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

关于训练depth的步骤 #45

Open
YooWang opened this issue Jan 10, 2025 · 2 comments
Open

关于训练depth的步骤 #45

YooWang opened this issue Jan 10, 2025 · 2 comments

Comments

@YooWang
Copy link

YooWang commented Jan 10, 2025

请问,在使用re10k dataset训练整个模型结束后,再使用ScanNet, DeMoN, TartanAir, 和 VKITTI2这四个数据集微调,是这四个数据集全部都使用吗? 请问怎么同时使用这四个数据集微调才能得到论文中的性能呢? 论文中使用的是TartanAir数据比较的depth性能,这部分eval怎么实现的呢?感谢

@haofeixu
Copy link
Member

Hi 你好,我们release的 depth model是在这四个混合数据集上训练的。论文中的对比实验Table 3是在 TartanAir 和 VKITTI2上进行的。如果需要evaluation的code,我后面可以整理下开源到unimatch repo: https://github.com/autonomousvision/unimatch

@YooWang
Copy link
Author

YooWang commented Jan 17, 2025

理解了,非常感谢解答。 期待您开源evaluation code,再次非常感谢。

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

2 participants