# danieldjohnson/biaxial-rnn-music-composition

A recurrent neural network designed to generate classical music.

Repository: https://github.com/danieldjohnson/biaxial-rnn-music-composition
Canonical: https://ross.abutalabs.com/products/biaxial-rnn-music-composition
Language: Python
License: BSD-2-Clause
License Family: permissive
Last push: 2023-12-12T05:04:29+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4048, "days_push": 995, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1926, forks 371 (observed 2026-08-28T04:05:55.596417+00:00)

## What it is
A Python implementation of a biaxial recurrent neural network (LSTM-based) trained to generate classical music from MIDI data. It includes training and composition-generation code built on Theano.

## Use cases
- generate classical music with a neural network
- train an LSTM on MIDI files to compose music
- produce AI-generated musical compositions
- experiment with recurrent networks for music composition
- sample new pieces from a trained music model

## When to choose
- you want to generate classical-style music from a corpus of MIDI files
- you want a reference implementation of biaxial RNN music composition
- you are studying or extending LSTM-based music generation models

## When to avoid
- you need a maintained, modern deep-learning stack (it depends on the deprecated Theano library)
- you want real-time or production music generation
- you need multi-instrument or non-4/4-time MIDI support out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, deep-learning, media
- platform: python
- tags: music-generation, lstm, rnn, midi, theano, algorithmic-composition, audio, linux, gpu

## Member repositories
- danieldjohnson/biaxial-rnn-music-composition (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.596417+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:09:13.259499+00:00, confidence not recorded.
  - readme: https://github.com/danieldjohnson/biaxial-rnn-music-composition (fetched 2026-08-28T04:05:55.596417+00:00, sha 1a536bc12f47)
- Data as of 2026-08-30T08:39:29.467469+00:00.