Tim Sainburg

Hey - I just wanted to check in again on this now that you've released KS4.

All good! Thanks for the quick reply. Closing this unless you have a suggestion for a merging tool you like/reccomend.

I ran into this error as well, using SpikeInterface with Kilosort2 on a 32 channel ~24hr recording with a Titan XP. No issues with the 12hr recording. I'll probably break...

Good catch. Can you see if this works for you: https://github.com/timsainb/noisereduce/tree/patch-torch-dependency

I think that would be a great addition.

hey @leriomaggio . Is this still something you're thinking about? I've been playing around with pytorch and I'm sold on it's advantages over tensorflow. It seems like it might be...

Sounds great. I'm trying to tie up my thesis at the moment so I relate to juggling a whole lot of things at once. > I am happy that you...

Hi @robert-lieck. I'm still trying to get my thesis finished and don't personally have the time to work on this. Very interested in seeing a torch implementation happen though! For...

Awesome to see someone working on this. I've just looked briefly, but it looks like the `convert_distance_to_probability` differs from the original?

I fixed the probability computation and it looks much better now: https://colab.research.google.com/drive/1CYxt0GD-Y2zPMOnJIXJWsAhr0LdqI0R6?usp=sharing  I'm not sure why the loss converges at 0.2 instead of 0.1, it might require some additional...