- [142,110, 192,243, 459,401] # P5/32# yolov7 backbone
backbone:# [from, number, module, args][[-1, 1, Conv, [32, 3, 1]], # 0[-1, 1, Conv, [64, 3, 2]], # 1-P1/2 [-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [128, 3, 2]], # 3-P2/4 [-1, 1, Conv, [64, 1, 1]],[-2, 1, Conv, [64, 1, 1]],[-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [64, 3, 1]],[[-1, -3, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [256, 1, 1]], # 11[-1, 1, MP, []],[-1, 1, Conv, [128, 1, 1]],[-3, 1, Conv, [128, 1, 1]],[-1, 1, Conv, [128, 3, 2]],[[-1, -3], 1, Concat, [1]], # 16-P3/8 [-1, 1, Conv, [128, 1, 1]],[-2, 1, Conv, [128, 1, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[[-1, -3, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [512, 1, 1]], # 24[-1, 1, MP, []],[-1, 1, Conv, [256, 1, 1]],[-3, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [256, 3, 2]],[[-1, -3], 1, Concat, [1]], # 29-P4/16 [-1, 1, Conv, [256, 1, 1]],[-2, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[[-1, -3, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [1024, 1, 1]], # 37[-1, 1, MP, []],[-1, 1, Conv, [512, 1, 1]],[-3, 1, Conv, [512, 1, 1]],[-1, 1, Conv, [512, 3, 2]],[[-1, -3], 1, Concat, [1]], # 42-P5/32 [-1, 1, Conv, [256, 1, 1]],[-2, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[[-1, -3, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [1024, 1, 1]], # 50[-1,1,Eca_layer,[1024,3]],]# yolov7 head
head:[[-1, 1, SPPCSPC, [512]], # 51[-1, 1, Conv, [256, 1, 1]],[-1, 1, nn.Upsample, [None, 2, 'nearest']],[37, 1, Conv, [256, 1, 1]], # route backbone P4[[-1, -2], 1, Concat, [1]],[-1, 1, Conv, [256, 1, 1]],[-2, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [256, 1, 1]], # 63[-1, 1, Conv, [128, 1, 1]],[-1, 1, nn.Upsample, [None, 2, 'nearest']],[24, 1, Conv, [128, 1, 1]], # route backbone P3[[-1, -2], 1, Concat, [1]],[-1, 1, Conv, [128, 1, 1]],[-2, 1, Conv, [128, 1, 1]],[-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [64, 3, 1]],[-1, 1, Conv, [64, 3, 1]],[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [128, 1, 1]], # 75[-1, 1, MP, []],[-1, 1, Conv, [128, 1, 1]],[-3, 1, Conv, [128, 1, 1]],[-1, 1, Conv, [128, 3, 2]],[[-1, -3, 63], 1, Concat, [1]],[-1, 1, Conv, [256, 1, 1]],[-2, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[-1, 1, Conv, [128, 3, 1]],[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [256, 1, 1]], # 88[-1, 1, MP, []],[-1, 1, Conv, [256, 1, 1]],[-3, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [256, 3, 2]],[[-1, -3, 52], 1, Concat, [1]],[-1, 1, Conv, [512, 1, 1]],[-2, 1, Conv, [512, 1, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[-1, 1, Conv, [256, 3, 1]],[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [512, 1, 1]], # 101[76, 1, RepConv, [256, 3, 1]],[89, 1, RepConv, [512, 3, 1]],[102, 1, RepConv, [1024, 3, 1]],[[103,104,105], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)]
根据yaml文件画出网络结构图如下所示:
三、YOLOv5添加方法
前三步同YOLOv7方法。
第四步:修改yaml文件,本文以修改backbone为例,将原C3模块后加入该模块。
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license# Parameters
nc: 4 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:- [10,13, 16,30, 33,23] # P3/8- [30,61, 62,45, 59,119] # P4/16- [116,90, 156,198, 373,326] # P5/32# YOLOv5 v6.0 backbone
backbone:# [from, number, module, args][[-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, SPPF, [1024, 5]], # 9[-1,1,Eca_layer,[1024,3]],]# 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)[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)]
第五步:将train.py中改为本文的yaml文件即可,开始训练。
结 果:本人在多个数据集上做了大量实验,针对不同的数据集效果不同,同一个数据集的不同添加位置方法也是有差异,需要大家进行实验。有效果有提升的情况占大多数。
预告一下:下一篇内容分享如何修改特征融合网络结构,将原BIFPN改为BIFPN,提升算法特征融合能力。有兴趣的朋友可以关注一下我,有问题可以留言或者私聊我哦
PS:ECA注意力机制,不仅仅是可以添加进YOLOv5,也可以添加进任何其他的深度学习网络,不管是分类还是检测还是分割,主要是计算机视觉领域,都可能会有不同程度的提升效果。
最后,希望能互粉一下,做个朋友,一起学习交流。
更多推荐
[YOLOv7/YOLOv5系列算法改进NO.4]添加ECA通道注意力机制
发布评论