My-implementation-of-What-Uncertainties-Do-We-Need-in-Bayesian-Deep-Learning-for-Computer-Vision icon indicating copy to clipboard operation
My-implementation-of-What-Uncertainties-Do-We-Need-in-Bayesian-Deep-Learning-for-Computer-Vision copied to clipboard

Pytorch implementation of classification task in What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision (simple version)

Results 3 My-implementation-of-What-Uncertainties-Do-We-Need-in-Bayesian-Deep-Learning-for-Computer-Vision issues
Sort by recently updated
recently updated
newest added

How to get a proper measure of the aleatoric uncertainty in the image classification? The testing part of aleatoric uncertainty in classification only says: `# Aleatoric uncertainty is measured by...

Hi, I notice that you get the mu and sigma as https://github.com/ShellingFord221/My-implementation-of-What-Uncertainties-Do-We-Need-in-Bayesian-Deep-Learning-for-Computer-Vision/blob/e6ed204cd25ac995eb8ec8da701117dcd5aabb1d/classification_aleatoric.py#L81. As I know, sigma should be larger than zero, how can the real value in logit.split to satisfy...