nerfbaselines.evaluate

nerfbaselines.evaluate.compute_metrics(pred: ndarray, gt: ndarray, *, run_extras: bool = False, reduce: Literal[True] = True) → Dict[str, float]

nerfbaselines.evaluate.compute_metrics(pred: ndarray, gt: ndarray, *, run_extras: bool = False, reduce: Literal[False]) → Dict[str, ndarray]

nerfbaselines.evaluate.evaluate(predictions: str | Path, output: Path, disable_extra_metrics: bool | None = None, description: str = 'evaluating')

Evaluate a set of predictions.

Parameters:

• predictions – Path to a directory containing the predictions.

• output – Path to a json file where the results will be written.

• disable_extra_metrics – If True, skip the evaluation of metrics requiring extra dependencies.

• description – Description of the evaluation, used for progress bar.

Returns:

A dictionary containing the results.

nerfbaselines.evaluate.get_predictions_hashes(predictions: Path, description: str = 'hashing predictions')

nerfbaselines.evaluate.test_extra_metrics()

Test if the extra metrics are available.