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.

Sign up for GitHub

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

Jump to bottom

最后的loss #4

Open

yanx57 opened this issue Oct 8, 2024 · 1 comment

yanx57 commented Oct 8, 2024 •

edited

Loading

您好，这篇工作很棒，我想请问一下你们训练到最优情况loss大概是多少吗？

Contributor

Hlings commented Oct 10, 2024

Hi, 感谢关注！训练到饱和的时候，(point cloud + image) <-> text的loss大概在3.4-3.8, image <-> text的loss在3.6-3.8，point -> image在0.42, point -> text在3.4-3.5。

也可以参考我的训练log，wandb网址：https://wandb.ai/yipeng123/CLIP3D_fundamental/reports/Partial-ablation-studies-of-the-MixCon3D--Vmlldzo5Njc1MTIy?accessToken=e27ociasdnvzdbrckuvug493qycmylzrnoyge1lnrijpy5g36iumm0kfvllzk5xy

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment