Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

distill的流程与配置 #1046

Open
4 tasks done
QiqLiang opened this issue May 17, 2024 · 2 comments
Open
4 tasks done

distill的流程与配置 #1046

QiqLiang opened this issue May 17, 2024 · 2 comments
Labels
question Further information is requested

Comments

@QiqLiang
Copy link

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 training your custom data carefully and organize my dataset correctly; (FYI: We recommand you to apply the config files of xx_finetune.py.) 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。(FYI: 我们推荐使用xx_finetune.py等配置文件训练自定义数据集。)

  • 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 YOLOv6 issues and found no similar questions.

Question

你好,我对于自蒸馏过程有以下一些问题:

  1. 我已经有一个在coco80c上预训练好的模型A,在训练过程中未开启use_dfl,假如我希望训练一个自己数据集上的模型,并利用自蒸馏提高检测性能,接下来的流程是这样吗: 以A为预训练模型,开启use_dfl和fuse_ab在自己数据集上训练一个教师模型B,再以B为教师模型,开启use_dfl和distill参数(关闭fuse_ab)训练学生模型C?
  2. 请问在训练C时config文件里的预训练模型应该设定为模型A还是模型B呢?
    谢谢!

Additional

No response

@QiqLiang QiqLiang added the question Further information is requested label May 17, 2024
@Chilicyy
Copy link
Collaborator

@QiqLiang 您好,问题1 描述的流程是对的;问题2 预训练模型设为模型A,教师模型设为模型B。

@QiqLiang
Copy link
Author

@QiqLiang 您好,问题1 描述的流程是对的;问题2 预训练模型设为模型A,教师模型设为模型B。

谢谢!我还有以下两个问题:

  1. 训练学生模型和教师模型的侧重点有什么不同呢?或者换句话说,建议训练时使用相同的数据集还是学生模型使用更针对性的数据集呢?
  2. 在实际使用yolov6n的时候存在比较多的背景误报为目标或者目标分类错误,除了可以从训练集入手或者增大模型外,有没有什么训练tricks可以尝试一下呢?
    非常感谢!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants