- 21 May, 2020 1 commit
-
-
Yan Yan authored
-
- 20 May, 2020 7 commits
- 15 May, 2020 1 commit
-
-
xmyqsh authored
The early break may miss some points in voxel_num < max_voxels. Use continue instead of break will be OK.
-
- 08 May, 2020 1 commit
-
-
Mohammad Shahedul Islam authored
-
- 02 May, 2020 2 commits
- 29 Apr, 2020 1 commit
-
-
benzlxs authored
-
- 26 Apr, 2020 4 commits
- 25 Apr, 2020 1 commit
-
-
benzlxs authored
-
- 23 Apr, 2020 1 commit
-
-
traveller59 authored
-
- 22 Apr, 2020 1 commit
-
-
tusimple authored
1. use dispatch instead of template 2. set use_hash default to False
-
- 01 Apr, 2020 1 commit
-
-
Yan Yan authored
-
- 21 Feb, 2020 1 commit
-
-
traveller59 authored
-
- 31 Jan, 2020 1 commit
-
-
dev-fennek authored
[for torch 1.4] torch::jit::RegisterOperators --> torch::RegisterOperators ref) https://github.com/pytorch/pytorch/commit/243298668caca7ee7de454ebc4d99c487ec9b272
-
- 26 May, 2019 2 commits
-
-
traveller59 authored
-
traveller59 authored
-
- 24 May, 2019 3 commits
-
-
traveller59 authored
-
traveller59 authored
1. workaround for gcc 5.5 avx512 problem 2. workaround for cuda 9 invalid device function problem
-
traveller59 authored
1. add cuda hash support for cuda indice generation. 2. use hash table instead of dense table in CPU code. 3. add CPU-only build support.
-
- 23 May, 2019 1 commit
-
-
traveller59 authored
-
- 22 May, 2019 1 commit
-
-
traveller59 authored
-
- 07 May, 2019 2 commits
-
-
traveller59 authored
-
traveller59 authored
-
- 04 May, 2019 1 commit
-
-
traveller59 authored
-
- 07 Apr, 2019 2 commits
-
-
traveller59 authored
-
traveller59 authored
-
- 05 Apr, 2019 1 commit
-
-
traveller59 authored
-
- 01 Apr, 2019 1 commit
-
-
traveller59 authored
-
- 22 Mar, 2019 3 commits
-
-
traveller59 authored
-
traveller59 authored
-
traveller59 authored
-