Deep Traffic Generation

Description

Package that provides neural networks (mostly autoencoders) to embed and generate traffic trajectories. This project relies on traffic and Pytorch-Lightning libraries.

Installation

# create new python environment for traffic
conda create -n traffic -c conda-forge python=3.9 traffic
conda activate traffic

# clone project   
git clone https://github.com/alafage/deep-traffic-generation

# install project
cd deep-traffic-generation
pip install .

How to run

Navigate to any python file in deep_traffic_generation and run it.

# module folder
cd deep_traffic_generation

# example: run module with default arguments
python linear_ae.py
# example: run module with custom arguments
python linear_ae.py --gpus 1 --early_stop 10 --max_epochs 200 --lr 0.001

You can use Tensorboard to visualize training logs.

tensorboard --logdir lightning_logs

Documentation

Is provided along this project a documentation generated using Sphinx. Here the commands to generate it. Navigate to the docs folder and do:

make html
# or
sphinx-build -b html source build