-
Notifications
You must be signed in to change notification settings - Fork 67
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
Comments
我们在ETH3D和Middlebury的预训练模型是按照unimatch的方法微调的,详情可见那篇论文https://arxiv.org/pdf/2211.05783.pdf2023-10-24 11:23:00>"Xiaguang Y" 写道:
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?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>
|
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? |
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 |
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? |
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
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?
The text was updated successfully, but these errors were encountered: