search

fakufaku / torchiva

Blind source separation with independent vector analysis family of algorithm in torch
https://torchiva.readthedocs.io/en/latest/
MIT License
86 stars 5 forks source link

Separation command #3

Closed fakufaku closed 1 year ago

fakufaku commented 1 year ago

Adds a separate command as part of the package that can be used to run separation on multichannel files.

python -m torchiva.separate <input> <output> --model-type nn
codecov[bot] commented 1 year ago

Codecov Report

Merging #3 (679cded) into master (ba54a38) will increase coverage by 19.38%. The diff coverage is 75.00%.

:exclamation: Current head 679cded differs from pull request most recent head 68a23db. Consider uploading reports for the commit 68a23db to get more accurate results

@@             Coverage Diff             @@
##           master       #3       +/-   ##
===========================================
+ Coverage   55.20%   74.59%   +19.38%     
===========================================
  Files          24       24               
  Lines        1478     1464       -14     
  Branches      140      159       +19     
===========================================
+ Hits          816     1092      +276     
+ Misses        631      307      -324     
- Partials       31       65       +34
Impacted Files Coverage Δ
torchiva/utils.py 54.54% <ø> (+39.16%) :arrow_up:
torchiva/separate.py 68.22% <68.22%> (ø)
torchiva/loader.py 85.71% <81.81%> (+39.56%) :arrow_up:
torchiva/__init__.py 100.00% <100.00%> (ø)
torchiva/auxiva_ip2.py 89.09% <100.00%> (ø)
torchiva/fftconvolve.py 66.66% <100.00%> (+60.60%) :arrow_up:
torchiva/linalg.py 89.11% <100.00%> (+45.43%) :arrow_up:
torchiva/models/classic.py 91.95% <0.00%> (+5.74%) :arrow_up:
... and 5 more

:mega: We’re building smart automated test selection to slash your CI/CD build times. Learn more