Tutorials#

On this page, you will find tutorials and insights on TorchUncertainty. Don’t hesitate to open an issue if you have any question or suggestion for tutorials.

Classification#

Tutorials for modeling uncertainty in classification tasks.

Training a LeNet for Image Classification with TorchUncertainty

Evaluating Model Performance Under Distribution Shift with TorchUncertainty

Deep Evidential Classification on a Toy Example

Out-of-distribution detection with TorchUncertainty

From a Standard Classifier to a Packed-Ensemble

Regression with Uncertainty#

Tutorials for modeling predictive uncertainty in regression tasks.

Deep Evidential Regression on a Toy Example

Deep Probabilistic Regression

Training an MLP for Tabular Regression with TorchUncertainty

Post-hoc Methods#

Tutorials focused on improving model with post-hoc techniques.

Conformal Prediction on CIFAR-10 with TorchUncertainty

Improve Top-label Calibration with Temperature Scaling

Bayesian Methods#

Tutorials for Bayesian approaches to uncertainty estimation.

Training a Bayesian Neural Network in 20 seconds

Training a LeNet with Monte Carlo Batch Normalization

Training a LeNet with Monte-Carlo Dropout

Monte Carlo Dropout for Semantic Segmentation on MUAD

Ensemble Methods#

Tutorials for ensemble-based techniques to improve uncertainty estimation.

Improved Ensemble parameter-efficiency with Packed-Ensembles

Segmentation#

Tutorials for modeling uncertainty in Segmentation tasks.

Deep ensembles Segmentation Tutorial using Muad Dataset

Packed ensembles Segmentation Tutorial using Muad Dataset

Segmentation Tutorial using Muad Dataset

Data Augmentation#

Tutorials illustrating data augmentation functionnalities in Torch-Uncertainty.

Corrupting Images with TorchUncertainty to Benchmark Robustness

Gallery generated by Sphinx-Gallery