Skip to content

GitLab

Commit 919b368c authored by fengzch-das's avatar fengzch-das
Browse files

update readme

parent 66101bd4
Pipeline #2953 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 191 additions and 124 deletions
README.md
View file @ 919b368c
# RODNet: Radar Object Detection Network
This is the official implementation of our RODNet papers
at [WACV 2021](https://openaccess.thecvf.com/content/WACV2021/html/Wang_RODNet_Radar_Object_Detection_Using_Cross-Modal_Supervision_WACV_2021_paper.html)
and [IEEE J-STSP 2021](https://ieeexplore.ieee.org/abstract/document/9353210).
[[Arxiv]](https://arxiv.org/abs/2102.05150)
[[Dataset]](https://www.cruwdataset.org)
[[ROD2021 Challenge]](https://codalab.lisn.upsaclay.fr/competitions/1063)
[[Presentation]](https://youtu.be/UZbxI4o2-7g)
[[Demo]](https://youtu.be/09HaDySa29I)
![RODNet Overview](./assets/images/overview.jpg?raw=true)
Please cite our paper if this repository is helpful for your research:
```
@inproceedings{wang2021rodnet,
author={Wang, Yizhou and Jiang, Zhongyu and Gao, Xiangyu and Hwang, Jenq-Neng and Xing, Guanbin and Liu, Hui},
title={RODNet: Radar Object Detection Using Cross-Modal Supervision},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month={January},
year={2021},
pages={504-513}
}
```
```
@article{wang2021rodnet,
title={RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization},
author={Wang, Yizhou and Jiang, Zhongyu and Li, Yudong and Hwang, Jenq-Neng and Xing, Guanbin and Liu, Hui},
journal={IEEE Journal of Selected Topics in Signal Processing},
volume={15},
number={4},
pages={954--967},
year={2021},
publisher={IEEE}
}
# <div align="center"><strong>RODNet</strong></div>
## 简介
RODNet 是一个深度雷达目标检测网络
## 安装
组件支持组合
| PyTorch版本 | fastpt版本 |RODNet版本 | DTK版本 | Python版本 | 推荐编译方式 |
| ----------- | ----------- | ----------- | ------------------------ | -----------------| ------------ |
| 2.5.1 | 2.1.0 |0.3 | >= 25.04 | 3.8、3.10、3.11 | fastpt不转码 |
| 2.4.1 | 2.0.1 |0.3 | >= 25.04 | 3.8、3.10、3.11 | fastpt不转码 |
| 其他 | 其他 | 其他 | 其他 | 3.8、3.10、3.11 | hip转码 |
+ pytorch版本大于2.4.1 && dtk版本大于25.04 推荐使用fastpt不转码编译。
### 1、使用pip方式安装
RODNet whl包下载目录：[光和开发者社区](https://download.sourcefind.cn:65024/4/main)，选择对应的pytorch版本和python版本下载对应RODNet的whl包
```shell
pip install torch* (下载torch的whl包)
pip install fastpt* --no-deps (下载fastpt的whl包)
source /usr/local/bin/fastpt -E
pip install rodnet* (下载的RODNet的whl包)
```
### 2、使用源码编译方式安装
## Installation
Clone RODNet code.
```commandline
cd $RODNET_ROOT
git clone https://github.com/yizhou-wang/RODNet.git
```
#### 编译环境准备
提供基于fastpt不转码编译：
Create a conda environment for RODNet. Tested under Python 3.6, 3.7, 3.8.
```commandline
conda create -n rodnet python=3.* -y
conda activate rodnet
```
1. 基于光源pytorch基础镜像环境：镜像下载地址：[光合开发者社区](https://sourcefind.cn/#/image/dcu/pytorch)，根据pytorch、python、dtk及系统下载对应的镜像版本。
Install pytorch.
**Note:** If you are using Temporal Deformable Convolution (TDC), we only tested under `pytorch<=1.4` and `CUDA=10.1`.
Without TDC, you should be able to choose the latest versions.
If you met some issues with environment, feel free to raise an issue.
