https://github.com/omerbsezer/MusicGeneration

Music generation with LSTM model (Keras)
https://github.com/omerbsezer/MusicGeneration

deep-learning lstm-neural-networks music-generation

Last synced: about 1 month ago
JSON representation

Music generation with LSTM model (Keras)

• Host: GitHub
• URL: https://github.com/omerbsezer/MusicGeneration
• Owner: omerbsezer
• Archived: true
• Created: 2018-08-12T14:19:19.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2018-08-19T20:32:48.000Z (about 6 years ago)
• Last Synced: 2024-04-06T19:32:19.680Z (5 months ago)
• Topics: deep-learning, lstm-neural-networks, music-generation
• Language: Python
• Homepage:
• Size: 108 KB
• Stars: 3
• Watchers: 3
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Music Generation

With trained DL model (LSTM), new sequences of time series data can be predicted. In this project, it will be implemented a model which inputs a sample jazz music and samples/generates a new music. Code is adapted from Andrew Ng's Course 'Sequential models'.

## Run

* To run code, download music21 toolkit from [http://web.mit.edu/music21/](http://web.mit.edu/music21/). "pip install music21". 

* Run main.py

## Input File and Parameters

Model is trained with "data/original_music"

* "X, Y, n_values, indices_values = load_music_utils()"

* Number of training examples: 60,

* Each of training examples length of sequence:30

* Our music generation system will use 78 unique values. 

* X: This is an (m,  Tx , 78) dimensional array. We have m training examples, each of which is a snippet of  Tx=30Tx=30  musical values. At each time step, the input is one of 78 different possible values, represented as a one-hot vector. Thus for example, X[i,t,:] is a one-hot vector representating the value of the i-th example at time t.

* Y: This is essentially the same as X, but shifted one step to the left (to the past). 

* n_values: The number of unique values in this dataset. This should be 78.

* indices_values: python dictionary mapping from 0-77 to musical values.

## LSTM Model

LSTM model structure is:



Model is implemented with "djmodel(Tx, n_a, n_values)" function.

## Predicting and Sampling

Adding model, predicting and sampling feature, model structure is: 



Music Inference Model is similar trained model and it is implemented with "music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 100)" function. Music is generated with "redict_and_sample" function.

Finally, your generated music is saved in output/my_music.midi.

## References

* Andrew Ng, Sequential Models Course, Deep Learning Specialization