lczerolens.concept#

Class for concept-based XAI methods.

Classes#

`Concept`	Class for concept-based XAI methods.
`BinaryConcept`	Class for binary concept-based XAI methods.
`NullConcept`	Class for binary concept-based XAI methods.
`OrBinaryConcept`	Class for binary concept-based XAI methods.
`AndBinaryConcept`	Class for binary concept-based XAI methods.
`MulticlassConcept`	Class for multiclass concept-based XAI methods.
`ContinuousConcept`	Class for continuous concept-based XAI methods.

Functions#

`concept_collate_fn`(batch)
`concept_init_rel`(output, infos)

Module Contents#

class lczerolens.concept.Concept[source]#

Bases: abc.ABC

Class for concept-based XAI methods.

abstract compute_label(board)[source]#

Compute the label for a given model and input.

Parameters:: board (lczerolens.board.LczeroBoard)
Return type:: Any

static compute_metrics(predictions, labels)[source]#

Abstractmethod:

Compute the metrics for a given model and input.

property features: datasets.Features[source]#

Abstractmethod:
Return type:: datasets.Features

Return the features for the concept.

class lczerolens.concept.BinaryConcept[source]#

Bases: Concept

Class for binary concept-based XAI methods.

features[source]#: Return the features for the concept.

static compute_metrics(predictions, labels)[source]#: Compute the metrics for a given model and input.

class lczerolens.concept.NullConcept[source]#

Bases: BinaryConcept

Class for binary concept-based XAI methods.

compute_label(board)[source]#

Compute the label for a given model and input.

Parameters:: board (lczerolens.board.LczeroBoard)
Return type:: Any

class lczerolens.concept.OrBinaryConcept(*concepts)[source]#

Bases: BinaryConcept

Class for binary concept-based XAI methods.

Parameters:: concepts (BinaryConcept)

concepts = ()[source]#

compute_label(board)[source]#

Compute the label for a given model and input.

Parameters:: board (lczerolens.board.LczeroBoard)
Return type:: Any

class lczerolens.concept.AndBinaryConcept(*concepts)[source]#

Bases: BinaryConcept

Class for binary concept-based XAI methods.

Parameters:: concepts (BinaryConcept)

concepts = ()[source]#

compute_label(board)[source]#

Compute the label for a given model and input.

Parameters:: board (lczerolens.board.LczeroBoard)
Return type:: Any

class lczerolens.concept.MulticlassConcept[source]#

Bases: Concept

Class for multiclass concept-based XAI methods.

features[source]#: Return the features for the concept.

static compute_metrics(predictions, labels)[source]#: Compute the metrics for a given model and input.

class lczerolens.concept.ContinuousConcept[source]#

Bases: Concept

Class for continuous concept-based XAI methods.

features[source]#: Return the features for the concept.

static compute_metrics(predictions, labels)[source]#: Compute the metrics for a given model and input.

lczerolens.concept.concept_collate_fn(batch)[source]#

lczerolens.concept.concept_init_rel(output, infos)[source]#