-
Notifications
You must be signed in to change notification settings - Fork 765
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
Getting negative loss while fine-tuning Segformer on custom dataset. #169
Comments
👋 Hello @mohdsaqibxa, thank you for leaving an issue on Roboflow Notebooks. 🐞 Bug reportsIf you are filing a bug report, please be as detailed as possible. This will help us more easily diagnose and resolve the problem you are facing. To learn more about contributing, check out our Contributing Guidelines. If you require support with custom code that is not part of Roboflow Notebooks, please reach out on the Roboflow Forum or on the GitHub Discussions page associated with this repository. 💬 Get in touchDo you have more questions about Roboflow that we haven't responded to yet? Feel free to ask them on the Roboflow Discuss forum. Our developer advocates and community team actively respond to questions there. To ask questions about Notebooks, head over to the GitHub Discussions section of this repository. |
Can anyone help me on this one please? |
Hi, @mohdsaqibxa 👋🏻! I just checked our notebook example, and it looks like it works. Loss is being minimized. We will need more information to debug. What dataset are you using? |
Hello @mohdsaqibxa Were you able to train with your custom dataset? |
Search before asking
Notebook name
https://github.com/roboflow/notebooks/blob/25204ae5e0c183f88b3e6d4c022ef86941fda14f/notebooks/train-segformer-segmentation-on-custom-data.ipynb
Bug
While trying to fine tune Segformer on a custom dataset, I am getting negative loss. I am trying to train Segformer for one class object.
Please let me know what's the solution of this. Am I doing some wrong here?
Environment
Minimal Reproducible Example
No response
Additional
No response
Are you willing to submit a PR?
The text was updated successfully, but these errors were encountered: