Shortcuts

Binned Recall At Fixed Precision

Module Interface

class torchmetrics.BinnedRecallAtFixedPrecision(num_classes, min_precision, thresholds=None, compute_on_step=None, **kwargs)[source]

Computes the higest possible recall value given the minimum precision thresholds provided.

Computation is performed in constant-memory by computing precision and recall for thresholds buckets/thresholds (evenly distributed between 0 and 1).

Forward accepts

  • preds (float tensor): (N, ...) (binary) or (N, C, ...) (multiclass) tensor with probabilities, where C is the number of classes.

  • target (long tensor): (N, ...) with integer labels

Parameters
  • num_classes (int) – integer with number of classes. Provide 1 for binary problems.

  • min_precision (float) – float value specifying minimum precision threshold.

  • thresholds (Union[int, Tensor, List[float], None]) – list or tensor with specific thresholds or a number of bins from linear sampling. It is used for computation will lead to more detailed curve and accurate estimates, but will be slower and consume more memory

  • compute_on_step (Optional[bool]) –

    Forward only calls update() and returns None if this is set to False.

    Deprecated since version v0.8: Argument has no use anymore and will be removed v0.9.

  • kwargs (Dict[str, Any]) – Additional keyword arguments, see Advanced metric settings for more info.

Raises

ValueError – If thresholds is not a list or tensor

Example (binary case):
>>> from torchmetrics import BinnedRecallAtFixedPrecision
>>> pred = torch.tensor([0, 0.2, 0.5, 0.8])
>>> target = torch.tensor([0, 1, 1, 0])
>>> average_precision = BinnedRecallAtFixedPrecision(num_classes=1, thresholds=10, min_precision=0.5)
>>> average_precision(pred, target)
(tensor(1.0000), tensor(0.1111))
Example (multiclass case):
>>> pred = torch.tensor([[0.75, 0.05, 0.05, 0.05, 0.05],
...                      [0.05, 0.75, 0.05, 0.05, 0.05],
...                      [0.05, 0.05, 0.75, 0.05, 0.05],
...                      [0.05, 0.05, 0.05, 0.75, 0.05]])
>>> target = torch.tensor([0, 1, 3, 2])
>>> average_precision = BinnedRecallAtFixedPrecision(num_classes=5, thresholds=10, min_precision=0.5)
>>> average_precision(pred, target)
(tensor([1.0000, 1.0000, 0.0000, 0.0000, 0.0000]),
tensor([6.6667e-01, 6.6667e-01, 1.0000e+06, 1.0000e+06, 1.0000e+06]))

Initializes internal Module state, shared by both nn.Module and ScriptModule.

compute()[source]

Returns float tensor of size n_classes.

Return type

Tuple[Tensor, Tensor]

Read the Docs v: v0.8.0
Versions
latest
stable
v0.8.0
v0.7.3
v0.7.2
v0.7.1
v0.7.0
v0.6.2
v0.6.1
v0.6.0
v0.5.1
v0.5.0
v0.4.1
v0.4.0
v0.3.2
v0.3.1
v0.3.0
v0.2.0
v0.1.0
Downloads
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.