GitLab

* feat: support torch>=1.11

Fix #900.
Support PyTorch version >= 1.11. Referring to https://github.com/pytorch/pytorch/pull/66765 and https://github.com/pytorch/pytorch/wiki/TH-to-ATen-porting-guide.

* fix: Remove preproc torch version check macros

* To make different spconv version compatible for focalsconv

* Update README.md

Merge to support Focals Conv (CVPR 2022 paper).

refactor database_sampler.py to support extending to other multimodal datasets (in addition to kitti)

* Reflect the changes of the default behavior of grid_sample and affine_grid. If PyTorch > 1.3.0 align_corners will be set to False by default. This is undesired behavior.

* Support grid_sample and affine_grid for PyTorch<1.3 as well.
Co-authored-by: Dusan Malic <dusan.malic@icg.tugraz.at>

Re-organize fix random seed code; Make saved checkpoint compatible among different torch versions (#986)

* fix TypeError in ROI subsampling function

* add comment

Updaet to 1000 temporarily to process old issues.

* bugfixed: stuck when training with dist_train.sh, support tcp_port

* bugfixed: solve the issue of blocking with dist_train.sh, automatically search tcp ports

add `operations-per-run: 300` to increase the limit of operations to process old issues.