- 19 Jan, 2021 1 commit
-
-
Starrah authored
caused by `features` in pointnet2_backbone.py:78, which is possible to be a non-contiguous tensor, being directly passed into SA_modules without calling .contiguous()
-
- 30 Jul, 2020 1 commit
-
-
Shaoshuai Shi authored
-
- 23 Jul, 2020 2 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
- 22 Jul, 2020 1 commit
-
-
Shaoshuai Shi authored
-
- 21 Jul, 2020 1 commit
-
-
Shaoshuai Shi authored
-
- 13 Jul, 2020 2 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
- 06 Jul, 2020 3 commits
-
-
Shaoshuai Shi authored
-
Gus-Guo authored
support more flexible setting of conv head; slice inputs when batch size is too large in PFNLayer to avoid bugs (#124) * support more flexible setting * slice inputs of nn.Linear when batch size is too large
-
Shaoshuai Shi authored
-
- 04 Jul, 2020 1 commit
-
-
Gus-Guo authored
support more flexible setting of conv head; slice inputs when batch size is too large in PFNLayer to avoid bugs (#124) * support more flexible setting * slice inputs of nn.Linear when batch size is too large
-
- 23 Jun, 2020 2 commits
-
-
Gus-Guo authored
-
Shaoshuai Shi authored
all model codes refactoring for training/testing, support multiple 3D detectors (SECOND, PartA2-Net (official release), PV-RCNN (official release))
-
