dtch1997/open-neural-car

Open-source code to train a neural network to emulate a MPC controller for a Reed-Shepp car

Neural Car

Description

Train a neural net agent to mimic a SCP agent for navigating a Reed-Shepp car

How to run

Install dependencies

# clone project
git clone https://github.com/dtch1997/open-neural-car
cd open-neural-car

# create conda environment
# this step is interactive
source bash/setup_conda.sh

# activate conda env you just created

# install requirements
pip install -r requirements.txt
pre-commit install

Generate data for model training

python run.py --config-name datagen_config.yaml

Train model with default configuration

# default
python run.py

# train on CPU
python run.py trainer.gpus=0

# train on GPU
python run.py trainer.gpus=1

Train model with chosen experiment configuration from configs/experiment/

# python run.py experiment=experiment_name

You can override any parameter from command line like this

python run.py trainer.max_epochs=20 datamodule.batch_size=64