Computes F-Beta score.
metric_fbetascore( num_classes, average = NULL, beta = 1, threshold = NULL, name = "fbeta_score", dtype = tf$float32, ... )
| num_classes | Number of unique classes in the dataset. |
|---|---|
| average | Type of averaging to be performed on data. Acceptable values are None, micro, macro and weighted. Default value is NULL. micro, macro and weighted. Default value is NULL. - None: Scores for each class are returned - micro: True positivies, false positives and false negatives are computed globally. - macro: True positivies, false positives and - false negatives are computed for each class and their unweighted mean is returned. - weighted: Metrics are computed for each class and returns the mean weighted by the number of true instances in each class.- |
| beta | Determines the weight of precision and recall in harmonic mean. Determines the weight given to the precision and recall. Default value is 1. |
| threshold | Elements of y_pred greater than threshold are converted to be 1, and the rest 0. If threshold is None, the argmax is converted to 1, and the rest 0. |
| name | (optional) String name of the metric instance. |
| dtype | (optional) Data type of the metric result. Defaults to `tf$float32`. |
| ... | additional parameters to pass |
F-Beta Score: float
It is the weighted harmonic mean of precision and recall. Output range is [0, 1]. Works for both multi-class and multi-label classification. F-Beta = (1 + beta^2) * (prec * recall) / ((beta^2 * prec) + recall)
ValueError: If the `average` has values other than [NULL, micro, macro, weighted].