Repository with several machine learning models to detect species on audio data using the AnuraSet. Models experiments include CNN from scratch, classic classifiers as linear and ensemble models using audio features and wavelets, and CCN pre-trained. We also frame the problem as binary and multi-class.
-
Install Conda
-
Create environment and install requirements
conda create -n chorus_env python=3.8 -y
conda activate chorus_env
pip install -r requirements.txt- Download the AnuraSet
The authors acknowledge financial support from the intergovernmental Group on Earth Observations (GEO) and Microsoft, under the GEO-Microsoft Planetary Computer Programme (October 2021).
- Juan Sebastián Ulloa ([email protected], juansulloa)
- Juan Sebastián Cañas ([email protected], jscanass)