```commandline
conda install pytorch=1.4 torchvision cudatoolkit=10.1 -c pytorch # if using TDC
# OR
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch # if not using TDC
2. 基于现有python环境：安装pytorch，fastpt whl包下载目录：[光合开发者社区](https://sourcefind.cn/#/image/dcu/pytorch)，根据python、dtk版本,下载对应pytorch的whl包。安装命令如下：
```shell
pip install torch* (下载torch的whl包)
pip install fastpt* --no-deps (下载fastpt的whl包, 安装顺序，先安装torch，后安装fastpt)
pip install pytest
pip install wheel
```
Install `cruw-devkit` package.
Please refer to [`cruw-devit`](https://github.com/yizhou-wang/cruw-devkit) repository for detailed instructions.
```commandline
git clone https://github.com/yizhou-wang/cruw-devkit.git
cd cruw-devkit
pip install .
cd ..
#### 源码编译安装
- 代码下载
```shell
git clone http://developer.sourcefind.cn/codes/OpenDAS/rodnet.git # 根据编译需要切换分支
```
Setup RODNet package.
```commandline
pip install -e .
- 提供2种源码编译方式（进入RODNet目录）：
```
**Note:** If you are not using TDC, you can rename script `setup_wo_tdc.py` as `setup.py`, and run the above command.
This should allow you to use the latest cuda and pytorch version.
## Prepare data for RODNet
1. 设置不转码编译环境变量
source /usr/local/bin/fastpt -C
Download [ROD2021 dataset](https://www.cruwdataset.org/download#h.mxc4upuvacso).
Follow [this script](https://github.com/yizhou-wang/RODNet/blob/master/tools/prepare_dataset/reorganize_rod2021.sh) to reorganize files as below.
2. 编译whl包并安装
python3 setup.py bdist_wheel
pip install dist/rodnet* --no-deps
3. 源码编译安装
python3 setup.py install --no-deps
```
data_root
- sequences
| - train
| | - <SEQ_NAME>
| | | - IMAGES_0
| | | | - <FRAME_ID>.jpg
| | | | - ***.jpg
| | | - RADAR_RA_H
| | | - <FRAME_ID>_<CHIRP_ID>.npy
| | | - ***.npy
| | - ***
| |
| - test
| - <SEQ_NAME>
| | - RADAR_RA_H
| | - <FRAME_ID>_<CHIRP_ID>.npy
| | - ***.npy
| - ***
|
- annotations
| - train
| | - <SEQ_NAME>.txt
| | - ***.txt
| - test
| - <SEQ_NAME>.txt
| - ***.txt
- calib
```
#### 注意事项
+ 若使用pip install下载安装过慢，可添加pypi清华源：-i https://pypi.tuna.tsinghua.edu.cn/simple/
+ ROCM_PATH为dtk的路径，默认为/opt/dtk
+ 在pytorch2.5.1环境下编译需要支持c++17语法，打开setup.py文件，把文件中的 -std=c++14 修改为 -std=c++17
Convert data and annotations to `.pkl` files.
```commandline
python tools/prepare_dataset/prepare_data.py \
--config configs/<CONFIG_FILE> \
--data_root <DATASET_ROOT> \
--split train,test \
--out_data_dir data/<DATA_FOLDER_NAME>
```
## Train models
## Known Issue
- 无
```commandline
python tools/train.py --config configs/<CONFIG_FILE> \
--data_dir data/<DATA_FOLDER_NAME> \
--log_dir checkpoints/
```
## Inference
```commandline
python tools/test.py --config configs/<CONFIG_FILE> \
--data_dir data/<DATA_FOLDER_NAME> \
--checkpoint <CHECKPOINT_PATH> \
--res_dir results/
```
## 参考资料
- [README_ORIGIN](README_ORIGIN.md)
- [https://github.com/yizhou-wang/RODNet](https://github.com/yizhou-wang/RODNet)
README_ORIGIN.md 0 → 100644
View file @ 919b368c
# RODNet: Radar Object Detection Network
This is the official implementation of our RODNet papers
at [WACV 2021](https://openaccess.thecvf.com/content/WACV2021/html/Wang_RODNet_Radar_Object_Detection_Using_Cross-Modal_Supervision_WACV_2021_paper.html)
and [IEEE J-STSP 2021](https://ieeexplore.ieee.org/abstract/document/9353210).
