https://github.com/developmentseed/label-maker

Data Preparation for Satellite Machine Learning
https://github.com/developmentseed/label-maker

computer-vision data-preparation deep-learning keras remote-sensing satellite-imagery

Last synced: about 2 months ago
JSON representation

Data Preparation for Satellite Machine Learning

• Host: GitHub
• URL: https://github.com/developmentseed/label-maker
• Owner: developmentseed
• License: mit
• Created: 2018-01-10T19:21:31.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-10-03T21:56:39.000Z (9 months ago)
• Last Synced: 2024-05-07T06:02:01.672Z (2 months ago)
• Topics: computer-vision, data-preparation, deep-learning, keras, remote-sensing, satellite-imagery
• Language: Python
• Homepage: http://devseed.com/label-maker/
• Size: 18.8 MB
• Stars: 454
• Watchers: 53
• Forks: 111
• Open Issues: 39
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: docs/contributing.rst
  • License: LICENSE.txt

Lists

• Awesome-Geospatial - Label Maker - Data Preparation for Satellite Machine Learning. (Deep Learning)
• awesome-stars - developmentseed/label-maker - Data Preparation for Satellite Machine Learning (Python)
• awesome-gis - label-maker - Data Preparation for Satellite Machine Learning. (Deep Learning / Deep Learning Framework for Geospatial)
• my-awesome-stars - developmentseed/label-maker - Data Preparation for Satellite Machine Learning (Python)
• awesome-python-data-science - label-maker - Data Preparation for Satellite Machine Learning. (Feature Extraction / Images and Video)
• awesome-gis - label-maker - Data Preparation for Satellite Machine Learning. (Deep Learning / Deep Learning Framework for Geospatial)
• awesome-stars - developmentseed/label-maker - Data Preparation for Satellite Machine Learning (Python)

README

        
# Label Maker

## Data Preparation for Satellite Machine Learning

Label Maker downloads [OpenStreetMap QA Tile]((https://osmlab.github.io/osm-qa-tiles/)) information and satellite imagery tiles and saves them as an [`.npz` file](https://docs.scipy.org/doc/numpy/reference/generated/numpy.savez.html) for use in machine learning training.

![example classification image overlaid over satellite imagery](examples/images/classification.png)

_satellite imagery from [Mapbox](https://www.mapbox.com/) and [Digital Globe](https://www.digitalglobe.com/)_

## Requirements

- [Python 3.6](https://www.python.org/)

- [tippecanoe](https://github.com/mapbox/tippecanoe)

## Installation

```bash

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.

## Documentation

Full documentation is available here: http://devseed.com/label-maker/

## Acknowledgements

This library builds on the concepts of [skynet-data](https://github.com/developmentseed/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](http://www.openstreetmap.org/copyright) and licensed under [ODbL](http://opendatacommons.org/licenses/odbl/)

- Mapbox Satellite data can be [traced for noncommercial purposes](https://www.mapbox.com/tos/#[YmtMIywt]).

It also relies heavily on Marc Farra's [tilepie](https://github.com/kamicut/tilepie) to asynchronously process vector tiles