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

Details of the training process #167

Open
li-wenquan opened this issue Dec 21, 2021 · 1 comment
Open

Details of the training process #167

li-wenquan opened this issue Dec 21, 2021 · 1 comment

Comments

@li-wenquan
Copy link

你好,关于训练细节,我请教几个问题:
1、训练中数据集的使用顺序依次为:VideoMatte240K、PhotoMatte13K、Distinctions-646,请问为什么要将PhotoMatte13K、Distinctions-646二者分离而不是合并在一起训练?分离的做法是出于什么样的考虑?
2、对于refine 模型的训练过程中,各个阶段(各个数据集上的训练)都是训练到收敛再进入下一个阶段?如果不是的话,那应该训练到什么样的程度才进入下一阶段?
3、在本文中似乎提到AIM和Distinctions-646数据集差异较大,但为什么没有像RVM(你的另一篇论文)那样,将两者结合训练?
谢谢。

@PeterL1n
Copy link
Owner

  1. PhotoMatte 的数据是通过绿屏抠像得到的,质量不如 Distinctions,所以后训练 Distinctions。
  2. 是。
  3. 都可以吧。

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