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

请问如何以半监督的方式训练monodistill #15

Open
aqr1961 opened this issue May 2, 2024 · 0 comments
Open

请问如何以半监督的方式训练monodistill #15

aqr1961 opened this issue May 2, 2024 · 0 comments

Comments

@aqr1961
Copy link

aqr1961 commented May 2, 2024

为了进一步提升检测精度,我正在考虑使用KITTI RAW数据集对monodistill进行半监督扩展。在此过程中,我遇到了一些技术问题,希望能得到您的指导与建议:

在半监督训练中,为了获取与RGB单目图像对应的密集深度图,我应该直接使用KITTI Depth Completion数据集中的gt图,还是应该从LIDAR点云补全获得?哪种方式更为合适?
关于伪标签的生成,我是否可以参考LPCG的模式?这样的方法是否可行,请问您有何高见?
非常感谢您的帮助和支持。

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

1 participant