torcheval.metrics.StructuralSimilarity¶
-
class
torcheval.metrics.
StructuralSimilarity
(device: Optional[device] = None)[source]¶ Compute the structural similarity index (SSIM) between two sets of images.
Args: device (torch.device): The device where the computations will be performed.
If None, the default device will be used.-
__init__
(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__
([device])Initialize a metric object and its internal states. compute
()Compute the mean of the mssim across all comparisons. 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
(images_1, images_2)Update the metric state with new input. Attributes
device
The last input device of Metric.to()
.-