Need help with BatchBALD?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

BlackHC
152 Stars 41 Forks GNU General Public License v3.0 7 Commits 1 Opened issues

Description

Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.

Services available

!
?

Need anything else?

Contributors list

# 91,726
Dart
HTML
dart-we...
Angular
5 commits

BatchBALD

This is the code drop for our paper BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.

The code comes as is.

See https://github.com/BlackHC/batchbaldredux and https://blackhc.github.io/batchbaldredux/ for a reimplementation.

ElementAI's Baal framework also supports BatchBALD: https://github.com/ElementAI/baal/.

Please cite us:

@misc{kirsch2019batchbald,
    title={BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning},
    author={Andreas Kirsch and Joost van Amersfoort and Yarin Gal},
    year={2019},
    eprint={1906.08158},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

How to run it

Make sure you install all requirements using

conda install pytorch torchvision cudatoolkit=10.0 -c pytorch
pip install -r requirements.txt

and you can start an experiment using:

python src/run_experiment.py --quickquick --num_inference_samples 10 --available_sample_k 40

which starts an experiment on a subset of MNIST with 10 MC dropout samples and acquisition size 40.

Have fun playing around with it!

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.