Aggregates, per prediction, a 2x2 panel: top row is "what was shown, how confident
was the model" (input label + ConfidenceMeter), bottom row is "how trustworthy is
this explanation" (LRP conservation delta + explainer stability), visually separated by a rule (Gestalt proximity grouping – these are two different semantic questions, not one undifferentiated block of numbers).
More...
#include <explanation_score_card.hpp>
Aggregates, per prediction, a 2x2 panel: top row is "what was shown, how confident
was the model" (input label + ConfidenceMeter), bottom row is "how trustworthy is
this explanation" (LRP conservation delta + explainer stability), visually separated by a rule (Gestalt proximity grouping – these are two different semantic questions, not one undifferentiated block of numbers).
◆ Draw()
| static void pulsatrix::ExplanationScoreCard::Draw |
( |
const char * |
title, |
|
|
const Input & |
input, |
|
|
ScoreCardScaleContext * |
shared_scale = nullptr |
|
) |
| |
|
static |
- Parameters
-
| title | A unique ImGui window/child id for this card. |
| input | The data to display. |
| shared_scale | When non-null, this card's attribution bar chart shares (and updates) this scale instead of auto-scaling to just its own attribution. |
The documentation for this class was generated from the following file: