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

In the classification loss, let the image ignore region not participate in the loss calculation, that is, not contribute to the classification loss #1063

Open
3 of 4 tasks
eorroot opened this issue Jul 18, 2024 · 0 comments
Labels
question Further information is requested

Comments

@eorroot
Copy link

eorroot commented Jul 18, 2024

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

I believe the code style of V6 is excellent for developers and represents a valuable open-source project. I am interested in starting a research project based on V6 for a specific task involving the treatment of image neglected regions. These neglected regions do not contribute when calculating the classification loss. I have already marked the ignored regions with mask tags, but I am encountering problems with the loss function. I would appreciate any assistance your team can provide to help me resolve this issue.

Additional

No response

@eorroot eorroot added the question Further information is requested label Jul 18, 2024
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

1 participant