Framework for uncertainty-based neural networks and active learning.
conda create -n dal-toolbox python=3.9
pip install -e .
To start developing it is best to use:
conda create -n dal-toolbox python=3.9
pip install -e .
All experiments are stored in the experiments folder.
We provide notebooks that give examples of how to work with this repository.
Examples of how to train models with improved uncertainty estimation:
Examples of how to train models with semi-supervised learning algorithms:
Examples of how to implement an active learning cycle: