georgid / ENST-drums-dataset

the dataset used in the paper https://drive.google.com/file/d/0B4bIMgQlCAuqdGVRbVNNbzJfeUU/view

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

all prepared files are in dir 
accompaniment_all_drummers_all_meters

script how to prepare these two dirs are in accompaniment_all_drummers. 
As well drum preparation is described in script /Users/joro/Documents/Linz/drumsbBarModel/BarModelMidiBarPositions/train/traindoit.m



and dir
accompaniment_all_drummers is the dir with 4/4/ meters only
it is same as the one up, but manually only 4/4 meters are taken. no script


Doing cross validation: 

- copy all from accompaniment_all_drummers to train dir
- cd to test dir
- manually mv each piece (in table in report) from train to test dir :   
 mv <name>* ../accompaniment_all_drummers_test_2fold/

About

the dataset used in the paper https://drive.google.com/file/d/0B4bIMgQlCAuqdGVRbVNNbzJfeUU/view


Languages

Language:Shell 100.0%