Yuchen Li
Yuchen Li
Same to you~
Hi! I also have this problem. I add the code like above, but the error was the same. How can I schedule it?
Same Problems too, I wanna train on more specificial dataset
RTX 8000 * 4 GPUS for 20 hours
please check paconv
**mIOU per categories then average** versus **overall mIOU **
I achieve mIOU 68.5 in the best model, 66.54 in the last model, train on 4 RTX 8000 GPU for two days
I achieve 69.8 for the best miou
The original work may use some tricks to improve the performance. However, in fact, this Github repo may be the best implemented currently for point transformer, they give the result...
Not yet. Wait for the point cloud official code ba±