Fabian-Robert Stöter
Fabian-Robert Stöter
Inside of museval the reference and estimate have 3 dimensions since it stacks all estimates for one track. You can't run museval with a single source estimate. You need at...
@aystiro can this be closed?
Hi, and thanks again for this initiative. Since I just released a new stable version of museval a few days ago, the next step is now to remove the bsseval...
This should be addressed after #1
I remember we did this on purpose, but can't remember why we did that. Maybe @aliutkus can jump in here?
@Jonathan-LeRoux would you be able to contribute Python code or could actively do a code review if we'd need to figure out the code from the paper ourself?
thanks. Thats impressively simple. Will add this as soon as the refactoring is done
when you call `museval` from the cli you are running the `eval_dir` function. What you want instead is to use the SiSEC MUS task-like scenario functions `eval_mus_track` or `eval_mus_dir` which...
maybe a `overwrite` flag would be simpler to understand, so that when `overwrite=False`, existing tracks are just skipped. Also, we know that v4 needs way more memory than v3, so...
@sevagh i think this would be great. Do the regression tests pass using this?