In the recent [nuScenes 3D detection challenge](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any) of the 5th AI Driving Olympics in NeurIPS 2020, we obtained the best PKL award and the second runner-up by multi-modality entry, and the best vision-only results.
In the recent [nuScenes 3D detection challenge](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any) of the 5th AI Driving Olympics in NeurIPS 2020, we obtained the best PKL award and the second runner-up by multi-modality entry, and the best vision-only results.
...
@@ -62,7 +62,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
...
@@ -62,7 +62,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
## Changelog
## Changelog
v0.13.0 was released in 1/5/2021.
v0.14.0 was released in 1/6/2021.
Please refer to [changelog.md](docs/changelog.md) for details and release history.
Please refer to [changelog.md](docs/changelog.md) for details and release history.
- Support points rotation even without bounding box in GlobalRotScaleTrans for point cloud segmentaiton (#540)
- Support visualization of detection results and dataset browse for nuScenes Mono-3D dataset (#542, #582)
- Support faster implementation of KNN (#586)
- Support RegNetX models on Lyft dataset (#589)
- Remove a useless parameter [label_weight] from segmentation datasets including [Custom3DSegDataset], [ScanNetSegDataset] and [S3DISSegDataset] (#607)
#### Bug Fixes
- Fix a corrupted lidar data file in Lyft dataset in [data_preparation](https://github.com/open-mmlab/mmdetection3d/tree/master/docs/data_preparation.md)(#546)
- Fix evaluation bugs in nuScenes and Lyft dataset (#549)
- Fix converting points between coordinates with specific transformation matrix in the [coord_3d_mode.py](https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/core/bbox/structures/coord_3d_mode.py)(#556)
- Support PointPillars models on Lyft dataset (#578)
- Fix the bug of demo with pre-trained VoteNet model on ScanNet (#600)
This document provides detailed descriptions of the BC-breaking changes in MMDetection3D.
This document provides detailed descriptions of the BC-breaking changes in MMDetection3D.
## MMDetection3D 0.15.0
## MMDetection3D 0.14.0
### Dataset class for 3D segmentation task
### Dataset class for 3D segmentation task
We remove a useless parameter `label_weight` from segmentation datasets including `Custom3DSegDataset`, `ScanNetSegDataset` and `S3DISSegDataset` since this weight is utilized in the loss function of model class. Please modify the code as well as the config files accordingly if you use or inherit from these codes.
We remove a useless parameter `label_weight` from segmentation datasets including `Custom3DSegDataset`, `ScanNetSegDataset` and `S3DISSegDataset` since this weight is utilized in the loss function of model class. Please modify the code as well as the config files accordingly if you use or inherit from these codes.
## MMDetection3D 0.14.0
### ScanNet data pre-processing
### ScanNet data pre-processing
We adopt new pre-processing and conversion steps of ScanNet dataset. In previous versions of MMDetection3D, ScanNet dataset was only used for 3D detection task, where we trained on the training set and tested on the validation set. In MMDetection3D 0.14.0, we further support 3D segmentation task on ScanNet, which includes online benchmarking on test set. Since the alignment matrix is not provided for test set data, we abandon the alignment of points in data generation steps to support both tasks. Besides, as 3D segmentation requires per-point prediction, we also remove the down-sampling step in data generation.
We adopt new pre-processing and conversion steps of ScanNet dataset. In previous versions of MMDetection3D, ScanNet dataset was only used for 3D detection task, where we trained on the training set and tested on the validation set. In MMDetection3D 0.14.0, we further support 3D segmentation task on ScanNet, which includes online benchmarking on test set. Since the alignment matrix is not provided for test set data, we abandon the alignment of points in data generation steps to support both tasks. Besides, as 3D segmentation requires per-point prediction, we also remove the down-sampling step in data generation.
MMDetection3D v0.13.0 is only compatible with MMDetection version `mmdet>=2.10.0, <=2.11.0`. The future versions will only support `mmdet>=2.12.0` since v0.14.0 (to be released in May).
MMDetection3D v0.14.0 is only compatible with MMDetection version `mmdet>=2.10.0, <=2.11.0`. The future versions will only support `mmdet>=2.12.0` since v0.15.0 (to be released in July).
