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

A conceptual question about choosing weight. #152

Open
4 tasks done
optimisticabouthumanity opened this issue Sep 3, 2024 · 0 comments
Open
4 tasks done

A conceptual question about choosing weight. #152

optimisticabouthumanity opened this issue Sep 3, 2024 · 0 comments
Labels
question Further information is requested

Comments

@optimisticabouthumanity
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 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

Is it okay to take weight from augmentation epochs?
Say, during training my model performs best during augmentation epochs.
But when MOSAIC is off, and trained without augmentations, the score does not fall rather keeps decreasing.

To deploy in real life, should I choose the weights from MOSAIC augmentation epochs even though it is the best?

Additional

No response

@optimisticabouthumanity optimisticabouthumanity added the question Further information is requested label Sep 3, 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