Update performance after benchmark

PJIANG-UNO · Jun 21, 2020 · b4cc412 · b4cc412
1 parent ce70413
commit b4cc412
Show file tree

Hide file tree

Showing 7 changed files with 72 additions and 27 deletions.
diff --git a/configs/dynamic_voxelization/README.md b/configs/dynamic_voxelization/README.md
@@ -0,0 +1,26 @@
+# Dynamic Voxelization
+
+## Introduction
+
+We implement Dynamic Voxelization proposed in  and provide its results and models on KITTI dataset.
+```
+@article{zhou2019endtoend,
+    title={End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds},
+    author={Yin Zhou and Pei Sun and Yu Zhang and Dragomir Anguelov and Jiyang Gao and Tom Ouyang and James Guo and Jiquan Ngiam and Vijay Vasudevan},
+    year={2019},
+    eprint={1910.06528},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+
+```
+
+## Results
+
+### KITTI
+
+|  Model   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
+| :---------: | :-----: |:-----: | :------: | :------------: | :----: | :------: |
+|[SECOND](./dv_second_secfpn_6x8_80e_kitti-3d-car.py)|Car    |cyclic 80e|5.5||78.83||
+|[SECOND](./dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py)| 3 Class|cosine 80e|5.5||65.10||
+|[PointPillars](./dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py)| Car|cyclic 80e|4.7||77.76||
diff --git a/configs/mvxnet/README.md b/configs/mvxnet/README.md
@@ -1,5 +1,7 @@
 # MVX-Net: Multimodal VoxelNet for 3D Object Detection
+
 ## Introduction
+
 We implement MVX-Net and provide its results and models on KITTI dataset.
 ```
 @inproceedings{sindagi2019mvx,
@@ -12,9 +14,11 @@ We implement MVX-Net and provide its results and models on KITTI dataset.
 }
 
 ```
-## Usage
+
 ## Results
+
 ### KITTI
-|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
+
+|  Backbone   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](../)    |||||
+|    [SECFPN](./dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class.py)|3 Class|cosine 80e|6.7||63.0||
diff --git a/configs/parta2/README.md b/configs/parta2/README.md
@@ -1,6 +1,9 @@
 # From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
+
 ## Introduction
+
 We implement Part-A^2 and provide its results and checkpoints on KITTI dataset.
+
 ```
 @article{shi2020points,
   title={From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network},
@@ -11,9 +14,11 @@ We implement Part-A^2 and provide its results and checkpoints on KITTI dataset.
 }
 
 ```
-## Usage
 ## Results
+
 ### KITTI
-|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
-| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](../)    |||||
+
+|  Backbone   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
+| :---------: | :-----: |:-----: | :------: | :------------: | :----: |:----: | :------: |
+|    [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py) |3 Class|cyclic 80e|4.1||67.9||
+|    [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py) |Car |cyclic 80e|4.0||79.16||
diff --git a/configs/pointpillars/README.md b/configs/pointpillars/README.md
@@ -1,6 +1,9 @@
 # PointPillars: Fast Encoders for Object Detection from Point Clouds
+
 ## Introduction
+
 We implement PointPillars and provide the results and checkpoints on KITTI and nuScenes datasets.
+
 ```
 @inproceedings{lang2019pointpillars,
   title={Pointpillars: Fast encoders for object detection from point clouds},
@@ -11,14 +14,19 @@ We implement PointPillars and provide the results and checkpoints on KITTI and n
 }
 
 ```
-## Usage
+
 ## Results
+
 ### KITTI
-|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
-| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](../)    |||||
+
+|  Backbone|Class   | Lr schd | Mem (GB) | Inf time (fps) | AP  |Download |
+| :---------: | :-----: |:-----: | :------: | :------------: | :----: | :------: |
+|    [SECFPN](./hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py)|Car|cyclic 160e|5.4||77.1||
+|    [SECFPN](./hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py)|3 Class|cyclic 160e|5.5||59.5|
 
 ### nuScenes
+
 |  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](../)    |||||
+|[SECFPN](./hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7||
+|[FPN](./hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||40.0|53.3||
diff --git a/configs/regnet/README.md b/configs/regnet/README.md
@@ -51,7 +51,7 @@ For other pre-trained models or self-implemented regnet models, the users are re
 
 |  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](../)     |  2x    ||||
-|[RegNetX-400MF-SECFPN](./hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py)|  2x    ||||
-|    [FPN](../)     |  2x    ||||
-|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|  2x    ||||
+|[SECFPN](../pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7||
+|[RegNetX-400MF-SECFPN](./hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py)|  2x    |16.4||41.2|55.2||
+|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.1||40.0|53.3||
+|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.3||44.8|56.4||
diff --git a/configs/second/README.md b/configs/second/README.md
@@ -1,22 +1,22 @@
 # Second: Sparsely embedded convolutional detection
+
 ## Introduction
+
 We implement SECOND and provide the results and checkpoints on KITTI dataset.
 ```
 @article{yan2018second,
   title={Second: Sparsely embedded convolutional detection},
   author={Yan, Yan and Mao, Yuxing and Li, Bo},
   journal={Sensors},
-  volume={18},
-  number={10},
-  pages={3337},
   year={2018},
   publisher={Multidisciplinary Digital Publishing Institute}
 }
 
 ```
-## Usage
 ## Results
+
 ### KITTI
-|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
+|  Backbone   |Class| Lr schd | Mem (GB) | Inf time (fps) | mAP |Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [SECFPN](../)    |||||
+|    [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-car.py)| Car |cyclic 80e|5.4||79.07|
+|    [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-3class.py)| 3 Class |cyclic 80e|5.4||64.41|
diff --git a/configs/votenet/README.md b/configs/votenet/README.md
@@ -1,4 +1,5 @@
 # Deep Hough Voting for 3D Object Detection in Point Clouds
+
 ## Introduction
 We implement VoteNet and provide the result and checkpoints on ScanNet and SUNRGBD datasets.
 ```
@@ -9,14 +10,15 @@ We implement VoteNet and provide the result and checkpoints on ScanNet and SUNRG
     year = {2019}
 }
 ```
-## Usage
+
 ## Results
+
 ### ScanNet
-|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
+|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | [email protected] |[email protected]| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [PointNet++](../)     |  3x    |3.9717|||
+|    [PointNet++](./votenet_8x8_scannet-3d-18class.py)     |  3x    |4.1||62.90|39.91||
 
 ### SUNRGBD
-|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
+|  Backbone   | Lr schd | Mem (GB) | Inf time (fps) | [email protected] |[email protected]| Download |
 | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
-|    [PointNet++](../)     |  3x    |7.878|||
+|    [PointNet++](./)     |  3x    |8.1||59.07|35.77||