YOLOV7改进--增加小目标检测层
YOLOV7改进--增加小目标检测层
- 说明
- 代码
- 原始p5配置
- 添加小目标检测层
说明
yolov7来啦!!!因为项目需要,尝试跑了下yolov7,感觉还不错。
由于现在使用的数据集大部分都是“小目标”,并且之前有在yolov5上增加小目标检测层的经验,所以尝试了下在yolov7上添加小目标检测层,废话不多说,直接看代码吧!
代码
原始p5配置
# parameters
nc: 80 # 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]# 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, 51], 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[75, 1, RepConv, [256, 3, 1]],[88, 1, RepConv, [512, 3, 1]],[101, 1, RepConv, [1024, 3, 1]],[[102,103,104], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)]
添加小目标检测层
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple# anchors
anchors:# 博主数据集下的anchor先验,由autoanchor生成。 - [12,15, 30,15, 15,30]- [56,19, 28,43, 93,30]- [46,95, 167,48, 110,155]- [383,136, 286,354, 609,255]# 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]# 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, Conv, [64, 1, 1]],[-1, 1, nn.Upsample, [None, 2, 'nearest']],[11, 1, Conv, [64, 1, 1]], # route backbone P2[[-1, -2], 1, Concat, [1]],[-1, 1, Conv, [64, 1, 1]],[-2, 1, Conv, [64, 1, 1]],[-1, 1, Conv, [32, 3, 1]],[-1, 1, Conv, [32, 3, 1]],[-1, 1, Conv, [32, 3, 1]],[-1, 1, Conv, [32, 3, 1]],[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],[-1, 1, Conv, [64, 1, 1]], # 87# ------------------------------------------------# [-1, 1, MP, []],[-1, 1, Conv, [64, 1, 1]],[-3, 1, Conv, [64, 1, 1]],[-1, 1, Conv, [64, 3, 2]],[[-1, -3, 75], 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]], # 100# ------------------------------------------------# [-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]], # 113[-1, 1, MP, []],[-1, 1, Conv, [256, 1, 1]],[-3, 1, Conv, [256, 1, 1]],[-1, 1, Conv, [256, 3, 2]],[[-1, -3, 51], 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]], # 126[87, 1, RepConv, [128, 3, 1]],[100, 1, RepConv, [256, 3, 1]],[113, 1, RepConv, [512, 3, 1]],[126, 1, RepConv, [1024, 3, 1]],[[127,128,129,130], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)]
YOLOV7改进--增加小目标检测层相关推荐
- 目标检测算法——YOLOv7改进|增加小目标检测层
>>>深度学习Tricks,第一时间送达<<< 小目标检测一直以来是计算机CV领域的难点之一,那么,刚出炉的YOLOv7该如何增加小目标检测层呢? 目录 1.YOL ...
- 目标检测算法——YOLOv5改进|增加小目标检测层
关注"PandaCVer"公众号 >>>深度学习Tricks,第一时间送达<<< 小目标检测一直以来是CV领域的难点之一,那么,YOLOv5该如 ...
- YOLOv5增加小目标检测层
采用增加小目标检测层的方式来使YOLOv5能够检测小目标,只需要修改models下的yaml文件中的内容即可. 主要改变如下: 原yaml: # parameters nc: 80 # number ...
- YOLOv8/YOLOv7/YOLOv5系列算法改进【NO.6】增加小目标检测层,提高对小目标的检测效果
前 言:作为当前先进的深度学习目标检测算法YOLO,已经集合了大量的trick,但是在处理一些复杂检测问题的时候,还是容易出现错漏检的问题.此后的系列文章,将重点对YOLOv8.YOLOv7以及YOL ...
- YOLOv7 tiny 新增小目标检测层
YOLOv7 tiny 新增小目标检测层 YOLOv7 tiny 新增小目标检测层 修改yolov7-tiny.yaml文件 YOLOv7 tiny 结构图 调用 models/yolo.py验证 Y ...
- [YOLOv7/YOLOv5系列算法改进NO.5]改进特征融合网络PANET为BIFPN(更新添加小目标检测层yaml)
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 ...
- yolov5增加一层小目标检测层
1.原始YOLOv5模型 # YOLOv5 head head:[[-1, 1, Conv, [512, 1, 1]],[-1, 1, nn.Upsample, [None, 2, 'nearest' ...
- TensorRT+yolov5:yolov5添加小目标检测层2--TensorRT部署
前面我们在yolov5添加了小目标检测层,进行了训练,但是训练的次数也不是很多,接下来我们使用tensorrt进行四个检测头的yolov5部署.具体如何添加小目标检测层可以查看我上一篇文章. Tens ...
- 暴力改进SSD | 小目标检测的福音
作者 | 小书童 编辑 | 集智书童 点击下方卡片,关注"自动驾驶之心"公众号 ADAS巨卷干货,即可获取 点击进入→自动驾驶之心技术交流群 小目标检测是一个具有挑战性的问题.在 ...
最新文章
- python+selenium百度贴吧自动签到
- 图解|2018年度中国科学十大进展
- python 3.9 新特性 简介
- 原型模式coding-克隆破坏单例
- 【UOJ575】光伏元件【网络流建图】【上下界网络流】【费用流】
- eclipse中在类saolei.Test 中找不到main方法
- 141. 环形链表 golang
- 【iOS开发】企业版证书($299)In-House方式发布指南
- 二级c语言需要知道的知识点,2020年全国计算机二级C语言复习知识点:C语言基本知识(...
- 【译】区块链是如何工作的——用JavaScript演示
- Dom4j下载及使用Dom4j读写XML简介
- 软件工程类图_软件工程系列-UML3
- 【Android学习笔记】ONTOUCHEVENT, ONCLICK及ONLONGCLICK的调用机制
- Apache Flink Meetup · 北京站,1.13 新版本 x 互娱实践分享的开发者盛筵!
- 微信,QQ抢红包软件原理解析
- R:导入其他样式数据的方法
- 一次Ajax报错:“存储空间不足,无法完成此操作”的解决经验
- L3-015 球队“食物链” (30 分)
- python爬虫 403 Forbidden 解决方法
- docker运行centos镜像 安装python3.9环境
热门文章
- 软考下午科目——第二章——数据库设计
- webrtc服务器架构Mesh/MCU/SFU
- Windows远程桌面(mstsc)笔记:Windows 7远程桌面连接Windows Server 2019报错:“您的凭证不工作“
- 数云原生·场景融合|神州数码第四届数字中国技术年会正式开幕
- ACL配置实验报告(XDU物联网安全)
- WordPress网站更换老鹰主机详细操作
- layui+腾讯地图坐标点选取插件,支持地址关键字模糊/联想搜索、当前城市定位、地址地图标点联动
- 动态规划-俄罗斯套娃信封问题
- c# wpf 控件取消Tab选中
- 《九州仙剑传》11.26正式上线链游玩家|唯美国风、闯荡仙界