Merge branch 'master' into v1.0.0.dev0

91925016 · Tai-Wang · 95c2db72 · dabe3ff4 · 91925016 · 91925016
Commit 91925016 authored Feb 16, 2022 by Tai-Wang
20 changed files
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -41,22 +41,22 @@ jobs:
        torch: [1.5.0+cu101, 1.6.0+cu101, 1.7.0+cu101, 1.8.0+cu101]
        include:
          - torch: 1.5.0+cu101
-            torch_version: torch1.5.0
+            torch_version: torch1.5
            torchvision: 0.6.0+cu101
            mmcv_link: "torch1.5.0"
            cuda_arch: "7.0"
          - torch: 1.6.0+cu101
-            torch_version: torch1.6.0
+            torch_version: torch1.6
            mmcv_link: "torch1.6.0"
            torchvision: 0.7.0+cu101
            cuda_arch: "7.0"
          - torch: 1.7.0+cu101
-            torch_version: torch1.7.0
+            torch_version: torch1.7
            mmcv_link: "torch1.7.0"
            torchvision: 0.8.1+cu101
            cuda_arch: "7.0"
          - torch: 1.8.0+cu101
-            torch_version: torch1.8.0
+            torch_version: torch1.8
            mmcv_link: "torch1.8.0"
            torchvision: 0.9.0+cu101
            cuda_arch: "7.0"

--- a/README.md
+++ b/README.md
 <div align="center">
  <img src="resources/mmdet3d-logo.png" width="600"/>
+  <div>&nbsp;</div>
+  <div align="center">
+    <b><font size="5">OpenMMLab website</font></b>
+    <sup>
+      <a href="https://openmmlab.com">
+        <i><font size="4">HOT</font></i>
+      </a>
+    </sup>
+    &nbsp;&nbsp;&nbsp;&nbsp;
+    <b><font size="5">OpenMMLab platform</font></b>
+    <sup>
+      <a href="https://platform.openmmlab.com">
+        <i><font size="4">TRY IT OUT</font></i>
+      </a>
+    </sup>
+  </div>
+  <div>&nbsp;</div>
 </div>
 [![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdetection3d.readthedocs.io/en/latest/)
@@ -8,7 +25,7 @@
 [![license](https://img.shields.io/github/license/open-mmlab/mmdetection3d.svg)](https://github.com/open-mmlab/mmdetection3d/blob/master/LICENSE)
-**News**: We released the codebase v0.17.3.
+**News**: We released the codebase v0.18.1.
 In addition, we have preliminarily supported several new models on the [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) branch, including [DGCNN](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/dgcnn/README.md), [SMOKE](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/smoke/README.md) and [PGD](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/pgd/README.md).
@@ -70,7 +87,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
 ## Changelog
-v0.17.3 was released in 1/12/2021.
+v0.18.1 was released in 1/2/2022.
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 For branch v1.0.0.dev0, please refer to [changelog_v1.0.md](https://github.com/Tai-Wang/mmdetection3d/blob/v1.0.0.dev0-changelog/docs/changelog_v1.0.md) for our latest features and more details.
@@ -104,7 +121,7 @@ Support methods
 - [x] [FCOS3D (ICCVW'2021)](configs/fcos3d/README.md)
 - [x] [PointNet++ (NeurIPS'2017)](configs/pointnet2/README.md)
 - [x] [Group-Free-3D (ICCV'2021)](configs/groupfree3d/README.md)
- [x] [ImVoxelNet (Arxiv'2021)](configs/imvoxelnet/README.md)
+- [x] [ImVoxelNet (WACV'2022)](configs/imvoxelnet/README.md)
 - [x] [PAConv (CVPR'2021)](configs/paconv/README.md)
 - [x] [DGCNN (TOG'2019)](configs/dgcnn/README.md)
 - [x] [SMOKE (CVPRW'2020)](configs/smoke/README.md)

--- a/README_zh-CN.md
+++ b/README_zh-CN.md
 <div align="center">
  <img src="resources/mmdet3d-logo.png" width="600"/>
+  <div>&nbsp;</div>
+  <div align="center">
+    <b><font size="5">OpenMMLab 官网</font></b>
+    <sup>
+      <a href="https://openmmlab.com">
+        <i><font size="4">HOT</font></i>
+      </a>
+    </sup>
+    &nbsp;&nbsp;&nbsp;&nbsp;
+    <b><font size="5">OpenMMLab 开放平台</font></b>
+    <sup>
+      <a href="https://platform.openmmlab.com">
+        <i><font size="4">TRY IT OUT</font></i>
+      </a>
+    </sup>
+  </div>
+  <div>&nbsp;</div>
 </div>
 [![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdetection3d.readthedocs.io/en/latest/)
@@ -8,7 +25,7 @@
 [![license](https://img.shields.io/github/license/open-mmlab/mmdetection3d.svg)](https://github.com/open-mmlab/mmdetection3d/blob/master/LICENSE)
-**新闻**: 我们发布了版本 v0.17.3.
