You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I saw that the BirdNET team is working on their own Python library for BirdNET. It doesn't provide as much functionality as birdnetlib, and it will probably stay that way.
However, their library supports Protobuf models and GPU inference. From my understanding of the birdnetlib code, neither are supported at the moment. I think it would be nice to have this functionality, and it seems from the birdnet code that it wouldn't be overly complex (I could very well be wrong!).
I'm curious - are there specific reasons this hasn't been implemented yet? Would it make sense to add these features, or are there technical hurdles that make it difficult, or is it more of a question of priorities? If anyone has thoughts on this, or would be interested in collaborating on it, I'd be happy to discuss it further. I understand that everyone here is contributing their time and effort generously, and I really appreciate all the hard work that's gone into the project so far.
Cheers,
Jaro
The text was updated successfully, but these errors were encountered:
Would it make sense to add these features, or are there technical hurdles that make it difficult, or is it more of a question of priorities?
It's 100% a question of priorities and available time.
I'd love to have this functionality in birdnetlib.
I've been considering switching to use the official BirdNET library behind the scenes, and keeping the api of birdnetlib intact/backwards compatible. Now that the BirdNET project has committed to maintaining their own official python library, I'm inclined to use their library as a dependency within birdnetlib. I would like to stay clear of duplicative efforts as much as possible.
Thanks for your quick response.
Unfortunately, I'm no programmer, more of a user... so not sure I can be of any help (I'm currently struggling to get tensorflow with GPU support running...).
Avoiding duplicate efforts is certainly a good idea, and since they want to keep the official BirdNET library rather minimal, it sure seems like a smart idea to have it as a dependency.
Hi there!
I saw that the BirdNET team is working on their own Python library for BirdNET. It doesn't provide as much functionality as birdnetlib, and it will probably stay that way.
However, their library supports Protobuf models and GPU inference. From my understanding of the birdnetlib code, neither are supported at the moment. I think it would be nice to have this functionality, and it seems from the birdnet code that it wouldn't be overly complex (I could very well be wrong!).
I'm curious - are there specific reasons this hasn't been implemented yet? Would it make sense to add these features, or are there technical hurdles that make it difficult, or is it more of a question of priorities? If anyone has thoughts on this, or would be interested in collaborating on it, I'd be happy to discuss it further. I understand that everyone here is contributing their time and effort generously, and I really appreciate all the hard work that's gone into the project so far.
Cheers,
Jaro
The text was updated successfully, but these errors were encountered: