This repository contains PyTorch training code for Verti-Wheelers.
Main libraries:
- PyTorch: as the main ML framework
- Comet.ml: tracking code, logging experiments
- OmegaConf: for managing configuration files
First create a virtual env for the project.
python3 -m venv .venv
source .venv/bin/activate
Then install the latest version of PyTorch from the official site. Finally, run the following:
pip install -r requirements
To set up Comet.Ml follow the official documentations.
To download the dataset please follow the instructions here.
To run parser, first edit the config file in conf/parser_config
directory. Then run:
./run.sh parse
To run the training pipeline, make sure everything in the config file is correct, then run:
./run.sh train
To deploy the trained model, please follow the instructions here.
If you find this repo to be helpful, please consider citing our work:
@article{datar2023a,
title={Toward Wheeled Mobility on Vertically Challenging Terrain: Platforms, Datasets, and Algorithms},
author={Datar, Aniket and Pan, Chenhui and Nazeri, Mohammad and Xiao, Xuesu},
journal={arXiv preprint arXiv:2303.00998},
year={2023}
}