[[Arxiv]](https://arxiv.org/abs/2102.05150)
[[Dataset]](https://www.cruwdataset.org)
[[ROD2021 Challenge]](https://codalab.lisn.upsaclay.fr/competitions/1063)
[[Presentation]](https://youtu.be/UZbxI4o2-7g)
[[Demo]](https://youtu.be/09HaDySa29I)
![RODNet Overview](./assets/images/overview.jpg?raw=true)
Please cite our paper if this repository is helpful for your research:
```
@inproceedings{wang2021rodnet,
author={Wang, Yizhou and Jiang, Zhongyu and Gao, Xiangyu and Hwang, Jenq-Neng and Xing, Guanbin and Liu, Hui},
title={RODNet: Radar Object Detection Using Cross-Modal Supervision},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month={January},
year={2021},
pages={504-513}
}
```
```
@article{wang2021rodnet,
title={RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization},
author={Wang, Yizhou and Jiang, Zhongyu and Li, Yudong and Hwang, Jenq-Neng and Xing, Guanbin and Liu, Hui},
journal={IEEE Journal of Selected Topics in Signal Processing},
volume={15},
number={4},
pages={954--967},
year={2021},
publisher={IEEE}
}
```
## Installation
Clone RODNet code.
```commandline
cd $RODNET_ROOT
git clone https://github.com/yizhou-wang/RODNet.git
```
Create a conda environment for RODNet. Tested under Python 3.6, 3.7, 3.8.
```commandline
conda create -n rodnet python=3.* -y
conda activate rodnet
```
Install pytorch.
**Note:** If you are using Temporal Deformable Convolution (TDC), we only tested under `pytorch<=1.4` and `CUDA=10.1`.
Without TDC, you should be able to choose the latest versions.
If you met some issues with environment, feel free to raise an issue.
```commandline
conda install pytorch=1.4 torchvision cudatoolkit=10.1 -c pytorch # if using TDC
# OR
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch # if not using TDC
```
Install `cruw-devkit` package.
Please refer to [`cruw-devit`](https://github.com/yizhou-wang/cruw-devkit) repository for detailed instructions.
```commandline
git clone https://github.com/yizhou-wang/cruw-devkit.git
cd cruw-devkit
pip install .
cd ..
```
Setup RODNet package.
```commandline
pip install -e .
```
**Note:** If you are not using TDC, you can rename script `setup_wo_tdc.py` as `setup.py`, and run the above command.
This should allow you to use the latest cuda and pytorch version.
## Prepare data for RODNet
Download [ROD2021 dataset](https://www.cruwdataset.org/download#h.mxc4upuvacso).
Follow [this script](https://github.com/yizhou-wang/RODNet/blob/master/tools/prepare_dataset/reorganize_rod2021.sh) to reorganize files as below.
```
data_root
- sequences
| - train
| | - <SEQ_NAME>
| | | - IMAGES_0
| | | | - <FRAME_ID>.jpg
| | | | - ***.jpg
| | | - RADAR_RA_H
| | | - <FRAME_ID>_<CHIRP_ID>.npy
| | | - ***.npy
| | - ***
| |
| - test
| - <SEQ_NAME>
| | - RADAR_RA_H
| | - <FRAME_ID>_<CHIRP_ID>.npy
| | - ***.npy
| - ***
|
- annotations
| - train
| | - <SEQ_NAME>.txt
| | - ***.txt
| - test
| - <SEQ_NAME>.txt
| - ***.txt
- calib
```
Convert data and annotations to `.pkl` files.
```commandline
python tools/prepare_dataset/prepare_data.py \
--config configs/<CONFIG_FILE> \
--data_root <DATASET_ROOT> \
--split train,test \
--out_data_dir data/<DATA_FOLDER_NAME>
```
## Train models
```commandline
python tools/train.py --config configs/<CONFIG_FILE> \
--data_dir data/<DATA_FOLDER_NAME> \
--log_dir checkpoints/
```
## Inference
```commandline
python tools/test.py --config configs/<CONFIG_FILE> \
--data_dir data/<DATA_FOLDER_NAME> \
--checkpoint <CHECKPOINT_PATH> \
--res_dir results/
```
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