[Feature] Add SMOKE benchmark (#988)

* add metafile and readme

* fix typos

* refine some typos

* fix some typos

* add smoke in readme and model-zoo

* change dlanet to dla

* change dlanet to dla in metafile

README.md

@@ -84,6 +84,7 @@ Support backbones:
 - [x] PointNet++ (NeurIPS'2017)
 - [x] RegNet (CVPR'2020)
 - [x] DGCNN (TOG'2019)
+- [x] DLA (CVPR'2018)
 
 Support methods
 
@@ -104,26 +105,28 @@ Support methods
 - [x] [ImVoxelNet (Arxiv'2021)](configs/imvoxelnet/README.md)
 - [x] [PAConv (CVPR'2021)](configs/paconv/README.md)
 - [x] [DGCNN (TOG'2019)](configs/dgcnn/README.md)
-
-|                    | ResNet   | ResNeXt  | SENet    |PointNet++ |DGCNN     | HRNet | RegNetX | Res2Net |
-|--------------------|:--------:|:--------:|:--------:|:---------:|:---------:|:-----:|:--------:|:-----:|
-| SECOND             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| PointPillars       | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| FreeAnchor         | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| VoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| H3DNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| 3DSSD            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| Part-A2            | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| MVXNet             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| CenterPoint        | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| SSN                | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| ImVoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| FCOS3D               | ✓        | ☐        | ☐        | ✗         | ✗         | ☐     | ☐        | ☐     |
-| PointNet++           | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| Group-Free-3D        | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| ImVoxelNet           | ✓         | ✗        | ✗        | ✗        | ✗         | ✗     | ✗        | ✗     |
-| PAConv               | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| DGCNN                | ✗        | ✗        | ✗        | ✗         | ✓         | ✗     | ✗        | ✗     |
+- [x] [SMOKE (CVPRW'2020)](configs/smoke/README.md)
+
+|                    | ResNet   | ResNeXt  | SENet    |PointNet++ |DGCNN     | HRNet | RegNetX | Res2Net | DLA |
+|--------------------|:--------:|:--------:|:--------:|:---------:|:---------:|:-----:|:--------:|:-----:|:---:|
+| SECOND             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| PointPillars       | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| FreeAnchor         | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| VoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| H3DNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| 3DSSD            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| Part-A2            | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| MVXNet             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| CenterPoint        | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| SSN                | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| ImVoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| FCOS3D               | ✓        | ☐        | ☐        | ✗         | ✗         | ☐     | ☐        | ☐     | ✗
+| PointNet++           | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| Group-Free-3D        | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| ImVoxelNet           | ✓         | ✗        | ✗        | ✗        | ✗         | ✗     | ✗        | ✗     | ✗
+| PAConv               | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| DGCNN                | ✗        | ✗        | ✗        | ✗         | ✓         | ✗     | ✗        | ✗     | ✗
+| SMOKE                | ✗        | ✗        | ✗        | ✗         | ✗         | ✗     | ✗        | ✗     | ✓
 
 Other features
 - [x] [Dynamic Voxelization](configs/dynamic_voxelization/README.md)

README_zh-CN.md

@@ -83,6 +83,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 - [x] PointNet++ (NeurIPS'2017)
 - [x] RegNet (CVPR'2020)
 - [x] DGCNN (TOG'2019)
+- [x] DLA (CVPR'2018)
 
 已支持的算法：
 
@@ -103,26 +104,28 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 - [x] [ImVoxelNet (Arxiv'2021)](configs/imvoxelnet/README.md)
 - [x] [PAConv (CVPR'2021)](configs/paconv/README.md)
 - [x] [DGCNN (TOG'2019)](configs/dgcnn/README.md)
-
-|                    | ResNet   | ResNeXt  | SENet    |PointNet++ |DGCNN     | HRNet | RegNetX | Res2Net |
-|--------------------|:--------:|:--------:|:--------:|:---------:|:---------:|:-----:|:--------:|:-----:|
-| SECOND             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| PointPillars       | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| FreeAnchor         | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| VoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| H3DNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| 3DSSD            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| Part-A2            | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| MVXNet             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| CenterPoint        | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| SSN                | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     |
-| ImVoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| FCOS3D               | ✓        | ☐        | ☐        | ✗         | ✗         | ☐     | ☐        | ☐     |
-| PointNet++           | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| Group-Free-3D        | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| ImVoxelNet           | ✓         | ✗        | ✗        | ✗        | ✗         | ✗     | ✗        | ✗     |
-| PAConv               | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     |
-| DGCNN                | ✗        | ✗        | ✗        | ✗         | ✓         | ✗     | ✗        | ✗     |
+- [x] [SMOKE (CVPRW'2020)](configs/smoke/README.md)
+
+|                    | ResNet   | ResNeXt  | SENet    |PointNet++ |DGCNN     | HRNet | RegNetX | Res2Net | DLA |
+|--------------------|:--------:|:--------:|:--------:|:---------:|:---------:|:-----:|:--------:|:-----:|:---:|
+| SECOND             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| PointPillars       | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| FreeAnchor         | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| VoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| H3DNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| 3DSSD            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| Part-A2            | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| MVXNet             | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| CenterPoint        | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| SSN                | ☐        | ☐        | ☐        | ✗         | ✗         | ☐     | ✓        | ☐     | ✗
+| ImVoteNet            | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| FCOS3D               | ✓        | ☐        | ☐        | ✗         | ✗         | ☐     | ☐        | ☐     | ✗
+| PointNet++           | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| Group-Free-3D        | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| ImVoxelNet           | ✓         | ✗        | ✗        | ✗        | ✗         | ✗     | ✗        | ✗     | ✗
+| PAConv               | ✗        | ✗        | ✗        | ✓         | ✗         | ✗     | ✗        | ✗     | ✗
+| DGCNN                | ✗        | ✗        | ✗        | ✗         | ✓         | ✗     | ✗        | ✗     | ✗
+| SMOKE                | ✗        | ✗        | ✗        | ✗         | ✗         | ✗     | ✗        | ✗     | ✓
 
 其他特性
 - [x] [Dynamic Voxelization](configs/dynamic_voxelization/README.md)

configs/smoke/README.md

+# SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+We implement SMOKE and provide the results and checkpoints on KITTI dataset.
+
+```
+@inproceedings{liu2020smoke,
+  title={Smoke: Single-stage monocular 3d object detection via keypoint estimation},
+  author={Liu, Zechen and Wu, Zizhang and T{\'o}th, Roland},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
+  pages={996--997},
+  year={2020}
+}
+```
+
+## Results
+
+### KITTI
+
+|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
+| :---------: | :-----: | :------: | :------------: | :----: | :------: |
+|[DLA34](./smoke_dla34_pytorch_dlaneck_gn-head_kitti_mono3d.py)|6x|9.64||13.85|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553-d46d9bb0.pth) &#124; [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553.log.json)
+
+Note: mAP represents Car moderate 3D strict AP11 results.
+
+Detailed performance on KITTI 3D detection (3D/BEV) is as follows, evaluated by AP11 metric:
+
+|             |     Easy      |    Moderate    |     Hard     |
+|-------------|:-------------:|:--------------:|:------------:|
+| Car         | 16.92 / 22.97 | 13.85 / 18.32  | 11.90 / 15.88|
+| Pedestrian  | 11.13 / 12.61| 11.10 / 11.32  | 10.67 / 11.14|
+| Cyclist     | 0.99  / 1.47  | 0.54 / 0.65    | 0.55 / 0.67  |

configs/smoke/metafile.yml

+Collections:
+  - Name: SMOKE
+    Metadata:
+      Training Data: KITTI
+      Training Techniques:
+        - Adam
+      Training Resources: 4x V100 GPUS
+      Architecture:
+        - SMOKEMono3DHead
+        - DLA
+    Paper:
+      URL: https://arxiv.org/abs/2002.10111
+      Title: 'SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation'
+    README: configs/smoke/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/smoke_mono3d.py#L7
+      Version: v0.17.1
+
+Models:
+  - Name: smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d
+    In Collection: SMOKE
+    Config: configs/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d.py
+    Metadata:
+      Training Memory (GB): 9.6
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 13.8
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553-d46d9bb0.pth

docs/model_zoo.md

@@ -80,4 +80,8 @@ Please refer to [PAConv](https://github.com/open-mmlab/mmdetection3d/blob/master
 
 ### DGCNN
 
-Please refer to [DGCNN](https://github.com/open-mmlab/mmdetection3d/blob/master/configs/dgcnn) for details. We provide DGCNN baselines on S3DIS dataset.
+Please refer to [DGCNN](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/dgcnn) for details. We provide DGCNN baselines on S3DIS dataset.
+
+### SMOKE
+
+Please refer to [SMOKE](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/smoke) for details. We provide SMOKE baselines on KITTI dataset.

docs_zh-CN/model_zoo.md

@@ -82,4 +82,8 @@
 
 ### DGCNN
 
-请参考 [DGCNN](https://github.com/open-mmlab/mmdetection3d/blob/master/configs/dgcnn) 获取更多细节，我们在 S3DIS 数据集上给出了相应的结果.
+请参考 [DGCNN](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/dgcnn) 获取更多细节，我们在 S3DIS 数据集上给出了相应的结果.
+
+### SMOKE
+
+请考考 [SMOKE](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0/configs/smoke) 获取更多细节，我们在 KITTI 数据集上给出了相应的结果.