- 30 Nov, 2021 1 commit
-
-
Shaoshuai Shi authored
-
- 28 Nov, 2021 1 commit
-
-
Shaoshuai Shi authored
-
- 26 Nov, 2021 2 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
- 25 Nov, 2021 2 commits
- 24 Nov, 2021 6 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
support FILTER_EMPTY_BOXES_FOR_TRAIN and DISABLE_NLZ_FLAG_ON_POINTS for WOD by default, eval with sample_interval=1
-
- 23 Nov, 2021 9 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
update create_groundtruth_database of WOD to generate global npy file for sharedmemory based GT_database
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
Improve WOD performance with two LiDAR returns, speed up WOD data pre-processing with multiprocesssing.Pool
-
Shaoshuai Shi authored
Add support for spconv 2.0
-
Shaoshuai Shi authored
bugfixed: weights transformation between spconv 1.x and spconv 2.x, should consider both native/implicit spconv 2.x
-
Shaoshuai Shi authored
-
- 16 Nov, 2021 1 commit
-
-
acivgin1 authored
-
- 05 Nov, 2021 2 commits
- 04 Nov, 2021 4 commits
- 03 Nov, 2021 3 commits
-
-
acivgin1 authored
- as per the spconv documentation, the order of channels in weights is now changed - we need to get all the affected weights, using the util function in spconv_utils - we need to check the version with the version checker in __init__.py - we need to transpose last two dimensions of existing weights, from older models - to avoid duplication a single _load_state_dict method is added
-
acivgin1 authored
-
acivgin1 authored
-
- 14 Sep, 2021 2 commits
-
-
jihan.yang authored
-
jihan.yang authored
-
- 11 Sep, 2021 2 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
- 09 Sep, 2021 5 commits
-
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-
Shaoshuai Shi authored
-