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

请教一些问题 #2

Open
lulu-Lucas opened this issue Nov 22, 2024 · 2 comments
Open

请教一些问题 #2

lulu-Lucas opened this issue Nov 22, 2024 · 2 comments
Labels
question Further information is requested

Comments

@lulu-Lucas
Copy link

1.可以提供pretrain之后的模型文件吗,不知道为什么我训练速度越来越慢,在第四个epoch,竟然要训练10个小时。
2.为什么kl损失一直是0呢?
3.如果下游任务没有标注数据的话,比如我下游任务是lidar语义分割,但是我没有标注数据,我该怎么使用预训练模型进行lidar语义分割呢。
感谢作者奉献!

@Eaphan
Copy link
Owner

Eaphan commented Nov 22, 2024

  1. 涉及训练速度的要素太多,根据你提供的信息我无法帮你定位原因.
  2. 前几个epoch我们先用特征来更新vMF分布,几个epoch之后才加入regularization (KL) loss.
  3. 我们提供的是预训练权重,但是这个权重无法直接用于语义分割任务,也就是不具有zero-shot的能力. 你需要的功能可以看看Clip2scene 这个文章.

@Eaphan Eaphan added the question Further information is requested label Nov 22, 2024
@lulu-Lucas
Copy link
Author

感谢您的快速恢复。1.您这边可以直接提供nus数据集的预训练文件吗?3.好的,我会去研究一下的

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

2 participants