Skip to main content

A generator of midi score based on GRU.

Project description

Midi Neuronal Generator (miding)

This program aims to generate listenable midi sequences, attempting to create fair scores.

Sincerely thanks for keras, the neuronal network model we have applied. In this program, we have combined a LSTM layer, a Dense layer with the activation Sigmoid and an Activation of Softmax layer before v3.0. And after v3.1, the construction has been changed into two GRU layer and a Dense layer with the activation Softmax, due to GRU has a faster processing speed than LSTM.

Download

Here is our website: https://github.com/JerrySkywolf/Midi-Neuronal-Generator. This package could also be downloaded through PyPi by:

pip install miding

View at the webpage

How to use our model?

For example,

from miding import Predict, get_seed

Predict(seed=get_seed(), epoch=256, model_version=1751770203)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

miding-3.1.2.tar.gz (91.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

miding-3.1.2-py3-none-any.whl (14.3 kB view details)

Uploaded Python 3

File details

Details for the file miding-3.1.2.tar.gz.

File metadata

  • Download URL: miding-3.1.2.tar.gz
  • Upload date:
  • Size: 91.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.5

File hashes

Hashes for miding-3.1.2.tar.gz
Algorithm Hash digest
SHA256 8eb2172fcd233b5a97c71749b57496cbb12593e587fb2511087e5e95bf8aedf4
MD5 3ec5d28a427af6a67ed2c061d14d7d49
BLAKE2b-256 a2d4942a0b2ca106cbd25b3b3638d245dbef68dc386af0396ad8af3a8760a5ea

See more details on using hashes here.

File details

Details for the file miding-3.1.2-py3-none-any.whl.

File metadata

  • Download URL: miding-3.1.2-py3-none-any.whl
  • Upload date:
  • Size: 14.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.5

File hashes

Hashes for miding-3.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 0bf726d6eb7e6eb9b25a8971eba8cb57c04b59eee832c72c81bde5379f6d9765
MD5 def23bd941e57c6502e0d2fe05cd8533
BLAKE2b-256 e3d90d95774b3f8e3b0fbda3853c8c995b2cf343d8eaf83f10ce7c6db436bf79

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page