nucleus.evaluation_v2

Evaluation V2 — metrics and examples for a model run.

AllowedLabelMatch

Ground-truth and prediction label pair that counts as a match.

EvaluationV2

An Evaluation V2 run for a model run.

EvaluationV2Status

Status of an Evaluation V2 run.
class nucleus.evaluation_v2.AllowedLabelMatch

Ground-truth and prediction label pair that counts as a match.

class nucleus.evaluation_v2.EvaluationV2

An Evaluation V2 run for a model run.

charts(iou_threshold=0.5, filters=None, query=None)

Return aggregate metrics for this evaluation.

Parameters:

  • iou_threshold (float) – IoU threshold for matching (default 0.5).

  • filters (Optional[Union[nucleus.data_transfer_object.evaluation_v2.EvaluationV2FilterArgs, Dict[str, Any]]]) – Optional filters (EvaluationV2FilterArgs or dict).

  • query (Optional[str]) – Optional query string to narrow results.

Returns:

Summary metrics (mAP, confusion matrix, PR curve, etc.).

Return type:

EvaluationV2Charts

delete()

Delete this evaluation.

Return type:

None

examples(match_type, limit=50, offset=0, sort_by=None, sort_order=None, filters=None, query=None)

Return paginated true-positive, false-positive, or false-negative examples.

Parameters:

  • match_type (str) – "TP", "FP", or "FN".

  • limit (int) – Page size (default 50).

  • offset (int) – Row offset for pagination.

  • sort_by (Optional[str]) – Optional field to sort by.

  • sort_order (Optional[str]) – Optional sort direction (e.g. "asc" or "desc").

  • filters (Optional[Union[nucleus.data_transfer_object.evaluation_v2.EvaluationV2FilterArgs, Dict[str, Any]]]) – Optional filters (EvaluationV2FilterArgs or dict).

  • query (Optional[str]) – Optional query string to narrow results.

Returns:

Matching rows and total count.

Return type:

EvaluationV2ExamplesPage

refresh()

Reload this evaluation from Nucleus.

Returns:

self, with updated fields.

Return type:

EvaluationV2

wait_for_completion(timeout_sec=600, poll_interval=5)

Wait until the evaluation finishes or is cancelled.

Parameters:

  • timeout_sec (float) – Maximum seconds to wait.

  • poll_interval (float) – Seconds between status checks.

Returns:

self, after a terminal status is reached.

Raises:

RuntimeError – If the evaluation fails or times out.

Return type:

EvaluationV2

class nucleus.evaluation_v2.EvaluationV2Status

Status of an Evaluation V2 run.

Initialize self. See help(type(self)) for accurate signature.