Hyperia
HyperIA

Trainings

Configure classifiers, selectors, and band ranges; then compare metrics across HyperIA runs.

A training ties together a name, a dataset, and a configuration:

  • Classifier — e.g. Support Vector Machines or Random Forest.
  • Selector — e.g. SFS (sequential feature selection) to pick informative bands.
  • Band range — initial and final band indices the selector searches within.

After training completes, use Metrics to compare runs: accuracy, kappa, F1 versus number of bands, plus spectral visualization (and confusion matrix where available) per model.

HyperIA training result: best model with classifier, selector, bands, metrics, and spectral plot
After training: best model summary, accuracy, F1, kappa, and spectral signature for selected bands.

Step-by-step UI flow: Quick start.

Datasets

Create and validate HyperIA datasets from per-class CSVs before training.

HyperLabel

Import .mat hyperspectral cubes, annotate polygons and boxes, then deploy datasets to HyperIA.