quantus.metrics.faithfulness.region_perturbation module

This module contains the implementation of the Region Perturbation metric.

final class quantus.metrics.faithfulness.region_perturbation.RegionPerturbation(patch_size: int = 8, order: str = 'morf', regions_evaluation: int = 100, abs: bool = False, normalise: bool = True, normalise_func: Callable[[ndarray], ndarray] | None = None, normalise_func_kwargs: Dict[str, Any] | None = None, perturb_func: Callable | None = None, perturb_baseline: str = 'black', perturb_func_kwargs: Dict[str, Any] | None = None, return_aggregate: bool = False, aggregate_func: Callable | None = None, default_plot_func: Callable | None = None, disable_warnings: bool = False, display_progressbar: bool = False, **kwargs)

Bases: Metric[List[float]]

Implementation of Region Perturbation by Samek et al., 2015.

Consider a greedy iterative procedure that consists of measuring how the class encoded in the image (e.g. as measured by the function f) disappears when we progressively remove information from the image x, a process referred to as region perturbation, at the specified locations.

Assumptions:

  • The original metric definition relies on image-patch functionality. Therefore, only apply the

metric to 3-dimensional (image) data. To extend the applicablity to other data domains, adjustments to the current implementation might be necessary.

References:

1) Wojciech Samek et al.: “Evaluating the visualization of what a deep neural network has learned.” IEEE transactions on neural networks and learning systems 28.11 (2016): 2660-2673.

Attributes:

  • _name: The name of the metric.

  • _data_applicability: The data types that the metric implementation currently supports.

  • _models: The model types that this metric can work with.

  • score_direction: How to interpret the scores, whether higher/ lower values are considered better.

  • evaluation_category: What property/ explanation quality that this metric measures.

Attributes:
disable_warnings

A helper to avoid polluting test outputs with warnings.

display_progressbar

A helper to avoid polluting test outputs with tqdm progress bars.

get_auc_score

Calculate the area under the curve (AUC) score for several test samples.

get_params

List parameters of metric.

Methods

__call__(model, x_batch, y_batch[, a_batch, ...])

This implementation represents the main logic of the metric and makes the class object callable.

batch_preprocess(data_batch)

If data_batch has no a_batch, will compute explanations.

custom_batch_preprocess(*, model, x_batch, ...)

Implement this method if you need custom preprocessing of data or simply for creating/initialising additional attributes or assertions before a data_batch can be evaluated.

custom_postprocess(*, model, x_batch, ...)

Implement this method if you need custom postprocessing of results or additional attributes.

custom_preprocess(*, model, x_batch, ...)

Implement this method if you need custom preprocessing of data, model alteration or simply for creating/initialising additional attributes or assertions.

evaluate_batch(model, x_batch, y_batch, ...)

This method performs XAI evaluation on a single batch of explanations.

explain_batch(model, x_batch, y_batch)

Compute explanations, normalise and take absolute (if was configured so during metric initialization.) This method should primarily be used if you need to generate additional explanation in metrics body. It encapsulates typical for Quantus pre- and postprocessing approach. It will do few things: - call model.shape_input (if ModelInterface instance was provided) - unwrap model (if ModelInterface instance was provided) - call explain_func - expand attribution channel - (optionally) normalise a_batch - (optionally) take np.abs of a_batch.

general_preprocess(model, x_batch, y_batch, ...)

Prepares all necessary variables for evaluation.

generate_batches(data, batch_size)

Creates iterator to iterate over all batched instances in data dictionary.

interpret_scores()

Get an interpretation of the scores.

plot([plot_func, show, path_to_save])

Basic plotting functionality for Metric class.
__call__(model, x_batch: ndarray, y_batch: ndarray, a_batch: ndarray | None = None, s_batch: ndarray | None = None, channel_first: bool | None = None, explain_func: Callable | None = None, explain_func_kwargs: Dict | None = None, model_predict_kwargs: Dict | None = None, softmax: bool | None = True, device: str | None = None, batch_size: int = 64, **kwargs) → List[float]

This implementation represents the main logic of the metric and makes the class object callable. It completes instance-wise evaluation of explanations (a_batch) with respect to input data (x_batch), output labels (y_batch) and a torch or tensorflow model (model).

Calls general_preprocess() with all relevant arguments, calls () on each instance, and saves results to evaluation_scores. Calls custom_postprocess() afterwards. Finally returns evaluation_scores.

Parameters:
model: torch.nn.Module, tf.keras.Model

A torch or tensorflow model that is subject to explanation.

x_batch: np.ndarray

A np.ndarray which contains the input data that are explained.

y_batch: np.ndarray

A np.ndarray which contains the output labels that are explained.

a_batch: np.ndarray, optional

A np.ndarray which contains pre-computed attributions i.e., explanations.

s_batch: np.ndarray, optional

A np.ndarray which contains segmentation masks that matches the input.

channel_first: boolean, optional

Indicates of the image dimensions are channel first, or channel last. Inferred from the input shape if None.

explain_func: callable

Callable generating attributions.

explain_func_kwargs: dict, optional

Keyword arguments to be passed to explain_func on call.

model_predict_kwargs: dict, optional

Keyword arguments to be passed to the model’s predict method.

softmax: boolean

Indicates whether to use softmax probabilities or logits in model prediction. This is used for this __call__ only and won’t be saved as attribute. If None, self.softmax is used.

device: string

Indicated the device on which a torch.Tensor is or will be allocated: “cpu” or “gpu”.

kwargs: optional

Keyword arguments.

