Closed jmbarr closed 1 year ago
Patch coverage: 95.71
% and project coverage change: -0.02
:warning:
Comparison is base (
78c88a4
) 94.90% compared to head (7c44dc2
) 94.89%.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.
Here are some cprofile files that may help to optimise this. ek_stats.txt skf_stats.txt
A Schmidt-Kalman version of the Kalman Updater. See the docs for how it works. A Gist is provided here: https://gist.github.com/jmbarr/fd76bc5e7e8eeb47122a023287de3e25. Trouble is, it doesn't seem to improve run time much. Which might be testament to how well Python does matrix arithmetic vs matrix assignment or, more likely, because I don't know how to optimise matrix assignment. Suggestions on this part welcome; the place to look is in the
posterior_covariance
method in the new class.