Skip to content

Commit fb5a323

Browse files
sunjiahao1999sunjiahao1999
authored
Bump to v1.2.0 (#2630)
* fix mmdet max version * add readme * fix changelog * fix keep index bug * fix open3d version bug
1 parent 12e2b7c commit fb5a323

File tree

9 files changed

+60
-15
lines changed

9 files changed

+60
-15
lines changed

‎README.md

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -106,7 +106,13 @@ Like [MMDetection](https://github.com/open-mmlab/mmdetection) and [MMCV](https:/
106106

107107
**We have renamed the branch `1.1` to `main` and switched the default branch from `master` to `main`. We encourage users to migrate to the latest version, though it comes with some cost. Please refer to [Migration Guide](docs/en/migration.md) for more details.**
108108

109-
We have constructed a comprehensive LiDAR semantic segmentation benchmark on SemanticKITTI, including Cylinder3D, MinkUNet and SPVCNN methods. Noteworthy, the improved MinkUNetv2 can achieve 70.3 mIoU on the validation set of SemanticKITTI. We have also supported the training of BEVFusion and an occupancy prediction method, TPVFormer, in our `projects`. More new features about 3D perception are on the way. Please stay tuned!
109+
We have constructed a comprehensive LiDAR semantic segmentation benchmark on SemanticKITTI, including Cylinder3D, MinkUNet and SPVCNN methods. Noteworthy, the improved MinkUNetv2 can achieve 70.3 mIoU on the validation set of SemanticKITTI. We have also supported the training of BEVFusion and an occupancy prediction method, TPVFomrer, in our `projects`. More new features about 3D perception are on the way. Please stay tuned!
110+
111+
**v1.2.0** was released in 4/7/2023
112+
113+
- Support [New Config Type](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta) in `mmdet3d/config`
114+
- Support the inference of [DSVT](<(https://arxiv.org/abs/2301.06051)>) in `projects`
115+
- Support downloading datasets from [OpenDataLab](https://opendatalab.com/) using `mim`
110116

111117
**v1.1.1** was released in 30/5/2023:
112118

@@ -336,7 +342,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
336342
| PETR | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
337343
| TPVFormer | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
338344

339-
**Note:** All the about **300+ models, methods of 40+ papers** in 2D detection supported by [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/model_zoo.md) can be trained or used in this codebase.
345+
**Note:** All the about **500+ models, methods of 90+ papers** in 2D detection supported by [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/model_zoo.md) can be trained or used in this codebase.
340346

341347
## FAQ
342348

‎README_zh-CN.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -108,6 +108,12 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱，下一代
108108

109109
我们在 SemanticKITTI 上构建了一个全面的点云语义分割基准，包括 Cylinder3D 、MinkUNet 和 SPVCNN 方法。其中，改进后的 MinkUNetv2 在验证集上可以达到 70.3 mIoU。我们还在 `projects` 中支持了 BEVFusion 的训练和全新的 3D 占有网格预测网络 TPVFormer。更多关于 3D 感知的新功能正在进行中。请继续关注！
110110

111+
**v1.2.0** 版本已经在 2023.7.4 发布：
112+
113+
- 在 `mmdet3d/config`中支持 [新Config样式](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta)
114+
- 在 `projects` 中支持 [DSVT](<(https://arxiv.org/abs/2301.06051)>) 的推理
115+
- 支持通过 `mim` 从 [OpenDataLab](https://opendatalab.com/) 下载数据集
116+
111117
**v1.1.1** 版本已经在 2023.5.30 发布：
112118

113119
- 在 `projects` 中支持 [TPVFormer](https://arxiv.org/pdf/2302.07817.pdf)

‎docs/en/notes/changelog.md

Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,38 @@
11
# Changelog of v1.1
22

