Upperbound Average Precision

Tutorials

There are no tutorials for UAP yet, but we will be adding one soon.

How To Guides

There are currently no how to’s for UAP. If there are scenarios that you want us to explain, contact us!

DAML API

class daml.metrics.UAP(labels: ndarray, scores: ndarray)

FR Test Statistic based estimate of the empirical mean precision

Parameters:

• labels (np.ndarray) – A numpy array of n_samples of class labels with M unique classes.

• scores (np.ndarray) – A 2D array of class probabilities per image

evaluate() → Dict[str, float]

Returns:

uap : The empirical mean precision estimate

Return type:

Dict[str, float]

Raises:

ValueError – If unique classes M < 2