• Docs >
  • Metrics >
  • torcheval.metrics.MulticlassPrecisionRecallCurve
Shortcuts

torcheval.metrics.MulticlassPrecisionRecallCurve

class torcheval.metrics.MulticlassPrecisionRecallCurve(*, num_classes: Optional[int] = None, device: Optional[device] = None)[source]

Returns precision-recall pairs and their corresponding thresholds for multi-class classification tasks. If a class is missing from the target tensor, its recall values are set to 1.0.

Its class version is torcheval.metrics.functional.multiclass_precision_recall_curve(). See also BinaryPrecisionRecallCurve, MultilabelPrecisionRecallCurve

Parameters:num_classes (int, Optional) – Number of classes. Set to the second dimension of the input if num_classes is None.

Examples:

>>> import torch
>>> from torcheval.metrics import MulticlassPrecisionRecallCurve
>>> metric = MulticlassPrecisionRecallCurve(num_classes=4)
>>> input = torch.tensor([[0.1, 0.1, 0.1, 0.1], [0.5, 0.5, 0.5, 0.5], [0.7, 0.7, 0.7, 0.7], [0.8, 0.8, 0.8, 0.8]])
>>> target = torch.tensor([0, 1, 2, 3])
>>> metric.update(input, target)
>>> metric.compute()
([tensor([0.2500, 0.0000, 0.0000, 0.0000, 1.0000]),
tensor([0.3333, 0.0000, 0.0000, 1.0000]),
tensor([0.5000, 0.0000, 1.0000]),
tensor([1., 1.])],
[tensor([1., 0., 0., 0., 0.]),
tensor([1., 0., 0., 0.]),
tensor([1., 0., 0.]),
tensor([1., 0.])],
[tensor([0.1000, 0.5000, 0.7000, 0.8000]),
tensor([0.5000, 0.7000, 0.8000]),
tensor([0.7000, 0.8000]),
tensor([0.8000])])
__init__(*, num_classes: Optional[int] = None, device: Optional[device] = None) 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 either torch.Tensor, a list of torch.Tensor, or a dictionary with torch.Tensor as values

Methods

__init__(*[, num_classes, device]) Initialize a metric object and its internal states.
compute()
returns:List of precision result. Each index indicates the result of a class.
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) Update states with the ground truth labels and predictions.

Attributes

device The last input device of Metric.to().

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources