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

在SceneFlow上训练完,是否要在Middlebury和Eth3d数据集微调?微调多少代 #44

Open
yxg19991231 opened this issue Oct 24, 2023 · 5 comments

Comments

@yxg19991231
Copy link

我看论文中似乎并没有提到要在这两个数据集上微调,但是只在scene flow上训练达不到论文的效果,而且作者的预训练模型就有ETH3d和Middlebury的,所以我想应该要在这两个数据集上微调,具体微调多少代?

@gangweiX
Copy link
Owner

gangweiX commented Oct 24, 2023 via email

@yxg19991231
Copy link
Author

这篇论文中在ETH3d和Middlebury的微调是微调两次,且都是在混合Scene flow,Tartan Air ,Sintel Stereo ,CREStereo Dataset ,InStereo 2K 和ETH 3D等数据集上,需要这么麻烦吗?能只在ETH3d和Middlebury上进行微调吗?

@gangweiX
Copy link
Owner

如果你想在ETH3D和Middlebury的benchmarks上测试,就需要这么麻烦。因为ETH3D和Middlebury的训练集太少了,只简单微调可能效果不好

@yxg19991231
Copy link
Author

在middlebury全分辨率上微调的时候,最大视差有调整么?调到多少比较合适?

@gangweiX
Copy link
Owner

我们之前训练的没有,所以效果并不是很理想。我觉得你可以试一下,比如,384,576等等。另外我们的 3d cost volume以及3d cnn是很轻量的,增大最大视差应该没有带来很大的代价

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