Returns:
evaluation_scores: list

a list of Any with the evaluation scores of the concerned batch.

Examples:

# Minimal imports. >> import quantus >> from quantus import LeNet >> import torch

# Enable GPU. >> device = torch.device(“cuda:0” if torch.cuda.is_available() else “cpu”)

# Load a pre-trained LeNet classification model (architecture at quantus/helpers/models). >> model = LeNet() >> model.load_state_dict(torch.load(“tutorials/assets/pytests/mnist_model”))

# Load MNIST datasets and make loaders. >> test_set = torchvision.datasets.MNIST(root=’./sample_data’, download=True) >> test_loader = torch.utils.data.DataLoader(test_set, batch_size=24)

# Load a batch of inputs and outputs to use for XAI evaluation. >> x_batch, y_batch = iter(test_loader).next() >> x_batch, y_batch = x_batch.cpu().numpy(), y_batch.cpu().numpy()

# Generate Saliency attributions of the test set batch of the test set. >> a_batch_saliency = Saliency(model).attribute(inputs=x_batch, target=y_batch, abs=True).sum(axis=1) >> a_batch_saliency = a_batch_saliency.cpu().numpy()

# Initialise the metric and evaluate explanations by calling the metric instance. >> metric = Metric(abs=True, normalise=False) >> scores = metric(model=model, x_batch=x_batch, y_batch=y_batch, a_batch=a_batch_saliency)

__init__(patch_size: int = 8, order: str = 'morf', regions_evaluation: int = 100, abs: bool = False, normalise: bool = True, normalise_func: Callable[[ndarray], ndarray] | None = None, normalise_func_kwargs: Dict[str, Any] | None = None, perturb_func: Callable | None = None, perturb_baseline: str = 'black', perturb_func_kwargs: Dict[str, Any] | None = None, return_aggregate: bool = False, aggregate_func: Callable | None = None, default_plot_func: Callable | None = None, disable_warnings: bool = False, display_progressbar: bool = False, **kwargs)
Parameters:
patch_size: integer

The patch size for masking, default=8.

regions_evaluation: integer

The number of regions to evaluate, default=100.

order: string
Indicates whether attributions are ordered randomly (“random”),

according to the most relevant first (“morf”), or least relevant first (“lerf”), default=”morf”.

abs: boolean

Indicates whether absolute operation is applied on the attribution, default=False.

normalise: boolean

Indicates whether normalise operation is applied on the attribution, default=True.

normalise_func: callable

Attribution normalisation function applied in case normalise=True. If normalise_func=None, the default value is used, default=normalise_by_max.

normalise_func_kwargs: dict

Keyword arguments to be passed to normalise_func on call, default={}.

perturb_func: callable

Input perturbation function. If None, the default value is used, default=baseline_replacement_by_indices.

perturb_baseline: string

Indicates the type of baseline: “mean”, “random”, “uniform”, “black” or “white”, default=”black”.

perturb_func_kwargs: dict

Keyword arguments to be passed to perturb_func, default={}.

return_aggregate: boolean

Indicates if an aggregated score should be computed over all instances.

aggregate_func: callable

Callable that aggregates the scores given an evaluation call.

default_plot_func: callable

Callable that plots the metrics result.

disable_warnings: boolean

Indicates whether the warnings are printed, default=False.

display_progressbar: boolean

Indicates whether a tqdm-progress-bar is printed, default=False.

kwargs: optional

Keyword arguments.

data_applicability: ClassVar[Set[DataType]] = {DataType.IMAGE}
evaluate_batch(model: ModelInterface, x_batch: ndarray, y_batch: ndarray, a_batch: ndarray, **kwargs) → List[List[float]]

This method performs XAI evaluation on a single batch of explanations. For more information on the specific logic, we refer the metric’s initialisation docstring.

Parameters:
model: ModelInterface

A ModelInteface that is subject to explanation.

x_batch: np.ndarray

The input to be evaluated on a batch-basis.

y_batch: np.ndarray

The output to be evaluated on a batch-basis.

a_batch: np.ndarray

The explanation to be evaluated on a batch-basis.

kwargs:

Unused.

Returns:
scores_batch:

The evaluation results.

evaluation_category: ClassVar[EvaluationCategory] = 'Faithfulness'
property get_auc_score

Calculate the area under the curve (AUC) score for several test samples.

model_applicability: ClassVar[Set[ModelType]] = {ModelType.TF, ModelType.TORCH}
name: ClassVar[str] = 'Region-Perturbation'
score_direction: ClassVar[ScoreDirection] = 'lower'