API Reference

Routines

The routine are the main building blocks of the library. They define the framework in which the models are trained and evaluated. They allow for easy computation of different metrics crucial for uncertainty estimation in different contexts, namely classification, regression and segmentation.

Classification

ClassificationRoutine

Routine for efficient training and testing on classification tasks using LightningModule.

Regression

RegressionRoutine

Routine for efficient training and testing on regression tasks using LightningModule.

Segmentation

SegmentationRoutine

Routine for efficient training and testing on segmentation tasks using LightningModule.

Baselines

TorchUncertainty provide lightning-based models that can be easily trained and evaluated. These models inherit from the routines and are specifically designed to benchmark different methods in similar settings, here with constant architectures.

Classification

ResNetBaseline	ResNet backbone baseline for classification providing support for various versions and architectures.
VGGBaseline	VGG backbone baseline for classification providing support for various versions and architectures.
WideResNetBaseline	Wide-ResNet28x10 backbone baseline for classification providing support for various versions.

Regression

MLPBaseline

MLP baseline for regression providing support for various versions.

Segmentation

SegFormerBaseline

SegFormer backbone baseline for segmentation providing support for various versions and architectures.

Layers

Ensemble layers

PackedLinear	Packed-Ensembles-style Linear layer.
PackedConv2d	Packed-Ensembles-style Conv2d layer.
BatchLinear	BatchEnsemble-style Linear layer.
BatchConv2d	BatchEnsemble-style Conv2d layer.
MaskedLinear	Masksembles-style Linear layer.
MaskedConv2d	Masksembles-style Conv2d layer.

Bayesian layers

BayesLinear	Bayesian Linear Layer with Mixture of Normals prior and Normal posterior.
BayesConv1d	Bayesian Conv1d Layer with Mixture of Normals prior and Normal posterior.
BayesConv2d	Bayesian Conv2d Layer with Mixture of Normals prior and Normal posterior.
BayesConv3d	Bayesian Conv3d Layer with Mixture of Normals prior and Normal posterior.

Models

Deep Ensembles

deep_ensembles

Build a Deep Ensembles out of the original models.

Monte Carlo Dropout

mc_dropout

MC Dropout wrapper for a model.

Metrics

AUSE	The Area Under the Sparsification Error curve (AUSE) metric to estimate the quality of the uncertainty estimates, i.e., how much they coincide with the true errors.
BrierScore	The Brier Score Metric.
CategoricalNLL	The Negative Log Likelihood Metric.
CE	Top-label Calibration Error.
Disagreement	The Disagreement Metric to estimate the confidence of an ensemble of estimators.
DistributionNLL	The Negative Log Likelihood Metric.
Entropy	The Shannon Entropy Metric to estimate the confidence of a single model or the mean confidence across estimators.
FPR95	The False Positive Rate at 95% Recall metric.
Log10	The Log10 metric.
MeanGTRelativeAbsoluteError	Compute Mean Absolute Error relative to the Ground Truth (MAErel or ARE).
MeanGTRelativeSquaredError	Compute mean squared error relative to the Ground Truth (MSErel or SRE).
MutualInformation	The Mutual Information Metric to estimate the epistemic uncertainty of an ensemble of estimators.
SILog	The Scale-Invariant Logarithmic Loss metric.
ThresholdAccuracy	The Threshold Accuracy metric, a.k.a.

Losses

DistributionNLLLoss	Negative Log-Likelihood loss using given distributions as inputs.
KLDiv	KL divergence loss for Bayesian Neural Networks.
ELBOLoss	The Evidence Lower Bound (ELBO) loss for Bayesian Neural Networks.
BetaNLL	The Beta Negative Log-likelihood loss.
DECLoss	The deep evidential classification loss.

Post-Processing Methods

TemperatureScaler	Temperature scaling post-processing for calibrated probabilities.
VectorScaler	Vector scaling post-processing for calibrated probabilities.
MatrixScaler	Matrix scaling post-processing for calibrated probabilities.
MCBatchNorm	Monte Carlo Batch Normalization wrapper.

Datamodules

Classification

CIFAR10DataModule	DataModule for CIFAR10.
CIFAR100DataModule	DataModule for CIFAR100.
MNISTDataModule	DataModule for MNIST.
TinyImageNetDataModule
ImageNetDataModule	DataModule for ImageNet.

Regression

UCIDataModule

The UCI regression datasets.

Segmentation

CamVidDataModule	DataModule for the CamVid dataset.
CityscapesDataModule	DataModule for the Cityscapes dataset.
MUADDataModule	Segmentation DataModule for the MUAD dataset.