We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
我跑了一下,在 这个配置下,比那个原始的bevFusion慢一倍以上,怎么解决,bev_pool_v2感觉就是节省内存,但是花费的时间直接变长
The text was updated successfully, but these errors were encountered:
@rubbish001 ……这个bevpoolv2加速已经被很多人验证过了,旷视基于这个motivation,也推出了voxelpoolv2,原理上可行性应该是没问题的,我提供的实现也应该是ok的,可以好好查下什么原因导致实现不符合预期的,对个人定制化的内容(修改部分)要好好斟酌
Sorry, something went wrong.
我看FB-BEV也是用你的套路,但是他跑50次迭代要4分钟,用的3090,我这里跑第二阶段用的4090,锁住lss的梯度,具有跑50次迭代要1分50秒,以前都是40几秒.不过确实节省显存,点数比以前的那个配置提升了1个点左右。
哦哦,谢谢博主哈,我的配置有问题,downsampe =8,速度正常,效果还可以,看看我的效果 https://github.com/rubbish001/Co-Fix3d
老板,有没有显卡刷一波多帧融合的,合作搞一篇冲CVPR25
No branches or pull requests
我跑了一下,在
这个配置下,比那个原始的bevFusion慢一倍以上,怎么解决,bev_pool_v2感觉就是节省内存,但是花费的时间直接变长
The text was updated successfully, but these errors were encountered: