Stefan Kahl
Stefan Kahl
Thanks. To be honest, I personally don't like to put virtual environments in the readme, because it complicates things and doesn't look as clean as without. I understand the motivation,...
Whoa...there's a LOT to digest :) Thanks for all the work you put into it, we'll take a look.
I'd say we assign these to the segment with the most overlap (in your case 3-6). Since the annotation is so short, we can still assume that a significant percentage...
The actual spectrogram computation is part of the model and not exposed in the code that runs the model. So, it's going to be tricky to manipulate the parameters. There...
In case of our model, one thing you could try is to use the audio speed parameter and actually speed up your recordings when training a custom classifier, which would...
I can access box through Cornell, but the link seems to be expired.
@Josef-Haupt could be a different cut-off threshold for the geomodel for single file analysis. @42DillEP could you share the file so we can investigate? Thanks!
Moved to docs.
Also, I think we should use the common name instead of the species code for segments folder names: `species = d[header_mapping["Species Code"]]` should be `species = d[header_mapping["Common Name"]]` when `rtype...
Thanks for posting, Sharon. I downloaded the data from your example and ran the training with default settings and (on Windows with GUI 1.3.0) everything seems to work fine. ...