Metadata-Version: 2.4
Name: miding
Version: 3.1.8
Summary: A generator of midi score based on GRU.
Author-email: Jerry_Skywolf <jerryskywolf@outlook.com>
License-Expression: GPL-3.0
Project-URL: Homepage, https://github.com/JerrySkywolf/miding
Project-URL: Issues, https://github.com/JerrySkywolf/miding/issues
Project-URL: DOWNLOAD, https://github.com/JerrySkywolf/miding/releases
Keywords: midi,miding,neuronal,generate,music,Jerry Skywolf
Classifier: Programming Language :: Python :: 3.11
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 4 - Beta
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: keras
Requires-Dist: mido
Requires-Dist: numpy
Requires-Dist: tensorflow
Dynamic: license-file

# Miding

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:
* https://github.com/JerrySkywolf/miding

This package could also be downloaded through PyPi by:

`pip install miding`

View at the webpage
* https://pypi.org/project/miding

### How to use the model?

First, **COPY** the model files (*.keras) in the package path to your programme directory before call Predict!

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

``from miding import Predict, Seed``

``s = Seed(midi_file='example_seed.mid')``

``Predict(seed=s.get_seed(),epoch=128, model_version=1751770203)``



 
