Skip to content

categorical_accuracy

allennlp.training.metrics.categorical_accuracy

[SOURCE]


CategoricalAccuracy

@Metric.register("categorical_accuracy")
class CategoricalAccuracy(Metric):
 | def __init__(self, top_k: int = 1, tie_break: bool = False) -> None

Categorical Top-K accuracy. Assumes integer labels, with each item to be classified having a single correct class. Tie break enables equal distribution of scores among the classes with same maximum predicted scores.

supports_distributed

class CategoricalAccuracy(Metric):
 | ...
 | supports_distributed = True

__call__

class CategoricalAccuracy(Metric):
 | ...
 | def __call__(
 |     self,
 |     predictions: torch.Tensor,
 |     gold_labels: torch.Tensor,
 |     mask: Optional[torch.BoolTensor] = None
 | )

Parameters

  • predictions : torch.Tensor
    A tensor of predictions of shape (batch_size, ..., num_classes).
  • gold_labels : torch.Tensor
    A tensor of integer class label of shape (batch_size, ...). It must be the same shape as the predictions tensor without the num_classes dimension.
  • mask : torch.BoolTensor, optional (default = None)
    A masking tensor the same size as gold_labels.

get_metric

class CategoricalAccuracy(Metric):
 | ...
 | def get_metric(self, reset: bool = False) -> float

Returns

  • The accumulated accuracy.

reset

class CategoricalAccuracy(Metric):
 | ...
 | def reset(self)