Function compute_average_precision

monai/metrics/average_precision.py:116–184

Computes Average Precision (AP). AP is a useful metric to evaluate a classifier when the classes are imbalanced. It summarizes a Precision-Recall according to equation :eq:`ap`. Referring to: `sklearn.metrics.average_precision_score <https://scikit-learn.org/stable/modules/generated/skle

(
    y_pred: torch.Tensor, y: torch.Tensor, average: Average | str = Average.MACRO
)

def compute_average_precision(
    y_pred: torch.Tensor, y: torch.Tensor, average: Average | str = Average.MACRO
) -> np.ndarray | float | npt.ArrayLike:
    """Computes Average Precision (AP). AP is a useful metric to evaluate a classifier when the classes are
    imbalanced. It summarizes a Precision-Recall according to equation :eq:`ap`.
    Referring to: `sklearn.metrics.average_precision_score
    <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score>`_.

    Args:
        y_pred: input data to compute, typical classification model output.
            the first dim must be batch, if multi-classes, it must be in One-Hot format.
            for example: shape `[16]` or `[16, 1]` for a binary data, shape `[16, 2]` for 2 classes data.
        y: ground truth to compute AP metric, the first dim must be batch.
            if multi-classes, it must be in One-Hot format.
            for example: shape `[16]` or `[16, 1]` for a binary data, shape `[16, 2]` for 2 classes data.
        average: {``"macro"``, ``"weighted"``, ``"micro"``, ``"none"``}
            Type of averaging performed if not binary classification.
            Defaults to ``"macro"``.

            - ``"macro"``: calculate metrics for each label, and find their unweighted mean.
                This does not take label imbalance into account.
            - ``"weighted"``: calculate metrics for each label, and find their average,
                weighted by support (the number of true instances for each label).
            - ``"micro"``: calculate metrics globally by considering each element of the label
                indicator matrix as a label.
            - ``"none"``: the scores for each class are returned.

    Raises:
        ValueError: When ``y_pred`` dimension is not one of [1, 2].
        ValueError: When ``y`` dimension is not one of [1, 2].
        ValueError: When ``average`` is not one of ["macro", "weighted", "micro", "none"].

    Note:
        Average Precision expects y to be comprised of 0's and 1's. `y_pred` must be either prob. estimates or confidence values.

    """
    y_pred_ndim = y_pred.ndimension()
    y_ndim = y.ndimension()
    if y_pred_ndim not in (1, 2):
        raise ValueError(
            f"Predictions should be of shape (batch_size, num_classes) or (batch_size, ), got {y_pred.shape}."
        )
    if y_ndim not in (1, 2):
        raise ValueError(f"Targets should be of shape (batch_size, num_classes) or (batch_size, ), got {y.shape}.")
    if y_pred_ndim == 2 and y_pred.shape[1] == 1:
        y_pred = y_pred.squeeze(dim=-1)
        y_pred_ndim = 1
    if y_ndim == 2 and y.shape[1] == 1:
        y = y.squeeze(dim=-1)

    if y_pred_ndim == 1:
        return _calculate(y_pred, y)

    if y.shape != y_pred.shape:
        raise ValueError(f"data shapes of y_pred and y do not match, got {y_pred.shape} and {y.shape}.")

    average = look_up_option(average, Average)
    if average == Average.MICRO: