Skip to content
Devkit for the public 2019 Lyft Level 5 AV Dataset (fork of
Python Jupyter Notebook
Branch: master
Clone or download

NuScenes Devkit - Lyft Level 5 AV Fork

Welcome to the devkit for the Lyft Level 5 AV dataset! This devkit shall help you to visualise and explore our dataset.

Release Notes

This devkit is a slightly modified version of the nuScenes devkit. We added the following features:

  • support for coloured rasterised maps (instead of just binary masks)
  • render vehicle-centered top-down views with map in the background

Some files from the original distribution which aren't directly related to the devkit are not part of this repository.

Getting Started

Devkit Setup

If you have a Python >=3.6 environment set up and Pip installed, you can simply run

pip install -r setup/requirements.txt

to install the required packages. Then you're set up to use the devkit.

For more detailed installation instructions, see ./setup/

Dataset Download

Go to to download the Lyft Level 5 AV Dataset.


To get started with the nuScenes devkit, run the tutorial using Jupyter Notebook:

jupyter notebook python-sdk/tutorial_lyft.ipynb

You can’t perform that action at this time.