+**新闻**: 我们发布了版本 v0.18.1.
 另外，我们在 [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) 分支初步支持了多个新模型，包括 [DGCNN](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/dgcnn/README.md), [SMOKE](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/smoke/README.md) 和 [PGD](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/pgd/README.md)。
@@ -70,7 +87,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 ## 更新日志
-最新的版本 v0.17.3 在 2021.12.01 发布。
+最新的版本 v0.18.1 在 2022.2.1 发布。
 如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/zh_cn/changelog.md)。
 对于分支 [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) ，请参考 [v1.0 更新日志](https://github.com/Tai-Wang/mmdetection3d/blob/v1.0.0.dev0-changelog/docs/changelog_v1.0.md) 来了解我们的最新功能和更多细节。
@@ -103,7 +120,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 - [x] [FCOS3D (ICCVW'2021)](configs/fcos3d/README.md)
 - [x] [PointNet++ (NeurIPS'2017)](configs/pointnet2/README.md)
 - [x] [Group-Free-3D (ICCV'2021)](configs/groupfree3d/README.md)
- [x] [ImVoxelNet (Arxiv'2021)](configs/imvoxelnet/README.md)
+- [x] [ImVoxelNet (WACV'2022)](configs/imvoxelnet/README.md)
 - [x] [PAConv (CVPR'2021)](configs/paconv/README.md)
 - [x] [DGCNN (TOG'2019)](configs/dgcnn/README.md)
 - [x] [SMOKE (CVPRW'2020)](configs/smoke/README.md)

--- a/configs/_base_/models/hv_pointpillars_secfpn_kitti.py
+++ b/configs/_base_/models/hv_pointpillars_secfpn_kitti.py
@@ -35,11 +35,11 @@ model = dict(
        feat_channels=384,
        use_direction_classifier=True,
        anchor_generator=dict(
-            type='Anchor3DRangeGenerator',
+            type='AlignedAnchor3DRangeGenerator',
            ranges=[
-                [0, -39.68, -0.6, 70.4, 39.68, -0.6],
+                [0, -39.68, -0.6, 69.12, 39.68, -0.6],
-                [0, -39.68, -0.6, 70.4, 39.68, -0.6],
+                [0, -39.68, -0.6, 69.12, 39.68, -0.6],
-                [0, -39.68, -1.78, 70.4, 39.68, -1.78],
+                [0, -39.68, -1.78, 69.12, 39.68, -1.78],
            ],
            sizes=[[0.8, 0.6, 1.73], [1.76, 0.6, 1.73], [3.9, 1.6, 1.56]],
            rotations=[0, 1.57],

--- a/docs/en/changelog.md
+++ b/docs/en/changelog.md
 ## Changelog
+### v0.18.1 (1/2/2022)
+#### Improvements
+- Support Flip3D augmentation in semantic segmentation task (#1182)
+- Update regnet metafile (#1184)
+- Add point cloud annotation tools introduction in FAQ (#1185)
+- Add missing explanations of `cam_intrinsic` in the nuScenes dataset doc (#1193)
+#### Bug Fixes
+- Deprecate the support for "python setup.py test" (#1164)
+- Fix the rotation matrix while rotation axis=0 (#1182)
+- Fix the bug in non-distributed multi-gpu training/testing (#1197)
+- Fix a potential bug when generating corners for empty bounding boxes (#1212)
+#### Contributors
+A total of 4 developers contributed to this release.
+@ZwwWayne, @ZCMax, @Tai-Wang, @wHao-Wu
+### v0.18.0 (1/1/2022)
+#### Highlights
+- Update the required minimum version of mmdet and mmseg
+#### Improvements
+- Use the official markdownlint hook and add codespell hook for pre-committing (#1088)
+- Improve CI operation (#1095, #1102, #1103)
+- Use shared menu content from OpenMMLab's theme and remove duplicated contents from config (#1111)
+- Refactor the structure of documentation (#1113, #1121)
+- Update the required minimum version of mmdet and mmseg (#1147)
+#### Bug Fixes
+- Fix symlink failure on Windows (#1096)
+- Fix the upper bound of mmcv version in the mminstall requirements (#1104)
+- Fix API documentation compilation and mmcv build errors (#1116)
+- Fix figure links and pdf documentation compilation (#1132, #1135)
+#### Contributors
+A total of 4 developers contributed to this release.
+@ZwwWayne, @ZCMax, @Tai-Wang, @wHao-Wu
 ### v0.17.3 (1/12/2021)
 #### Improvements

--- a/docs/en/datasets/nuscenes_det.md
+++ b/docs/en/datasets/nuscenes_det.md
@@ -77,7 +77,7 @@ Next, we will elaborate on the details recorded in these info files.
        - info['sweeps'][i]['sensor2lidar_translation']: The translation from the current sensor (for collecting the sweep data) to lidar. (1x3 list)
        - info['sweeps'][i]['sensor2lidar_rotation']: The rotation from the current sensor (for collecting the sweep data) to lidar. (1x4 list in the quaternion format)
    - info['cams']: Cameras calibration information. It contains six keys corresponding to each camera: `'CAM_FRONT'`, `'CAM_FRONT_RIGHT'`, `'CAM_FRONT_LEFT'`, `'CAM_BACK'`, `'CAM_BACK_LEFT'`, `'CAM_BACK_RIGHT'`.
-    Each dictionary contains detailed information following the above way for each sweep data (has the same keys for each information as above).
+    Each dictionary contains detailed information following the above way for each sweep data (has the same keys for each information as above). In addition, each camera has a key `'cam_intrinsic'` for recording the intrinsic parameters when projecting 3D points to each image plane.
    - info['lidar2ego_translation']: The translation from lidar to ego vehicle. (1x3 list)
    - info['lidar2ego_rotation']: The rotation from lidar to ego vehicle. (1x4 list in the quaternion format)
    - info['ego2global_translation']: The translation from the ego vehicle to global coordinates. (1x3 list)

--- a/docs/en/datasets/waymo_det.md
+++ b/docs/en/datasets/waymo_det.md
@@ -104,16 +104,21 @@ Considering there are many similar frames in the original dataset, we can basica
 For evaluation on Waymo, please follow the [instruction](https://github.com/waymo-research/waymo-open-dataset/blob/master/docs/quick_start.md/) to build the binary file `compute_detection_metrics_main` for metrics computation and put it into `mmdet3d/core/evaluation/waymo_utils/`.  Basically, you can follow the commands below to install `bazel` and build the file.
   ```shell
+   # download the code and enter the base directory
   git clone https://github.com/waymo-research/waymo-open-dataset.git waymo-od
   cd waymo-od
   git checkout remotes/origin/master
+   # use the Bazel build system
   sudo apt-get install --assume-yes pkg-config zip g++ zlib1g-dev unzip python3 python3-pip
-   wget https://github.com/bazelbuild/bazel/releases/download/0.28.0/bazel-0.28.0-installer-linux-x86_64.sh
+   BAZEL_VERSION=3.1.0
-   sudo bash bazel-0.28.0-installer-linux-x86_64.sh
+   wget https://github.com/bazelbuild/bazel/releases/download/${BAZEL_VERSION}/bazel-${BAZEL_VERSION}-installer-linux-x86_64.sh
+   sudo bash bazel-${BAZEL_VERSION}-installer-linux-x86_64.sh
   sudo apt install build-essential
+   # configure .bazelrc
   ./configure.sh
+   # delete previous bazel outputs and reset internal caches
   bazel clean
   bazel build waymo_open_dataset/metrics/tools/compute_detection_metrics_main

--- a/docs/en/faq.md
+++ b/docs/en/faq.md
@@ -30,3 +30,12 @@ We list some potential troubles encountered by users and developers, along with
  or
  ``pip install -e "git+https://github.com/ppwwyyxx/cocoapi#egg=pycocotools&subdirectory=PythonAPI"``
+## How to annotate point cloud?
