vis4d.eval.scalabel

Scalabel evaluator.

class ScalabelEvaluator(annotation_path, config=None)[source]

Scalabel base evaluation class.

__init__(annotation_path, config=None)[source]: Initialize the evaluator.

gather(gather_func)[source]

Gather variables in case of distributed setting (if needed).

Parameters:: gather_func (Callable[[Any], Any]) – Gather function.
Return type:: None

reset()[source]

Reset the evaluator.

Return type:: None

evaluate(metric)[source]

Evaluate the dataset.

Return type:: tuple[Dict[str, Union[float, int, Tensor]], str]

class ScalabelDetectEvaluator(annotation_path, config=None, mask_threshold=0.0)[source]

Scalabel 2D detection evaluation class.

__init__(annotation_path, config=None, mask_threshold=0.0)[source]: Initialize the evaluator.

__repr__()[source]

Concise representation of the dataset evaluator.

Return type:: str

property metrics: list[str]: Supported metrics.

process_batch(frame_ids, sample_names, sequence_names, pred_boxes, pred_classes, pred_scores, pred_masks=None)[source]

Process tracking results.

Return type:: None

evaluate(metric)[source]

Evaluate the dataset.

Return type:: tuple[Dict[str, Union[float, int, Tensor]], str]

class ScalabelTrackEvaluator(annotation_path, config=None, mask_threshold=0.0)[source]

Scalabel 2D tracking evaluation class.

__init__(annotation_path, config=None, mask_threshold=0.0)[source]: Initialize the evaluator.

__repr__()[source]

Concise representation of the dataset evaluator.

Return type:: str

property metrics: list[str]: Supported metrics.

process_batch(frame_ids, sample_names, sequence_names, pred_boxes, pred_classes, pred_scores, pred_track_ids, pred_masks=None)[source]

Process tracking results.

Return type:: None

evaluate(metric)[source]

Evaluate the dataset.

Return type:: tuple[Dict[str, Union[float, int, Tensor]], str]

Modules

`base`	Scalabel base evaluator.
`detect`	Scalabel detection evaluator.
`track`	Scalabel tracking evaluator.