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

Backone for Segmentation task #14

Open
liuxy1103 opened this issue May 31, 2023 · 1 comment
Open

Backone for Segmentation task #14

liuxy1103 opened this issue May 31, 2023 · 1 comment

Comments

@liuxy1103
Copy link

I came across your GitHub repository where you have shared a PyTorch implementation of a backbone network for a classification task. I'm interested in using this backbone for a segmentation task, but I'm not sure how to modify it for this purpose.

Could you please provide some guidance or suggestions on how to modify the backbone network for a segmentation task? Specifically, I would like to know if there are any changes that need to be made to the architecture, loss function, or training procedure to adapt the network for segmentation.

Thank you for your help.

@HantingChen
Copy link
Collaborator

Hello,

Thank you for your interest in our work and for reaching out with your question.

We will release the code for downstream tasks (including detection and segmentation) in several days. When that becomes available, it should serve as a helpful reference for you in adapting the backbone network for a segmentation task.

The updated implementation will include any necessary modifications to the architecture, loss function, and training procedure to suit the segmentation task. We recommend that you check back on our repository for these updates.

We appreciate your patience and hope that our upcoming code release will be helpful for your project.

Thank you again for your interest in our work.

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

No branches or pull requests

2 participants