-
Notifications
You must be signed in to change notification settings - Fork 6
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
3d高斯的tune.py运行速度稍微有些慢 #16
Comments
In tune.py, we need to render depth maps and calculate other losses. We cannot help you if you do not specify the adopted data and commands. |
I suggest trying Trim2DGS instead. Trim2DGS inherently handles |
Feel free to reopen this issue if you would like to offer more details. |
我没看到论文关于速度的评价。以你们默认参数的情况下,原版高斯和你们修改的高斯,速度差距多少(30K的情况下)。原版2D和你们修改的2D高斯,速度差距是多少(30K的情况下)。 |
这个文章并不是为了加速,所以并没有专门讨论速度。你说的速度应该是指训练速度? 渲染速度是不变的。 训练速度3D情况下因为多一次深度图渲染,所以会慢2倍多。为了方便开发,我们没对这个做优化,你想加速的话,可以把rgb和depth的渲染写到一个cuda kernel里,这样就快很多了。 2D情况下相比2DGS基本不变,因为没有额外的渲染操作。 |
好的,我知道了,谢谢您的回答。 |
另外你可以把你的具体训练参数发一下,我们看看有没有啥问题。 @chenqi13814529300 |
训练参数就默认参数,30K,就self.lambda_dist = 0.0 ,原始2D高斯我也是这么干的。而且你们的2D高斯跑出来的速度比较慢,原始的论文的2D是27分钟,在里面的工程中你们需要50多分钟(2d的train.py和tune.py都如此) |
速度比2DGS慢是因为他们进行了优化,可见 hbb1/diff-surfel-rasterization#7
|
好的,谢谢您的回复,我的问题已经解决 |
train.py比tune.py运行速度快好几倍?为什么?
The text was updated successfully, but these errors were encountered: