Parts of the code for the callbird project (and changes to the BirdSet code in this repository) were generated by CoPilot. All generated code was reviewed and changed if needed.
This project addresses the challenge of call type classification, for the ”DeepBirdDetect” project aimed at harmonizing wind power expansion with avian conservation. We aim to evaluate how Multi-Task Learning compares to single task models.
The simplest way to install
You can also use the devcontainer configured as as git submodule:
git submodule update --init --recursiveAnd install python dependencies with poetry.
poetry install
eval $(poetry env activate)
Our experiments are defined in the projects/callbird/configs/experiment/ folder. To run an experiment, use the following command in the directory of the repository:
./projects/callbird/train.sh experiment="EXPERIMENT_PATH"E.g.
./projects/callbird/train.sh experiment=resnet_esc50 This repository is a fork of BirdSet. All project related changes are made in the projects/callbird folder. If you want to change or fixed a bug in the original code, please make a pull request to the original repository. You can use all configurations and scripts from the original repository. If you want to override the configurations add a file with the appropriate path in the projects/callbird/configs/ folder. Python code can be added in the projects/callbird/src folder use the same folder structure as in /birdset.