Configuration for LRP relevance propagation: which rule a module applies and its hyperparameters. A module that does not implement the requested rule throws (see Module::supports_lrp_rule()) – the rule is never silently substituted. More...

#include <lrp_rule_config.hpp>

Public Attributes
float	epsilon = 1e-6f
	Stabilizer added to every rule's denominator: z + epsilon * sign(z), sign(0) = +1.

LRPRule	rule = LRPRule::Epsilon
	Which rule to apply.

float	gamma = 0.25f
	Gamma rule: weight of the positive (or negative) part added to the weights.

float	alpha = 1.0f
	AlphaBeta rule: weight of the positive contributions. Needs alpha, beta >= 0, alpha - beta == 1.

float	beta = 0.0f
	AlphaBeta rule: weight of the negative contributions.

float	low = 0.0f
	ZBox rule: lowest admissible input value (scalar, applied to every input element).

float	high = 1.0f
	ZBox rule: highest admissible input value.

bool	epsilon_bias_in_denominator = false
	Epsilon rule only, honoured by LinearModule / Conv2DModule: include the bias in the denominator, z = xW + b (Zennit's Epsilon). The default (false) keeps this codebase's conservative pre-bias z = xW, under which the bias absorbs no relevance.

Detailed Description

Configuration for LRP relevance propagation: which rule a module applies and its hyperparameters. A module that does not implement the requested rule throws (see Module::supports_lrp_rule()) – the rule is never silently substituted.

Note: epsilon stays the first member so aggregate initialization LRPRuleConfig{0.01f} keeps meaning "epsilon rule, epsilon 0.01". It is also the denominator stabilizer of Gamma / AlphaBeta / ZBox (Zennit's stabilizer, default 1e-6 there as well).

Member Data Documentation

◆ alpha

float pulsatrix::LRPRuleConfig::alpha = 1.0f

AlphaBeta rule: weight of the positive contributions. Needs alpha, beta >= 0, alpha - beta == 1.

◆ beta

float pulsatrix::LRPRuleConfig::beta = 0.0f

AlphaBeta rule: weight of the negative contributions.

◆ epsilon

float pulsatrix::LRPRuleConfig::epsilon = 1e-6f

Stabilizer added to every rule's denominator: z + epsilon * sign(z), sign(0) = +1.

◆ epsilon_bias_in_denominator

bool pulsatrix::LRPRuleConfig::epsilon_bias_in_denominator = false

Epsilon rule only, honoured by LinearModule / Conv2DModule: include the bias in the denominator, z = xW + b (Zennit's Epsilon). The default (false) keeps this codebase's conservative pre-bias z = xW, under which the bias absorbs no relevance.

◆ gamma

float pulsatrix::LRPRuleConfig::gamma = 0.25f

Gamma rule: weight of the positive (or negative) part added to the weights.

◆ high

float pulsatrix::LRPRuleConfig::high = 1.0f

ZBox rule: highest admissible input value.

◆ low

float pulsatrix::LRPRuleConfig::low = 0.0f

ZBox rule: lowest admissible input value (scalar, applied to every input element).

◆ rule

LRPRule pulsatrix::LRPRuleConfig::rule = LRPRule::Epsilon

Which rule to apply.

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

include/pulsatrix/lrp_rule_config.hpp

Public Attributes