Hi, Thanks for the amazing work and concise explanation in the paper. But can I use other sparse Conv libraries like ME, or torch sparse or is there any reason for using spconv. And is spconv tensorrt compatible?
We follow the popular setting in 3D detection (like SECOND, PointPillar) to use the spconv as the basic block; Other sparse convs may work too, while we do not have a try.
Hi, Thanks for the amazing work and concise explanation in the paper. But can I use other sparse Conv libraries like ME, or torch sparse or is there any reason for using spconv. And is spconv tensorrt compatible?