+MMDetection3D does not support point cloud annotation. Some open-source annotation tool are offered for reference:
+- [SUSTechPOINTS](https://github.com/naurril/SUSTechPOINTS)
+- [LATTE](https://github.com/bernwang/latte)
+Besides, we improved [LATTE](https://github.com/bernwang/latte) for better use. More details can be found [here](https://arxiv.org/abs/2011.10174).
--- a/docs/en/getting_started.md
+++ b/docs/en/getting_started.md
@@ -13,20 +13,22 @@ The required versions of MMCV, MMDetection and MMSegmentation for different vers
 | MMDetection3D version | MMDetection version | MMSegmentation version |    MMCV version     |
 |:-------------------:|:-------------------:|:-------------------:|:-------------------:|
 | master              | mmdet>=2.19.0, <=3.0.0| mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
-| 0.17.3              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.18.1              | mmdet>=2.19.0, <=3.0.0| mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
-| 0.17.2              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.18.0              | mmdet>=2.19.0, <=3.0.0| mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
-| 0.17.1              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.3              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.17.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.2              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.16.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.1              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.15.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.14.0              | mmdet>=2.10.0, <=2.11.0| mmseg==0.14.0 | mmcv-full>=1.3.1, <=1.5.0|
+| 0.16.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.13.0              | mmdet>=2.10.0, <=2.11.0| Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.15.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.12.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.14.0              | mmdet>=2.10.0, <=2.11.0| mmseg==0.14.0 | mmcv-full>=1.3.1, <=1.4.0|
-| 0.11.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.13.0              | mmdet>=2.10.0, <=2.11.0| Not required  | mmcv-full>=1.2.4, <=1.4.0|
-| 0.10.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.12.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.4.0|
-| 0.9.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.11.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.3.0|
-| 0.8.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.5.0|
+| 0.10.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.3.0|
-| 0.7.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.5.0|
+| 0.9.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.3.0|
+| 0.8.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.3.0|
+| 0.7.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.3.0|
 | 0.6.0               | mmdet>=2.4.0, <=2.11.0 | Not required  | mmcv-full>=1.1.3, <=1.2.0|
 | 0.5.0               | 2.3.0                  | Not required  | mmcv-full==1.0.5|
@@ -82,6 +84,13 @@ Please replace `{cu_version}` and `{torch_version}` in the url to your desired o
 pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7.0/index.html
 ```
+mmcv-full is only compiled on PyTorch 1.x.0 because the compatibility usually holds between 1.x.0 and 1.x.1. If your PyTorch version is 1.x.1, you can install mmcv-full compiled with PyTorch 1.x.0 and it usually works well.
+```shell
+# We can ignore the micro version of PyTorch
+pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7/index.html
+```
 See [here](https://github.com/open-mmlab/mmcv#install-with-pip) for different versions of MMCV compatible to different PyTorch and CUDA versions.
