torcheval.metrics.PeakSignalNoiseRatio

class torcheval.metrics.PeakSignalNoiseRatio(data_range: Optional[float] = None, *, device: Optional[device] = None)

Compute the PSNR (Peak Signal to Noise Ratio) between two images. Its functional version is torcheval.metrics.functional.psnr

Parameters:data_range (float) – the range of the input images. Default: None. If None, the range computed from the target data (target.max() - targert.min()).

Examples:

>>> import torch
>>> from torcheval.metrics import PeakSignalNoiseRatio
>>> metric = PeakSignalNoiseRatio()
>>> input = torch.tensor([[0.1, 0.2], [0.3, 0.4]])
>>> target = input * 0.9
>>> metric.update(input, target)
>>> metric.compute()
tensor(19.8767)

__init__(data_range: Optional[float] = None, *, 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__([data_range, device])	Initialize a metric object and its internal states.
compute()	Return the peak signal-to-noise ratio.
load_state_dict(state_dict[, strict])	Loads metric state variables from state_dict.
merge_state(metrics)	Merge the metric state with its counterparts from other metric instances.
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 the metric state with new input.

Attributes

device

The last input device of Metric.to().