Skip to main content

A generator of midi score based on GRU.

Project description

Miding 3.2.1

This program names 'miding', an abbreviation of 'Midi Neuronal Generator', which 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, the model construction is two GRU layer and a Dense layer with the activation Softmax.

Download

Here is our website:

This package could also be downloaded through PyPi by:

pip install miding

View at the webpage

How to use the model?

First, COPY the model files (*.keras) from our package to your programme path by calling 'resources.check()' after importing the package, which is extremely important!

from miding import Predict, Seed, resources resources.check(resources.absolute_path(__file__))

And then, for example, you could use a random seed:

s = Seed(midi_file='example_seed.mid') Predict(seed=s.get_seed(),epoch=128, 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-3.2.1.tar.gz (95.6 kB view details)

Uploaded Source

Built Distribution

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

miding-3.2.1-py3-none-any.whl (94.0 kB view details)

Uploaded Python 3

File details

Details for the file miding-3.2.1.tar.gz.

File metadata

  • Download URL: miding-3.2.1.tar.gz
  • Upload date:
  • Size: 95.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for miding-3.2.1.tar.gz
Algorithm Hash digest
SHA256 4b7de079425f3a9648d4ef191ab2d8cd36b0d027d2cdeb93488101f158a9f919
MD5 5561579d00c04abc876fbd50178514c9
BLAKE2b-256 4aa9e3b1e4be0da1d00ac1b96e5ee06534fa3d596f63a755175a795fa97cd633

See more details on using hashes here.

File details

Details for the file miding-3.2.1-py3-none-any.whl.

File metadata

  • Download URL: miding-3.2.1-py3-none-any.whl
  • Upload date:
  • Size: 94.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for miding-3.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7971efac7a67042256c994b331a723257d9fcb09e2f3c147ed29dcbfc1bbff2b
MD5 c7773c5397dd5a6f38cc170c076f806f
BLAKE2b-256 54d59e1cf7a410c1e0a860a0a0e9a7b9cdcde4dd985b618363ffe2f3eb70d9e7

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