nicetoolbox.evaluation.metrics.base_metric.Metric¶

class nicetoolbox.evaluation.metrics.base_metric.Metric(**kwargs: Any)[source]¶

Bases: ABC

Abstract base class for a single, stateful metric computation.

Initializes the metric. Subclasses can use kwargs for specific setup.

Methods

`compute`	Compute the final metric from the stored state and return as a dictionary.
`get_axis3`	Get the metrics output description.
`reset`	Reset the metric's internal state to prepare for a new run.
`update`	Update metric state with a batch of data and its corresponding metadata.

abstract compute() → Dict[Tuple[str, str, str], List[BatchResult] | AggregatedResult][source]¶: Compute the final metric from the stored state and return as a dictionary.

abstract get_axis3(meta_chunks: List[ChunkWorkItem] | None = None) → List[str][source]¶: Get the metrics output description. E.g. bone names or joint names.

abstract reset() → None[source]¶: Reset the metric’s internal state to prepare for a new run.

abstract update(preds: torch.Tensor, gts: torch.Tensor, meta_chunks: List[ChunkWorkItem], meta_frames: List[FrameInfo]) → None[source]¶: Update metric state with a batch of data and its corresponding metadata.