JOP-Lee
JOP-Lee
@piong2333 请问你这个怎么跑起来的，pytorch版本是多少呀，我这总提示CUDA error
> > @piong2333 请问你这个怎么跑起来的，pytorch版本是多少呀，我这总提示CUDA error > > 你有几个gpu呀，我电脑只有一个gpu，改了这几个好像j就跑起来了   @piong2333 4块，改了还是这个错。我跑的是cityscape那个视频序列的，不知道是不是这个模型预测出来的结果，不能当作GT训练
I think your training data is too small to be divided into test sets
Maybe it's the lack of a monitor, you need to set it to headless mode
Set the viewport, for example python viewer.py --config downloads/kitti6.yaml --viewport 1800x500
Thanks for pointing out the error, this part of the code is using NPBG. In our work, point clouds have normals, so it doesn't matter
If you want to set it to headless mode(without X server enabled), see the MyRender in the src folder. That is, run python train.py in the src folder
Please refer to the documentation for details. https://zenodo.org/record/7395608#.Y_3DDXZByUl
Maybe it's the lack of a monitor, you need to set it to headless mode