First of all, clone the code:
git clone https://github.com/xinshuoweng/AB3DMOT.git
This code has only been tested on the following combination of major pre-requisites. Please check beforehand.
- Ubuntu 18.04
- Python 3.6
To run the code on the supported datasets, please follow instructions here.
This code requires the following packages:
- scikit-learn==0.19.2
- filterpy==1.4.5
- numba==0.43.1
- matplotlib==2.2.3
- pillow==6.2.2
- opencv-python==4.2.0.32
- glob2==0.6
- PyYAML==5.4
- easydict==1.9
- llvmlite==0.32.1
- nuscenes-devkit==1.1.9
- motmetrics<=1.1.3
- pandas>=0.24
One can either use the system python or create a virtual enviroment (venv for python3) specifically for this project (https://www.pythonforbeginners.com/basics/how-to-use-python-virtualenv). To install required dependencies on the system python, please run the following command at the root of this code:
$ cd path/to/AB3DMOT
$ pip3 install -r requirements.txt
To install required dependencies on the virtual environment of the python, please run the following command at the root of this code:
$ pip3 install venv
$ python3 -m venv env
$ source env/bin/activate
$ pip3 install -r requirements.txt
Additionally, this code depends on my personal toolbox: https://github.com/xinshuoweng/Xinshuo_PyToolbox. Please install the toolbox by:
1. Clone the github repository.
git clone https://github.com/xinshuoweng/Xinshuo_PyToolbox
2. Install dependency for the toolbox.
cd Xinshuo_PyToolbox
pip3 install -r requirements.txt
cd ..
Please add the path to the code to your PYTHONPATH in order to load the library appropriately. For example, if the code is located at /home/user/workspace/code/AB3DMOT, please add the following to your ~/.profile:
$ export PYTHONPATH=${PYTHONPATH}:/home/user/workspace/code/AB3DMOT
$ export PYTHONPATH=${PYTHONPATH}:/home/user/workspace/code/AB3DMOT/Xinshuo_PyToolbox
Then update your configuration with
$ source ~/.profile
$ cd path/to/AB3DMOT
$ source env/bin/activate
You are now done with the installation!