tinyvision / DAMO-YOLO

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

官方提供的人头检测模型结果偏差比较大

FourTest opened this issue · comments

Before Asking

  • I have read the README carefully. 我已经仔细阅读了README上的操作指引。

  • I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集,我已经仔细阅读了训练自定义数据的教程,以及按照正确的目录结构存放数据集。

  • I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码,重新运行之后,问题仍不能解决。

Search before asking

  • I have searched the DAMO-YOLO issues and found no similar questions.

Question

使用官方提供的人头检测模型,头部轻微动作出来的结果偏差比较大.这样的结果就:应用于视频的时候,绘制人头矩形框,会发现矩形框抖动非常厉害.yolo5就非常稳定,不存在抖动的情况.这是模型下载地址

https://github.com/tinyvision/DAMO-YOLO/blob/master/README_cn.md#工业应用模型

Additional

No response