Skip to content

Installation

The installation process may take roughly ten minutes because BirdBox relies on large deep learning libraries such as PyTorch and Ultralytics.

Prerequisites

  • Python 3.12 has to be installed in advance
  • ~4 GB disk space for dependencies (PyTorch, Ultralytics and CUDA binaries)
  • CUDA-capable GPU for accelerated model inference
  • a non-CUDA setup is also possible, but model inference will take significantly longer
  • the installation script will automatically detect GPU/CPU/Mac environments and install the appropriate dependencies and CUDA binaries

Installation Scripts

Simply copy the script below that matches your operating system. All scripts will create a new virtual environment and install the dependencies into it via install.py. Alternatively, you can also run install.py inside a conda environment.

Select the tab below that matches your operating system.

# 1. Clone the repository
git clone https://github.com/birdnet-team/BirdBox.git
cd BirdBox

# 2. Create a virtual environment
python -m venv .venv

# 3. Activate the environment
source .venv/bin/activate

# 4. Install dependencies
python install.py

# 1. Clone the repository
git clone https://github.com/birdnet-team/BirdBox.git
cd BirdBox

# 2. Create a virtual environment
python -m venv .venv

# 3. Activate the environment
.venv\Scripts\Activate.ps1

# 4. Install dependencies
python install.py

rem 1. Clone the repository
git clone https://github.com/birdnet-team/BirdBox.git
cd BirdBox

rem 2. Create a virtual environment
python -m venv .venv

rem 3. Activate the environment
.venv\Scripts\activate.bat

rem 4. Install dependencies
python install.py

Model Download

The YOLO-models are not included in the BirdBox GitHub-Repository. This yields the advantage that only the required models have to be downloaded.

Recommended: Once downloaded, store the model files in your own local models/ directory.

TUC-Cloud

Trained YOLO-Models for this task can be found on the TUC-Cloud. For more details see Models and Metrics.

Custom Model Training

Alternatively, you can train your own model on a custom dataset by using the code available in the BirdBox-Train repository.

Restricted Access

BirdBox-Train is currently only available to members of the BirdNET Team.