 Optionally, you could also build the full version from source:

--- a/docs/zh_cn/datasets/nuscenes_det.md
+++ b/docs/zh_cn/datasets/nuscenes_det.md
@@ -78,7 +78,7 @@ mmdetection3d
        - info['sweeps'][i]['sensor2lidar_translation']：从当前传感器（用于收集扫描数据）到激光雷达的转换（1x3 列表）。
        - info['sweeps'][i]['sensor2lidar_rotation']：从当前传感器（用于收集扫描数据）到激光雷达的旋转（四元数格式的 1x4 列表）。
    - info['cams']：相机校准信息。它包含与每个摄像头对应的六个键值： `'CAM_FRONT'`, `'CAM_FRONT_RIGHT'`, `'CAM_FRONT_LEFT'`, `'CAM_BACK'`, `'CAM_BACK_LEFT'`, `'CAM_BACK_RIGHT'`。
-    每个字典包含每个扫描数据按照上述方式的详细信息（每个信息的关键字与上述相同）。
+    每个字典包含每个扫描数据按照上述方式的详细信息（每个信息的关键字与上述相同）。除此之外，每个相机还包含了一个键值 `'cam_intrinsic'` 用来保存 3D 点投影到图像平面上需要的内参信息。
    - info['lidar2ego_translation']：从激光雷达到自车的转换（1x3 列表）。
    - info['lidar2ego_rotation']：从激光雷达到自车的旋转（四元数格式的 1x4 列表）。
    - info['ego2global_translation']：从自车到全局坐标的转换（1x3 列表）。

--- a/docs/zh_cn/datasets/waymo_det.md
+++ b/docs/zh_cn/datasets/waymo_det.md
@@ -104,16 +104,21 @@ mmdetection3d
 为了在 Waymo 数据集上进行检测性能评估，请按照[此处指示](https://github.com/waymo-research/waymo-open-dataset/blob/master/docs/quick_start.md/)构建用于计算评估指标的二进制文件 `compute_detection_metrics_main`，并将它置于 `mmdet3d/core/evaluation/waymo_utils/` 下。您基本上可以按照下方命令安装 `bazel`，然后构建二进制文件：
   ```shell
+   # download the code and enter the base directory
   git clone https://github.com/waymo-research/waymo-open-dataset.git waymo-od
   cd waymo-od
   git checkout remotes/origin/master
+   # use the Bazel build system
   sudo apt-get install --assume-yes pkg-config zip g++ zlib1g-dev unzip python3 python3-pip
-   wget https://github.com/bazelbuild/bazel/releases/download/0.28.0/bazel-0.28.0-installer-linux-x86_64.sh
+   BAZEL_VERSION=3.1.0
-   sudo bash bazel-0.28.0-installer-linux-x86_64.sh
+   wget https://github.com/bazelbuild/bazel/releases/download/${BAZEL_VERSION}/bazel-${BAZEL_VERSION}-installer-linux-x86_64.sh
+   sudo bash bazel-${BAZEL_VERSION}-installer-linux-x86_64.sh
   sudo apt install build-essential
+   # configure .bazelrc
   ./configure.sh
+   # delete previous bazel outputs and reset internal caches
   bazel clean
   bazel build waymo_open_dataset/metrics/tools/compute_detection_metrics_main

--- a/docs/zh_cn/faq.md
+++ b/docs/zh_cn/faq.md
@@ -30,3 +30,12 @@
  或者
  ``pip install -e "git+https://github.com/ppwwyyxx/cocoapi#egg=pycocotools&subdirectory=PythonAPI"``
+## 如何标注点云？
+MMDetection3D 不支持点云标注。我们提供一些开源的标注工具供参考：
+- [SUSTechPOINTS](https://github.com/naurril/SUSTechPOINTS)
+- [LATTE](https://github.com/bernwang/latte)
+此外，我们改进了 [LATTE](https://github.com/bernwang/latte) 以便更方便的标注。 更多的细节请参考 [这里](https://arxiv.org/abs/2011.10174)。
--- a/docs/zh_cn/getting_started.md
+++ b/docs/zh_cn/getting_started.md
@@ -10,20 +10,22 @@
 | MMDetection3D version | MMDetection version | MMSegmentation version |    MMCV version     |
 |:-------------------:|:-------------------:|:-------------------:|:-------------------:|
 | master              | mmdet>=2.19.0, <=3.0.0| mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
-| 0.17.3              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.18.1              | mmdet>=2.19.0, <=3.0.0| mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
-| 0.17.2              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.18.0              | mmdet>=2.19.0, <=3.0.0| mmseg>=0.20.0, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
-| 0.17.1              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.3              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.17.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.2              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.16.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.1              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.15.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.5.0|
+| 0.17.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.14.0              | mmdet>=2.10.0, <=2.11.0| mmseg>=0.14.0 | mmcv-full>=1.3.1, <=1.5.0|
+| 0.16.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.13.0              | mmdet>=2.10.0, <=2.11.0| Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.15.0              | mmdet>=2.14.0, <=3.0.0| mmseg>=0.14.1, <=1.0.0 | mmcv-full>=1.3.8, <=1.4.0|
