Bird song classification
Table of contents
To use the repository, you will need to add images dataset (in DCOM or PNG format) in a folder kaggle_dataset
at the root of the project.
We advise you to use the docker configuration, but if one prefers to work without it, you will need to install requirements with pip3 install -r requirements.txt
.
Be carefull, the repository is built to give the possibility to use a GPU. If you don't have a GPU on your computer, please comment lines below deploy in the docker-compose file or it won't work.
Build the container
docker-compose build
Up containers
docker-compose up -d
Stop containers
docker-compose stop
Open a shell inside the main container
docker-compose exec bird_song sh
Run jupyter lab from the container
jupyter lab --ip 0.0.0.0 --allow-root
If some issues with jupyter lab or port already on used on 8888
lsof -i :8888
>kill -9 <PID>
With PID being the process ID of python (for notebook)