This version of Label-Maker has been modified from the one offered by DevelopmentSeed, in order to support 4-bands (or more) imagery for tiles computation and data preparation.
4 bands satellite images (Near-Infrared + RGB) are nowadays more and more accessible and near-infrared band usually adds valuable information to datasets.
Label Maker downloads OpenStreetMap QA Tile information and satellite imagery tiles and saves them as an .npz
file for use in machine learning training.
satellite imagery from Mapbox and Digital Globe
pip install label-maker
Note that running this library this requires tippecanoe
as a "peer-dependency" and that command should be available from your command-line before running this.
Full documentation is available here: http://devseed.com/label-maker/
This library builds on the concepts of skynet-data. It wouldn't be possible without the excellent data from OpenStreetMap and Mapbox under the following licenses:
- OSM QA tile data copyright OpenStreetMap contributors and licensed under ODbL
- Mapbox Satellite data can be traced for noncommercial purposes.
It also relies heavily on Marc Farra's tilepie to asynchronously process vector tiles