torcheval.metrics.BinaryAUROC¶
-
class
torcheval.metrics.
BinaryAUROC
(*, num_tasks: int = 1, device: Optional[device] = None, use_fbgemm: Optional[bool] = False)[source]¶ Compute AUROC, which is the area under the ROC Curve, for binary classification. AUROC is defined as the area under the Receiver Operating Curve, a plot with x=false positive rate y=true positive rate. The points on the curve are sampled from the data given and the area is computed using the trapezoid method.
Multiple tasks are supported for Binary AUROC. A two-dimensional vector can given for the predicted values (inputs) and targets. This gives equivalent results to having one BinaryAUROC object for each row.
Its functional version is
torcheval.metrics.functional.binary_auroc()
. See alsoMulticlassAUROC
Examples:
>>> import torch >>> from torcheval.metrics import BinaryAUROC >>> metric = BinaryAUROC() >>> input = torch.tensor([0.1, 0.5, 0.7, 0.8]) >>> target = torch.tensor([1, 0, 1, 1]) >>> metric.update(input, target) >>> metric.compute() tensor([0.6667]) >>> input = torch.tensor([1, 1, 1, 0]) >>> target = torch.tensor([1, 1, 1, 0]) >>> metric.update(input, target) >>> metric.compute() tensor([1.0]) >>> metric = BinaryAUROC(num_tasks=2) >>> input = torch.tensor([[1, 1, 1, 0], [0.1, 0.5, 0.7, 0.8]]) >>> target = torch.tensor([[1, 0, 1, 0], [1, 0, 1, 1]]) >>> metric.update(input, target) >>> metric.compute() tensor([0.7500, 0.6667])
-
__init__
(*, num_tasks: int = 1, device: Optional[device] = None, use_fbgemm: Optional[bool] = False) None [source]¶ 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 eithertorch.Tensor
, a list oftorch.Tensor
, or a dictionary withtorch.Tensor
as values
Methods
__init__
(*[, num_tasks, device, use_fbgemm])Initialize a metric object and its internal states. compute
()Return AUROC. load_state_dict
(state_dict[, strict])Loads metric state variables from state_dict. merge_state
(metrics)Implement this method to update the current metric's state variables to be the merged states of the current metric and input metrics. 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 states with the ground truth labels and predictions. Attributes
device
The last input device of Metric.to()
.-