HLJT

Hello, what I am wondering now is, in the pytorch extension of tcnn, can the encoding method based on hash_grid directly encode three-dimensional points in space?

I have a question and would like your reply, why your numstep is 100 instead of 1000, but your generated result is still good

Voxel features are all zero

3

voxel_features, voxel_coords = self.voxelization(features, coords) right now I am using CUDA 11.3 and Pytorch 1.12 and I have the exact issue, without giving any error, the code runs and produces...