Code for TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources (IJCAI 2022).
- python=3.6.13
- torch=1.9.0+cu111
- numpy=1.19.2
- CityFlow=0.1.0
We made some modifications based on CityFlow v0.1.0 to enrich its APIs. To ensure reproducibility, please install our adapted CityFlow by:
cd CityFlow
pip install .Note: all the following steps are performed in TinyLight folder.
python 01_run_baseline.py --model=FixedTime --dataset=AtlantaThe model will be stored in {log_path}/TinyLight/model/.
python 02_run_tiny_light.py --dataset=AtlantaThis step converts the floating-point operations into integer-only ones. It will generate a series of model files in {log_path}/TinyLightQuan/pc and
{log_path}/TinyLightQuan/mcu, which are used for evaluation in step 4.
python 03_run_tinylight_quan.py --dataset=Atlanta You can run TinyLight on an Arduino Uno (with ATmega328P as the default MCU) by:
- replacing
TinyLight_MCU/model.hwith the corresponding.hfile in{log_path}/TinyLightQuan/mcu, and - running the project in MCU
If you do not have an Arduino board on hand, we also provide an equivalent implementation of TinyLight (w/ PTQ) on computers to verify its performance on traffic. For this, please:
cd {log_path}/TinyLightQuan/mcu/
python setup.py build_ext --inplace
cd {project_dir}
python 04_run_tinylight_mcu.py --dataset=Atlanta If you find our work helpful in your research, please consider citing our paper:
@inproceedings{ijcai2022-tinylight,
title = {TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources},
author = {Xing, Dong and Zheng, Qian and Liu, Qianhui and Pan, Gang},
booktitle = {Proceedings of the Thirty-First International Joint Conference on
Artificial Intelligence, {IJCAI-22}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Lud De Raedt},
pages = {3999--4005},
year = {2022},
month = {7},
note = {Main Track}
doi = {10.24963/ijcai.2022/555},
url = {https://doi.org/10.24963/ijcai.2022/555},
}