view testdata/evaluation/README @ 338:8a2166088b94 livemode

Initialise pitch and shift vectors to 1.0 instead of randomly -- seems to produce at least no worse results, and has the advantage of producing deterministic output
author Chris Cannam
date Mon, 29 Jun 2015 16:22:32 +0100
parents 1b7b31aab82a
children
line wrap: on
line source

 * run.sh is our basic Silvet evaluation script. It runs Silvet
against single- and multiple-instrument files from the TRIOS dataset
using the theoretically best settings for each file, and then
evaluates the results against the ground truth and MIREX 2012
submission.

 * batchProcessingEvaluate.m evaluates a set of .lab output files
against MIDI.  The MIDI can be found in ../TRIOS-groundtruth, and some
example .lab files in ../TRIOS-mirex2012-matlab and ../TRIOS-silvet.

 * evaluate_lab.yeti evaluates one lab file against another, onsets
only, to a given timing tolerance.