torcheval.metrics.functional.binary_recall¶
-
torcheval.metrics.functional.
binary_recall
(input: Tensor, target: Tensor, *, threshold: float = 0.5) Tensor [source]¶ Compute recall score for binary classification class, which is calculated as the ratio between the number of true positives (TP) and the total number of actual positives (TP + FN). Its class version is
torcheval.metrics.BinaryRecall
. See alsomulticlass_recall
Parameters: - input (Tensor) – Tensor of the predicted labels/logits/probabilities, with shape of (n_sample, ).
- target (Tensor) – Tensor of ground truth labels with shape of (n_sample, ).
- threshold (float, default 0.5) – Threshold for converting input into predicted labels for each sample.
torch.where(input < threshold, 0, 1)
will be applied to theinput
.
Examples:
>>> import torch >>> from torcheval.metrics.functional.classification import binary_recall >>> input = torch.tensor([0, 0, 1, 1]) >>> target = torch.tensor([0, 1, 1, 1]) >>> binary_recall(input, target) tensor(0.6667) # 2 / 3 >>> input = torch.tensor([0, 0.2, 0.4, 0.7]) >>> target = torch.tensor([1, 0, 1, 1]) >>> binary_recall(input, target) tensor(0.3333) # 1 / 3 >>> binary_recall(input, target, threshold=0.4) tensor(0.5000) # 1 / 2