chainer.functions.classification_summary¶
-
chainer.functions.
classification_summary
(y, t, label_num=None, beta=1.0, ignore_label=-1)[source]¶ Calculates Precision, Recall, F beta Score, and support.
This function calculates the following quantities for each class.
- Precision: \(\frac{\mathrm{tp}}{\mathrm{tp} + \mathrm{fp}}\)
- Recall: \(\frac{\mathrm{tp}}{\mathrm{tp} + \mathrm{tn}}\)
- F beta Score: The weighted harmonic average of Precision and Recall.
- Support: The number of instances of each ground truth label.
Here,
tp
,fp
, andtn
stand for the number of true positives, false positives, and true negative, respectively.label_num
specifies the number of classes, that is, each value int
must be an integer in the range of[0, label_num)
. Iflabel_num
isNone
, this function regardslabel_num
as a maximum of int
plus one.ignore_label
determines which instances should be ignored. Specifically, instances with the given label are not taken into account for calculating the above quantities. By default, it is set to -1 so that all instances are taken into consideration, as labels are supposed to be non-negative integers. Settingignore_label
to a non-negative integer less thanlabel_num
is illegal and yields undefined behavior. In the current implementation, it arisesRuntimeWarning
andignore_label
-th entries in output arrays do not contain correct quantities.Parameters: - y (Variable) – Variable holding a vector of scores.
- t (Variable) – Variable holding a vector of ground truth labels.
- label_num (int) – The number of classes.
- beta (float) – The parameter which determines the weight of precision in the F-beta score.
- ignore_label (int) – Instances with this label are ignored.
Returns: 4-tuple of ~chainer.Variable of size
(label_num,)
. Each element represents precision, recall, F beta score, and support of this minibatch.