-| 0.12.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.14.0              | mmdet>=2.10.0, <=2.11.0| mmseg==0.14.0 | mmcv-full>=1.3.1, <=1.4.0|
-| 0.11.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.13.0              | mmdet>=2.10.0, <=2.11.0| Not required  | mmcv-full>=1.2.4, <=1.4.0|
-| 0.10.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.12.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.4.0|
-| 0.9.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.5.0|
+| 0.11.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.3.0|
-| 0.8.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.5.0|
+| 0.10.0              | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.3.0|
-| 0.7.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.5.0|
+| 0.9.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.2.4, <=1.3.0|
+| 0.8.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.3.0|
+| 0.7.0               | mmdet>=2.5.0, <=2.11.0 | Not required  | mmcv-full>=1.1.5, <=1.3.0|
 | 0.6.0               | mmdet>=2.4.0, <=2.11.0 | Not required  | mmcv-full>=1.1.3, <=1.2.0|
 | 0.5.0               | 2.3.0                  | Not required  | mmcv-full==1.0.5|
@@ -74,6 +76,13 @@ pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{
 pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7.0/index.html
 ```
+PyTorch 在 1.x.0 和 1.x.1 之间通常是兼容的，故 mmcv-full 只提供 1.x.0 的编译包。如果你的 PyTorch 版本是 1.x.1，你可以放心地安装在 1.x.0 版本编译的 mmcv-full。
+```
+# 我们可以忽略 PyTorch 的小版本号
+pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7/index.html
+```
 请参考 [MMCV](https://mmcv.readthedocs.io/en/latest/#installation) 获取不同版本的 MMCV 所兼容的的不同的 PyTorch 和 CUDA 版本。同时，也可以通过以下命令行从源码编译 MMCV：
 ```shell

--- a/mmdet3d/core/bbox/structures/depth_box3d.py
+++ b/mmdet3d/core/bbox/structures/depth_box3d.py
@@ -71,7 +71,9 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
               (x0, y0, z0) + ----------- + --------> right x
                                          (x1, y0, z0)
        """
-        assert len(self.tensor) != 0
+        if self.tensor.numel() == 0:
+            return torch.empty([0, 8, 3], device=self.tensor.device)
        dims = self.dims
        corners_norm = torch.from_numpy(
            np.stack(np.unravel_index(np.arange(8), [2] * 3), axis=1)).to(

--- a/mmdet3d/core/bbox/structures/lidar_box3d.py
+++ b/mmdet3d/core/bbox/structures/lidar_box3d.py
@@ -69,9 +69,9 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
            left y<-------- + ----------- + (x0, y1, z0)
                (x0, y0, z0)
        """
-        # TODO: rotation_3d_in_axis function do not support
+        if self.tensor.numel() == 0:
-        #  empty tensor currently.
+            return torch.empty([0, 8, 3], device=self.tensor.device)
-        assert len(self.tensor) != 0
        dims = self.dims
        corners_norm = torch.from_numpy(
            np.stack(np.unravel_index(np.arange(8), [2] * 3), axis=1)).to(

--- a/mmdet3d/datasets/kitti_dataset.py
+++ b/mmdet3d/datasets/kitti_dataset.py
@@ -153,12 +153,14 @@ class KittiDataset(Custom3DDataset):
                - gt_bboxes (np.ndarray): 2D ground truth bboxes.
                - gt_labels (np.ndarray): Labels of ground truths.
                - gt_names (list[str]): Class names of ground truths.
+                - difficulty (int): kitti difficulty.
        """
        # Use index to get the annos, thus the evalhook could also use this api
        info = self.data_infos[index]
        rect = info['calib']['R0_rect'].astype(np.float32)
        Trv2c = info['calib']['Tr_velo_to_cam'].astype(np.float32)
+        difficulty = info['annos']['difficulty']
        annos = info['annos']
        # we need other objects to avoid collision when sample
        annos = self.remove_dontcare(annos)
@@ -192,7 +194,8 @@ class KittiDataset(Custom3DDataset):
            gt_labels_3d=gt_labels_3d,
            bboxes=gt_bboxes,
            labels=gt_labels,
-            gt_names=gt_names)
+            gt_names=gt_names,
+            difficulty=difficulty)
        return anns_results
    def drop_arrays_by_name(self, gt_names, used_classes):
@@ -319,6 +322,7 @@ class KittiDataset(Custom3DDataset):
                If not specified, a temp file will be created. Default: None.
            submission_prefix (str, optional): The prefix of submission data.
