The code for "Simple and Effective Approaches for Uncertainty Prediction in Facial Action Unit Intensity Regression" at FG 2020

All building blocks are part of this repository:

• DWAR
• GP-VFE
• MLP ensemble
• Loss Attenuation
• MLP Model for dropout, U-MLP, and the Multi-Task MLP

git clone [email protected]:twoertwein/UncertaintyRegression.git
cd UncertaintyRegression
poetry update
poetry run pip install torchvision --extra-index-url https://download.pytorch.org/whl/cu116

Run the grid-search for a primary model to predict facial action units (AU) intensities. Some primary models can also estimate their uncertainty.

python train.py --method dropout --workers 4 --dataset mnist

Train a secondary model to estimate the uncertainty of the primary dropout model.

python train_secundary.py --uncertainty umlp --workers 4 --dataset mnist