torcheval.metrics.Mean

class torcheval.metrics.Mean(*, device: Optional[device] = None)

Calculate the weighted mean value of all elements in all the input tensors. When weight is not provided, it calculates the unweighted mean. Its functional version is torcheval.functional.mean().

Examples:

>>> import torch
>>> from torcheval.metrics import Mean
>>> metric = Mean()
>>> metric.update(1)
>>> metric.update(torch.tensor([2, 3]))
>>> metric.compute()
tensor(2.)

>>> metric.update(torch.tensor(-1)).compute()
tensor(1.25)

>>> metric.reset()
>>> metric.update(torch.tensor(-1)).compute()
tensor(-1.)

>>> metric = Mean()
>>> metric.update(torch.tensor([2, 3]), torch.tensor([0.2, 0.8])).compute()
tensor(2.8)
>>> metric.update(torch.tensor([4, 5]), 0.5).compute()
tensor(3.65)
>>> metric.update(torch.tensor([6]), 2).compute()
tensor(4.825)

__init__(*, device: Optional[device] = 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, or a dictionary with torch.Tensor as values

Methods

__init__(*[, device])	Initialize a metric object and its internal states.
compute()	If no calls to update() are made before compute() is called, the function throws a warning and returns 0.0.
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, *[, weight])	Compute weighted mean.

Attributes

device

The last input device of Metric.to().