                If not specified, the submission data will not be generated.
+                Default: None.
            show (bool, optional): Whether to visualize.
                Default: False.
            out_dir (str, optional): Path to save the visualization results.

--- a/mmdet3d/datasets/pipelines/transforms_3d.py
+++ b/mmdet3d/datasets/pipelines/transforms_3d.py
@@ -116,6 +116,10 @@ class RandomFlip3D(RandomFlip):
                updated in the result dict.
        """
        assert direction in ['horizontal', 'vertical']
+        # for semantic segmentation task, only points will be flipped.
+        if 'bbox3d_fields' not in input_dict:
+            input_dict['points'].flip(direction)
+            return
        if len(input_dict['bbox3d_fields']) == 0:  # test mode
            input_dict['bbox3d_fields'].append('empty_box3d')
            input_dict['empty_box3d'] = input_dict['box_type_3d'](
@@ -921,6 +925,12 @@ class PointSample(object):
                and 'pts_semantic_mask' keys are updated in the result dict.
        """
        points = results['points']
+        # Points in Camera coord can provide the depth information.
+        # TODO: Need to support distance-based sampling for other coord system.
+        if self.sample_range is not None:
+            from mmdet3d.core.points import CameraPoints
+            assert isinstance(points, CameraPoints), \
+                'Sampling based on distance is only applicable for CAM coord'
        points, choices = self._points_random_sampling(
            points,
            self.num_points,

--- a/mmdet3d/version.py
+++ b/mmdet3d/version.py
 # Copyright (c) Open-MMLab. All rights reserved.
-__version__ = '0.17.3'
+__version__ = '0.18.1'
 short_version = __version__

--- a/setup.py
+++ b/setup.py
@@ -217,8 +217,6 @@ if __name__ == '__main__':
            'Programming Language :: Python :: 3.7',
        ],
        license='Apache License 2.0',
-        setup_requires=parse_requirements('requirements/build.txt'),
-        tests_require=parse_requirements('requirements/tests.txt'),
        install_requires=parse_requirements('requirements/runtime.txt'),
        extras_require={
            'all': parse_requirements('requirements.txt'),

--- a/tools/test.py
+++ b/tools/test.py
@@ -36,6 +36,18 @@ def parse_args():
        action='store_true',
        help='Whether to fuse conv and bn, this will slightly increase'
        'the inference speed')
+    parser.add_argument(
+        '--gpu-ids',
+        type=int,
+        nargs='+',
+        help='(Deprecated, please use --gpu-id) ids of gpus to use '
+        '(only applicable to non-distributed training)')
+    parser.add_argument(
+        '--gpu-id',
+        type=int,
+        default=0,
+        help='id of gpu to use '
+        '(only applicable to non-distributed testing)')
    parser.add_argument(
        '--format-only',
        action='store_true',
@@ -152,6 +164,15 @@ def main():
            for ds_cfg in cfg.data.test:
                ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
+    if args.gpu_ids is not None:
+        cfg.gpu_ids = args.gpu_ids[0:1]
+        warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
+                      'Because we only support single GPU mode in '
+                      'non-distributed testing. Use the first GPU '
+                      'in `gpu_ids` now.')
+    else:
+        cfg.gpu_ids = [args.gpu_id]
    # init distributed env first, since logger depends on the dist info.
    if args.launcher == 'none':
        distributed = False
@@ -195,7 +216,7 @@ def main():
        model.PALETTE = dataset.PALETTE
    if not distributed:
-        model = MMDataParallel(model, device_ids=[0])
+        model = MMDataParallel(model, device_ids=cfg.gpu_ids)
        outputs = single_gpu_test(model, data_loader, args.show, args.show_dir)
    else:
        model = MMDistributedDataParallel(