BatDetect2

Code for detecting and classifying bat echolocation calls in high frequency audio recordings.

Warning

BatDetect2 2.0.1 is out. There are many changes and new recommended workflows. We have left the previous batdetect2.api module intact, but if you run into issues or want to upgrade, see the migration guide in the docs site.

This update also ships with a refreshed default model. It was trained in the same way and on the same data as before, but you should still expect small output differences in some cases.

What BatDetect2 is useful for

BatDetect2 can help you screen recordings for bat calls, find recordings that need expert review, and compare model outputs across sites or projects with appropriate caution.

It is best used as a tool to support ecological work, not as a replacement for validation or expert interpretation.

Start here

If you want the simplest current workflow, use the documentation site and start with:

• getting started: docs/source/getting_started.md
• first tutorial: docs/source/tutorials/run-inference-on-folder.md

If you need the previous workflow based on batdetect2 detect or batdetect2.api, use the legacy docs section and migration guide in the docs site.

Install BatDetect2

If you already use Python, activate the environment where you want BatDetect2 to live.

If not, create a fresh one first so BatDetect2 stays separate from other software on your machine.

Two common options are:

• Install the Anaconda Python 3.10 distribution for your operating system from here. Create a new environment and activate it:

conda create -y --name batdetect2 python==3.10
conda activate batdetect2

• If you already have Python installed (version >= 3.10,< 3.14), you can create a fresh environment with:

python -m venv .venv
source .venv/bin/activate

Installing BatDetect2

You can use pip to install batdetect2:

pip install batdetect2

Alternatively, download this code from the repository (by clicking on the green button on top right) and unzip it. Once unzipped, run this from extracted folder.

pip install .

Make sure you have the environment activated before installing batdetect2.

Run BatDetect2 on a folder of recordings

Once installed, the simplest current workflow is to run BatDetect2 on a folder of .wav files.

If you are working from this repository checkout, you can use this example checkpoint path:

src/batdetect2/models/checkpoints/Net2DFast_UK_same.pth.tar

Example command:

batdetect2 predict directory \
  src/batdetect2/models/checkpoints/Net2DFast_UK_same.pth.tar \
  example_data/audio \
  outputs

This will scan the audio files in example_data/audio and save model outputs to outputs.

For the full beginner walkthrough, use docs/source/tutorials/run-inference-on-folder.md.

Legacy workflow

The sections below are kept only for people maintaining older BatDetect2 scripts and analysis pipelines.

If you are new to BatDetect2, stop here and use the current docs and command above.

If you really do need the older workflow, the reference material is below.

Try the model

1. You can try a demo of the model (for UK species) on huggingface.

2. Alternatively, click here to run the model using Google Colab. You can also run this notebook locally.

Running the model on your own data

After following the above steps to install the code you can run the model on your own data.

The remainder of this section is legacy reference material.

Using the command line

The commands below describe the legacy CLI workflow.

For new work, prefer the current docs and batdetect2 predict.

You can run the model by opening the command line and typing:

batdetect2 detect AUDIO_DIR ANN_DIR DETECTION_THRESHOLD

e.g.

batdetect2 detect example_data/audio/ example_data/anns/ 0.3

AUDIO_DIR is the path on your computer to the audio wav files of interest. ANN_DIR is the path on your computer where the model predictions will be saved. The model will output both .csv and .json results for each audio file. DETECTION_THRESHOLD is a number between 0 and 1 specifying the cut-off threshold applied to the calls. A smaller number will result in more calls detected, but with the chance of introducing more mistakes.

There are also optional arguments, e.g. you can request that the model outputs features (i.e. estimated call parameters) such as duration, max_frequency, etc. by setting the flag --spec_features. These will be saved as *_spec_features.csv files: batdetect2 detect example_data/audio/ example_data/anns/ 0.3 --spec_features

You can also specify which model to use by setting the --model_path argument. If not specified, it will default to using a model trained on UK data e.g. batdetect2 detect example_data/audio/ example_data/anns/ 0.3 --model_path models/Net2DFast_UK_same.pth.tar

Using the Python API

The examples below describe the legacy Python API.

For new work, prefer batdetect2.api_v2.BatDetect2API and the current docs site.

If you prefer to process your data within a Python script then you can use the batdetect2 Python API.

from batdetect2 import api

AUDIO_FILE = "example_data/audio/20170701_213954-MYOMYS-LR_0_0.5.wav"

# Process a whole file
results = api.process_file(AUDIO_FILE)

# Or, load audio and compute spectrograms
audio = api.load_audio(AUDIO_FILE)
spec = api.generate_spectrogram(audio)

# And process the audio or the spectrogram with the model
detections, features, spec = api.process_audio(audio)
detections, features = api.process_spectrogram(spec)

# Do something else ...

You can integrate the detections or the extracted features to your custom analysis pipeline.

Training the model on your own data

Take a look at the training tutorial in the docs site first.

If you are working from this repository checkout, start with docs/source/tutorials/train-a-custom-model.md.

Data and annotations

The raw audio data and annotations used to train the models in the paper will be added soon. The audio interface used to annotate audio data for training and evaluation is available here.

Warning

The models developed and shared as part of this repository should be used with caution. While they have been evaluated on held out audio data, great care should be taken when using the model outputs for any form of biodiversity assessment. Your data may differ, and as a result it is very strongly recommended that you validate the model first using data with known species to ensure that the outputs can be trusted.

FAQ

For more information please consult our FAQ.

Reference

If you find our work useful in your research please consider citing our paper which you can find here:

@article{batdetect2_2022,
    title     = {Towards a General Approach for Bat Echolocation Detection and Classification},
    author    = {Mac Aodha, Oisin and  Mart\'{i}nez Balvanera, Santiago and  Damstra, Elise and  Cooke, Martyn and  Eichinski, Philip and  Browning, Ella and  Barataudm, Michel and  Boughey, Katherine and  Coles, Roger and  Giacomini, Giada and MacSwiney G., M. Cristina and  K. Obrist, Martin and Parsons, Stuart and  Sattler, Thomas and  Jones, Kate E.},
    journal   = {bioRxiv},
    year      = {2022}
}

Acknowledgements

Thanks to all the contributors who spent time collecting and annotating audio data.