pulsatrix 1.1.0
Loading...
Searching...
No Matches
pulsatrix::ModelTraits Struct Reference

What the caller has: the model, its inputs and its data. More...

#include <explanation_planner.hpp>

Public Attributes

ModelAccess access = ModelAccess::BlackBox
 The most the model gives, from a prediction function only (BlackBox) to an LRP rule at every layer (Relevance). Each level includes the ones before it.
 
InputKind input = InputKind::Any
 What the model takes. Any means unknown: explainers for one kind of input are then kept, with that kind as a condition.
 
bool can_reinitialize = false
 A pulsatrix Module whose weights can be redrawn and restored, for the randomization test and the null-model baseline.
 
bool has_dataset = false
 Many inputs, not just the one being explained: global explainers need them, and so does aggregating explanations over a dataset.
 
bool has_labels = false
 The dataset's true labels, and a slice for each input (a group, a data source), for the per-slice error check (KS-3).
 
bool has_base_model = false
 The model this one was fine-tuned from, for explainers that compare the two.
 
int64_t features = 0
 How many features each input has, or 0 if unknown; explainers with a limit (ExplainerCapabilities::max_features) are excluded above it.
 

Detailed Description

What the caller has: the model, its inputs and its data.

Member Data Documentation

◆ access

ModelAccess pulsatrix::ModelTraits::access = ModelAccess::BlackBox

The most the model gives, from a prediction function only (BlackBox) to an LRP rule at every layer (Relevance). Each level includes the ones before it.

◆ can_reinitialize

bool pulsatrix::ModelTraits::can_reinitialize = false

A pulsatrix Module whose weights can be redrawn and restored, for the randomization test and the null-model baseline.

◆ features

int64_t pulsatrix::ModelTraits::features = 0

How many features each input has, or 0 if unknown; explainers with a limit (ExplainerCapabilities::max_features) are excluded above it.

◆ has_base_model

bool pulsatrix::ModelTraits::has_base_model = false

The model this one was fine-tuned from, for explainers that compare the two.

◆ has_dataset

bool pulsatrix::ModelTraits::has_dataset = false

Many inputs, not just the one being explained: global explainers need them, and so does aggregating explanations over a dataset.

◆ has_labels

bool pulsatrix::ModelTraits::has_labels = false

The dataset's true labels, and a slice for each input (a group, a data source), for the per-slice error check (KS-3).

◆ input

InputKind pulsatrix::ModelTraits::input = InputKind::Any

What the model takes. Any means unknown: explainers for one kind of input are then kept, with that kind as a condition.


The documentation for this struct was generated from the following file: