msaf
msaf copied to clipboard
Music Structure Analysis Framework
The Numpy [API documentation](https://numpy.org/doc/stable/reference/generated/numpy.linalg.multi_dot.html) recommends using `np.linalg.multi_dot` instead of multiple `np.dot` calls since it is more succinct and effective. This PR is to make the required changes.
Bumps [numpy](https://github.com/numpy/numpy) from 1.14.5 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
Hello, I try to run run_msaf.py, but an error occured, here is the traceback information: ModuleNotFoundError: No module named 'numpy.core._multiarray_umath' Traceback (most recent call last): File "run_msaf.py", line 12, in...
I know maybe the new architecture is not supported. but would be cool to support arm64 processors. Thank you :)
It appears that this is a compatibility issue with SciPy 1.3 where the 'factorial' has been moved to 'scipy.special'. Is there a new release coming up? The following is the...
I installed MSAF to Python 3.6 in the cmd in Windows 10. `pip3.6 install msaf` It installed properly, and shows up when I type help("modules") in Python 3.6. The folders...
Then boundaries_id = 'gt' the boundaries are converted first to frame indices [here](https://github.com/urinieto/msaf/blob/master/msaf/run.py#L144). Then once the labeling algorithm outputs the results [this line](https://github.com/urinieto/msaf/blob/master/msaf/run.py#L163) recomputes the boundaries from the frame indices,...
In the run.py: process(in_path, annot_beats=False, feature="pcp", framesync=False, boundaries_id=msaf.config.default_bound_id, labels_id=msaf.config.default_label_id, hier=False, sonify_bounds=False, plot=False, n_jobs=4, **annotator_id=0**, config=None, out_bounds="out_bounds.wav", out_sr=22050): but ``` if plot=True: plotting.plot_one_track(file_struct, est_times, est_labels, boundaries_id, labels_id) ``` I noticed it...
After running the current version of MSAF with the following recommended parameters, the HitRate_t3F of the Structural Features algorithm on the BeatlesTUT dataset only obtains approximately 0.57. The published [msaf-experiments](https://github.com/urinieto/msaf-experiments)...
When I can msaf.process function, if I have already load the music using librosa.load, can I use that directly? Also how to use annot_beats and framesync parameter?