Skip to content

GitLab

Commit b4cc412b authored by zhangwenwei's avatar zhangwenwei
Browse files

Update performance after benchmark

parent ce70413f
Hide whitespace changes
Inline Side-by-side
Showing with 72 additions and 27 deletions
configs/dynamic_voxelization/README.md 0 → 100644
View file @ b4cc412b
# 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||
configs/mvxnet/README.md
View file @ b4cc412b
# 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||
configs/parta2/README.md
View file @ b4cc412b
# 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||
configs/pointpillars/README.md
View file @ b4cc412b
# 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||
configs/regnet/README.md
View file @ b4cc412b
......@@ -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||
configs/second/README.md
View file @ b4cc412b
# 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|
configs/votenet/README.md
View file @ b4cc412b
# 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) | AP@0.25 |AP@0.5| 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) | AP@0.25 |AP@0.5| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [PointNet++](../) | 3x |7.878|||
| [PointNet++](./) | 3x |8.1||59.07|35.77||
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment