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.

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

你们是怎么训练的 #15

Open
rubbish001 opened this issue Nov 4, 2023 · 3 comments
Open

你们是怎么训练的 #15

rubbish001 opened this issue Nov 4, 2023 · 3 comments

Comments

@rubbish001
Copy link

rubbish001 commented Nov 4, 2023 •
edited
Loading

我设计了一套模型，15轮数据增加+5轮数据退化，测集上精度是0.696，nds是0.731，由于我没有卡，在4张4090上训练一次得到的结果，follow 那个北京的bevfuison，退化了，求指点一下，还有12天cvpr，训练一次要5天，现在只能在做一次实验了
@hht1996ok
Copy link
Owner

@rubbish001 抱歉，可以略微详细的介绍一下吗，不太理解。

@rubbish001
Copy link
Author

还有一个问题，v299跑出来的精度是多少，我是用v299跑出来的

@shangxi123lou
Copy link

我设计了一套模型，15轮数据增加+5轮数据退化，测集上精度是0.696，nds是0.731，由于我没有卡，在4张4090上训练一次得到的结果，follow 那个北京的bevfuison，退化了，求指点一下，还有12天cvpr，训练一次要5天，现在只能在做一次实验了

请问你是怎么训练的，为啥我四张4090照样显存溢出？？求指点

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@rubbish001 @hht1996ok @shangxi123lou