SaliencyMapExplanation<T>

Models & Types · AiDotNet.Interpretability.Explainers

Represents the result of a Saliency Map analysis.

Implements: IFeatureAttribution<T>

Constructors

Constructor Summary
SaliencyMapExplanation()

Properties

Property Summary
SaliencyMethod Method { get; set; } Gets or sets the saliency method used.
Vector<T> Input { get; set; } Gets or sets the input instance.
Vector<T> NormalizedSaliency { get; set; } Gets or sets the normalized saliency values (0 to 1).
Vector<T> Prediction { get; set; } Gets or sets the model prediction.
Vector<T> Saliency { get; set; } Gets or sets the raw saliency values.
int OutputIndex { get; set; } Gets or sets the output index that was explained.
string[] FeatureNames { get; set; } Gets or sets the feature names.

Methods

Method Summary
List<ValueTuple<string, T, T>> GetSortedSaliency() Gets saliency values sorted by absolute value (most salient first).
List<ValueTuple<string, T>> GetTopSalientFeatures(int topK) Gets the top K most salient features.
Vector<T> GetFeatureAttributions()
string ToString() Returns a human-readable summary.