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

How to train a EViT-LVViT-S #13

Open
Fanghaipeng opened this issue Nov 3, 2022 · 2 comments
Open

How to train a EViT-LVViT-S #13

Fanghaipeng opened this issue Nov 3, 2022 · 2 comments

Comments

@Fanghaipeng
Copy link

Fanghaipeng commented Nov 3, 2022

我想训练一下EViT-LVViT-S,请问具体怎么实现?
1.关于token蒸馏,只蒸馏最后留下的token,还是蒸馏全部的token呢?
2.关于fuse token,需要蒸馏吗?

@youweiliang
Copy link
Owner

你好,对于EViT-LVViT-S

  1. 只需蒸馏最后留下的token
  2. fuse token不需要蒸馏

我这周会上传EViT-LVViT的代码。谢谢!

@andyoung009
Copy link

你好,对您的工作非常感兴趣。
我想请教下,关于EViT-LVViT-S的训练与微调:
1、训练与微调时图片像素不一样,那么patches数量也不一样,那预训练模型如何用高像素图片微调呢?是采用了token fusion的策略吗?
2、看有其他文章中也提到了低像素图像训练,高像素图像微调,这种处理方式一般采用什么方法去弥补patches数量不一致的gap呢?
谢谢!

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

3 participants