2019-05-29 10:50:00 +02:00
|
|
|
## MUSIC GENERATION USING DEEP LEARNING ##
|
|
|
|
|
## AUTHOR: CEZARY PUKOWNIK
|
|
|
|
|
|
2019-05-30 11:23:34 +02:00
|
|
|
files:
|
|
|
|
|
- midi.py - code for data extraction, and midi convertion
|
|
|
|
|
- train.py - code for model definition, and training session
|
|
|
|
|
- generate.py - code for model loading, predicting ang saving to midi_dir
|
|
|
|
|
- settings.py - file where deafult settings are stored
|
|
|
|
|
- readme - this file
|
|
|
|
|
- data/midi - directory where input midi are stored
|
|
|
|
|
- data/models - directory where trained models are stored
|
|
|
|
|
- data/output - directory where generated music is stored
|
|
|
|
|
- data/samples - directory where extracted data from midi is stored
|
|
|
|
|
- data/samples.npz - deprecated
|
|
|
|
|
|
2019-05-29 10:50:00 +02:00
|
|
|
How to use:
|
|
|
|
|
|
|
|
|
|
1. Use midi.py to export data from midi files
|
|
|
|
|
|
2019-05-30 11:23:34 +02:00
|
|
|
./midi.py <midi_folder_path> <output_path>
|
2019-05-29 10:50:00 +02:00
|
|
|
|
|
|
|
|
2. Use train.py to train a model (this can take a while)
|
|
|
|
|
|
2019-05-30 11:23:34 +02:00
|
|
|
./train.py <input_training_data> <model_save_path> <epochs>
|
2019-05-29 10:50:00 +02:00
|
|
|
|
|
|
|
|
3. Use generate.py to generate music from trained models
|
|
|
|
|
|
2019-05-30 11:23:34 +02:00
|
|
|
./generate.py <trained_model_path> <output_path> <treshold>
|
