metric

Metrics to use for training or explanations.

Metric

Represents a metric for the explainable model.

TorchMetric

Represent a metric to be used in the training or evaluation process for the whole model (global metric).

Parameters:

Name	Type	Description	Default
metric		The torchmetrics metric to use, as partial.	required
display_metric_type		If set, overrides the default metric name in XpViz.	required
on_raw_data		If set, value are compute from raw data and not preprocessed data (inputs or targets).	required

metric: partial[torchmetrics.metric.Metric]

display_metric_type: str | None = None

on_raw_data: bool = False

TorchLeafMetric

Represent a metric to be used during the training or the evaluation process, per leaf.

Parameters:

Name	Type	Description	Default
metric		The torchmetrics metric to use, as partial.	required
display_metric_type		If set, overrides the default metric name in XpViz.	required
on_raw_data		If set, value are compute from raw data and not preprocessed data (inputs or targets).	required

metric: partial[torchmetrics.metric.Metric]

display_metric_type: str | None = None

on_raw_data: bool = False

DictMetrics

Dictionary of metrics (torch eval etc...) used in training or explain stage.

Each metric will be computed globally (for the whole model) and per leaf. In the training stage, help to monitor the training. In the explain stage, allow to visualize metrics in xpdeep-viz along with explanations.