torcheval.metrics.BinaryNormalizedEntropy

class torcheval.metrics.BinaryNormalizedEntropy(*, from_logits: bool = False, num_tasks: int = 1, device: device | None = None)

Compute the normalized binary cross entropy between predicted input and ground-truth binary target. Its functional version is torcheval.metrics.functional.binary_normalized_entropy()

Parameters:

• from_logits (bool) – A boolean indicator whether the predicted value y_pred is a floating-point logit value (i.e., value in [-inf, inf] when from_logits=True) or a probablity value (i.e., value in [0., 1.] when from_logits=False) Default value is False.

• num_tasks (int) – Number of tasks that need BinaryNormalizedEntropy calculation. Default value is 1. BinaryNormalizedEntropy for each task will be calculated independently.

Examples:

>>> import torch
>>> from torcheval.metrics import BinaryNormalizedEntropy

>>> metric = BinaryNormalizedEntropy()
>>> metric.update(torch.tensor([0.2, 0.3]), torch.tensor([1.0, 0.0]))
>>> metric.compute()
tensor([1.4183], dtype=torch.float64)

>>> metric = BinaryNormalizedEntropy()
>>> metric.update(torch.tensor([0.2, 0.3]), torch.tensor([1.0, 0.0]), torch.tensor([5.0, 1.0]))
>>> metric.compute()
tensor([3.1087], dtype=torch.float64)

>>> metric = BinaryNormalizedEntropy(from_logits = True)
>>> metric.update(tensor([-1.3863, -0.8473]), torch.tensor([1.0, 0.0]))
>>> metric.compute()
tensor([1.4183], dtype=torch.float64)

>>> metric = BinaryNormalizedEntropy(num_tasks=2)
>>> metric.update(torch.tensor([[0.2, 0.3], [0.5, 0.1]]), torch.tensor([[1.0, 0.0], [0.0, 1.0]]))
>>> metric.compute()
tensor([1.4183, 2.1610], dtype=torch.float64)

__init__(*, from_logits: bool = False, num_tasks: int = 1, device: device | None = None) → None

Initialize a metric object and its internal states.

Use self._add_state() to initialize state variables of your metric class. The state variables should be either torch.Tensor, a list of torch.Tensor, a dictionary with torch.Tensor as values, or a deque of torch.Tensor.

Methods

__init__(*[, from_logits, num_tasks, device])	Initialize a metric object and its internal states.
compute()	Return the normalized binary cross entropy.
load_state_dict(state_dict[, strict])	Loads metric state variables from state_dict.
merge_state(metrics)	Merge the metric state with its counterparts from other metric instances.
reset()	Reset the metric state variables to their default value.
state_dict()	Save metric state variables in state_dict.
to(device, *args, **kwargs)	Move tensors in metric state variables to device.
update(input, target, *[, weight])	Update the metric state with the total entropy, total number of examples and total number of positive targets.

Attributes

device

The last input device of Metric.to().