Running Sum¶

Module Interface¶

class torchmetrics.aggregation.RunningSum(window=5, nan_strategy='warn', **kwargs)[source]¶

Aggregate a stream of value into their sum over a running window.

Using this metric compared to SumMetric allows for calculating metrics over a running window of values, instead of the whole history of values. This is beneficial when you want to get a better estimate of the metric during training and don’t want to wait for the whole training to finish to get epoch level estimates.

As input to forward and update the metric accepts the following input

value (float or Tensor): a single float or an tensor of float values with arbitrary shape (...,).

As output of forward and compute the metric returns the following output

agg (Tensor): scalar float tensor with aggregated sum over all inputs received

Parameters:

window¶ (int) – The size of the running window.
nan_strategy¶ (Union[str, float]) – options: - 'error': if any nan values are encountered will give a RuntimeError - 'warn': if any nan values are encountered will give a warning and continue - 'ignore': all nan values are silently removed - a float: if a float is provided will impute any nan values with this value
kwargs¶ (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Raises:

ValueError – If nan_strategy is not one of error, warn, ignore or a float

Example

>>> from torch import tensor
>>> from torchmetrics.aggregation import RunningSum
>>> metric = RunningSum(window=3)
>>> for i in range(6):
...     current_val = metric(tensor([i]))
...     running_val = metric.compute()
...     total_val = tensor(sum(list(range(i+1))))  # total sum over all samples
...     print(f"{current_val=}, {running_val=}, {total_val=}")
current_val=tensor(0.), running_val=tensor(0.), total_val=tensor(0)
current_val=tensor(1.), running_val=tensor(1.), total_val=tensor(1)
current_val=tensor(2.), running_val=tensor(3.), total_val=tensor(3)
current_val=tensor(3.), running_val=tensor(6.), total_val=tensor(6)
current_val=tensor(4.), running_val=tensor(9.), total_val=tensor(10)
current_val=tensor(5.), running_val=tensor(12.), total_val=tensor(15)