3+
### v1.2.0 (4/7/2023)
4+
5+
#### Highlights
6+
7+
- Support [New Config Type](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta) in `mmdet3d/config` (#2608)
8+
- Support the inference of [DSVT](<(https://arxiv.org/abs/2301.06051)>) in `projects` (#2606)
9+
- Support downloading datasets from [OpenDataLab](https://opendatalab.com/) using `mim` (#2593)
10+
11+
#### New Features
12+
13+
- Support [New Config Type](https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta) in `mmdet3d/config` (#2608)
14+
- Support the inference of [DSVT](<(https://arxiv.org/abs/2301.06051)>) in `projects` (#2606)
15+
- Support downloading datasets from [OpenDataLab](https://opendatalab.com/) using `mim` (#2593)
16+
17+
#### Improvements
18+
19+
- Enhanced visualization in interactive form (#2611)
20+
- Update README.md and Model Zoo (#2599, #2600)
21+
- Speed up S3DIS data preparation (#2585)
22+
23+
#### Bug Fixes
24+
25+
- Remove PointRCNN in benchmark training (#2610)
26+
- Fix wrong indoor detection visualization (#2625)
27+
- Fix MinkUNet download link (#2590)
28+
- Fix the formula in the `readthedocs` (#2580)
29+
30+
#### Contributors
31+
32+
A total of 5 developers contributed to this release.
33+
34+
@sunjiahao1999, @Xiangxu-0103, @JingweiZhang12, @col14m, @zhulf0804
35+
336
### v1.1.1 (30/5/2023)
437

538
#### Highlights

‎docs/en/notes/faq.md

Lines changed: 6 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -8,14 +8,12 @@ We list some potential troubles encountered by users and developers, along with
88

99
- The required versions of MMEngine, MMCV and MMDetection for different versions of MMDetection3D are as below. Please install the correct version of MMEngine, MMCV and MMDetection to avoid installation issues.
1010

11-
| MMDetection3D version | MMEngine version | MMCV version | MMDetection version |
12-
| --------------------- | :----------------------: | :---------------------: | :----------------------: |
13-
| dev-1.x | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
14-
| main | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
15-
| v1.1.1 | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
16-
| v1.1.0rc3 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc3, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
17-
| v1.1.0rc2 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc3, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
18-
| v1.1.0rc1 | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
11+
| MMDetection3D version | MMEngine version | MMCV version | MMDetection version |
12+
| --------------------- | :----------------------: | :---------------------: | :-------------------: |
13+
| dev-1.x | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.2.0 |
14+
| main | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.2.0 |
15+
| v1.2.0 | mmengine>=0.8.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.2.0 |
16+
| v1.1.1 | mmengine>=0.7.1, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0, \<3.1.0 |
1917

2018
**Note:** If you want to install mmdet3d-v1.0.0rcx, the compatible MMDetection, MMSegmentation and MMCV versions table can be found at [here](https://mmdetection3d.readthedocs.io/en/latest/faq.html#mmcv-mmdet-mmdet3d-installation). Please choose the correct version of MMCV, MMDetection and MMSegmentation to avoid installation issues.
2119

‎mmdet3d/__init__.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,12 +10,12 @@
1010
mmcv_maximum_version = '2.1.0'
1111
mmcv_version = digit_version(mmcv.__version__)
1212

13-
mmengine_minimum_version = '0.7.1'
13+
mmengine_minimum_version = '0.8.0'
1414
mmengine_maximum_version = '1.0.0'
1515
mmengine_version = digit_version(mmengine.__version__)
1616

1717
mmdet_minimum_version = '3.0.0'
18-
mmdet_maximum_version = '3.1.0'
18+
mmdet_maximum_version = '3.2.0'
1919
mmdet_version = digit_version(mmdet.__version__)
2020

2121
assert (mmcv_version >= digit_version(mmcv_minimum_version)

‎mmdet3d/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Copyright (c) Open-MMLab. All rights reserved.
22

3-
__version__ = '1.1.1'
3+
__version__ = '1.2.0'
44
short_version = __version__
55

66

‎mmdet3d/visualization/local_visualizer.py

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -964,6 +964,8 @@ def add_datasample(self,
964964
ignore_index = self.dataset_meta.get('ignore_index', None)
965965
if ignore_index is not None and 'gt_pts_seg' in data_sample and vis_task == 'lidar_seg': # noqa: E501
966966
keep_index = data_sample.gt_pts_seg.pts_semantic_mask != ignore_index # noqa: E501
967+
else:
968+
keep_index = None
967969

968970
gt_data_3d = None
969971
pred_data_3d = None

‎requirements/mminstall.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
mmcv>=2.0.0rc4,<2.1.0
2-
mmdet>=3.0.0,<3.1.0
2+
mmdet>=3.0.0,<3.2.0
33
mmengine>=0.7.1,<1.0.0

‎requirements/runtime.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ networkx>=2.5
33
numba # you should install numba==0.53.0 if your environment is cuda-9.0
44
numpy
55
nuscenes-devkit
6-
open3d
6+
open3d==0.16.0
77
plyfile
88
scikit-image
99
# by default we also use tensorboard to log results

0 commit comments

Comments
 (0)