← Python API
vraven · class

LRPResult

LRPResult(layers: 'list[LayerRelevance]', input_relevance: 'list[float] | None', input_relevance_shape: 'tuple[int, ...] | None', target_score: 'float', conservation_ratio: 'float', epsilon: 'float', metadata: 'dict[str, Any]' = <factory>) -> None

LRPResult(layers: 'list[LayerRelevance]', input_relevance: 'list[float] | None', input_relevance_shape: 'tuple[int, ...] | None', target_score: 'float', conservation_ratio: 'float', epsilon: 'float', metadata: 'dict[str, Any]' = <factory>)

Usage

from vraven import LRPResult

value = LRPResult(...)

Methods

layer_matrix(self, max_units: 'int' = 64) -> 'tuple[list[str], np.ndarray]'

Return layer names and a [layers, units] relevance magnitude matrix.

Source of truthThis page is generated from the checked-out public symbol, signature, and docstring. Pin the package version for reproducible work.