torcheval.metrics.PeakSignalNoiseRatio¶
-
class
torcheval.metrics.
PeakSignalNoiseRatio
(data_range: Optional[float] = None, *, device: Optional[device] = None)[source]¶ 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 [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 eithertorch.Tensor
, a list oftorch.Tensor
, or a dictionary withtorch.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()
.-