search

torch-points3d / torch-points-kernels

Pytorch kernels for spatial operations on point clouds
MIT License
96 stars 25 forks source link

Problem about the chamfer distance #81

Closed LJL36 closed 3 years ago

LJL36 commented 3 years ago

I have found that the return value of the ChamferFunction is not consistent with the source code of the cuda version I have tested the code, and show it in the following

Python 3.7.4 (default, Aug 13 2019, 20:35:49) [GCC 7.3.0] :: Anaconda, Inc. on linux Type "help", "copyright", "credits" or "license" for more information.

import torch a = torch.randn((100,3)).cuda() b = torch.randn((10,3)).cuda() from torch_points_kernels.chamfer_dist import ChamferFunction d1, d2 = ChamferFunction.apply(a,b) d1.shape torch.Size([100, 3]) d2.shape torch.Size([100, 3])

Python version 3.7 torch-points-kernel verison 3.6.6

I want to know why this happens Hope to get a reply, thank you