search

hajicj / muscima

Tools for working with the MUSCIMA++ dataset of handwritten music notation.
https://muscima.readthedocs.io
MIT License
16 stars 4 forks source link

readme

MUSCIMA

The muscima (Music Score Images) package implements a data model for the MUSCIMA++ dataset of music notation.

Build Status PyPI version Documentation Status License: CC BY-NC-SA 4.0 Coverage Status codecov

This package should work with both Python 2.7 and Python 3.6, although the doctest-based test suite only works on Python 3.

Getting started

  1. Install this package: pip install muscima
  2. Download the MUSCIMA++ dataset.
  3. Run through the tutorial.

Dataset

The dataset itself is available for download here and due to its derived nature, licensed differently:

abc License: CC BY-NC-SA 4.0

MuNG

The mung (Music Notation Graph) package is the successor of this project, updated to accommodate MUSCIMA++ v2.0 and with lots of improvements, such as performance enhancements, a more consistent naming convention, class-names that are close to SMuFL and type hints.

More information can be found here. For future updates and improvements, consider migrating to MuNG.