GitLab

* fix ci of dataset and visualizer by regenerate pkl

* decrease channels in ut for reducing cuda memory

* still use sample_id in the kitti submitted files

* minor changes

* use waymo-open-dataset-tf-2-6-0

* use waymo-open-dataset-tf-2-5-0 to be compabible with python3.6

* use waymo-open-dataset-tf-2-4-0 to be compabible with python3.6

* no dependency about waymo-open-dataset

* Revert "no dependency about waymo-open-dataset"

This reverts commit 581d4eefe26851a295b3190bcfa73d6fb2ba54aa.

* not install waymo-open-dataset for ci

* max python version is 3.8 because of trimesh

* Revert "max python version is 2.8 because of trimesh"

This reverts commit 6d8a1851b22a2059e7de75b576c2b7f633ad7cfa.

* fix networkx in ci

* update docstring of data_preprocessor

* modify version of typingextensions

* argument show, score_thr added to single_gpu_test

* Implemented label color visualization for show_result function

* Added show, score_thr argument for base 3 model(mmdetection3d)

* Fixed typo(color < 1) for show_result function

* Applied pre-commit run --all-files

* Revised documentation of show_result and revised variable name

* Updated documentation and set default value of score_thr to None

* Support nuscenes mono3d json info generation

* Support nuscenes mono3d dataset class

* Support attribute and bbox2d prediction in bbox3dnms and bbox3d2result

* Rename dataset class and add comments to 'attrs'

* Support mono3d related pipelines

* Fix unittest for loading 3D annotations

* Add unit test for nuscenes mono3d dataset

* Rename the sample result file

* Upload sample data for mono3d unit test

* Upload sample data for mono3d unit test

* Upload sample image for unit test

* Delete tests/data/nuscenes/samples/LIDAR_TOP/CAM_BACK_LEFT directory

* Add files via upload

* Remove unnecessary 'f'

* Remove unnecessary \ in arguments

* Remove check for pycocotools version because it has been done in the cocodataset

* Remove unnecessary comma, add TODO and change init of attrs in format_results

* Merge RandomFlip3D and RandomFlipMono3D

* Add pytest to check whether cuda is available in the unit test

* Add visualization TODO

* Remove useless init in loading mono3d images

* Add bottom2gravity and balance_class option.

* Add valid_flag.

* Add use_valid_flag.

* Change balance_class option.

* Add wrapper, remove gravity and balance_class option.

* Change flag, change load_infos to repeat_indices.

* Remove pdb, change docstring.

* Change name, remove unnecessary args.

* Remove _concat_dataset.

* Change name of ClassSampledDataset.

* Change docstring.

* Add get_cat_ids in nus_dataset, add unittest for wrapper.

* Change to len(self.dataset)

* Update nus data.

* Add unittest.

* Change to 'defaults to'.

* Add replace=False, remove T op, add num_sweeps=10 unittest.

* Change lyft_infos.pkl.

* Add nus unittest.

* Add nus unittest.

* Change nus_info.pkl.

* Add test_mode.