Error Relative Global Dim. Synthesis (ERGAS)¶

Module Interface¶

class torchmetrics.image.ergas.ErrorRelativeGlobalDimensionlessSynthesis(ratio=4, reduction='elementwise_mean', **kwargs)[source]

Calculates Relative dimensionless global error synthesis (ERGAS) is used to calculate the accuracy of Pan sharpened image considering normalized average error of each band of the result image (ErrorRelativeGlobalDimensionlessSynthesis).

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

preds (Tensor): Predictions from model
target (Tensor): Ground truth values

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

ergas (Tensor): if reduction!='none' returns float scalar tensor with average ERGAS value over sample else returns tensor of shape (N,) with ERGAS values per sample

Parameters

ratio¶ (Union[int, float]) – ratio of high resolution to low resolution
reduction¶ (Literal[‘elementwise_mean’, ‘sum’, ‘none’, None]) –
a method to reduce metric score over labels.
- 'elementwise_mean': takes the mean (default)
- 'sum': takes the sum
- 'none' or None: no reduction will be applied
kwargs¶ (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Example

>>> import torch
>>> from torchmetrics import ErrorRelativeGlobalDimensionlessSynthesis
>>> preds = torch.rand([16, 1, 16, 16], generator=torch.manual_seed(42))
>>> target = preds * 0.75
>>> ergas = ErrorRelativeGlobalDimensionlessSynthesis()
>>> torch.round(ergas(preds, target))
tensor(154.)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

Functional Interface¶

torchmetrics.functional.error_relative_global_dimensionless_synthesis(preds, target, ratio=4, reduction='elementwise_mean')[source]

Erreur Relative Globale Adimensionnelle de Synthèse.

Parameters

preds¶ (Tensor) – estimated image
target¶ (Tensor) – ground truth image
ratio¶ (Union[int, float]) – ratio of high resolution to low resolution
reduction¶ (Literal[‘elementwise_mean’, ‘sum’, ‘none’, None]) –
a method to reduce metric score over labels.
- 'elementwise_mean': takes the mean (default)
- 'sum': takes the sum
- 'none' or None: no reduction will be applied

Return type

Tensor

Returns

Tensor with RelativeG score

Raises

TypeError – If preds and target don’t have the same data type.
ValueError – If preds and target don’t have BxCxHxW shape.

Example

>>> from torchmetrics.functional import error_relative_global_dimensionless_synthesis
>>> preds = torch.rand([16, 1, 16, 16], generator=torch.manual_seed(42))
>>> target = preds * 0.75
>>> ergds = error_relative_global_dimensionless_synthesis(preds, target)
>>> torch.round(ergds)
tensor(154.)

References

[1] Qian Du; Nicholas H. Younan; Roger King; Vijay P. Shah, “On the Performance Evaluation of Pan-Sharpening Techniques” in IEEE Geoscience and Remote Sensing Letters, vol. 4, no. 4, pp. 518-522, 15 October 2007, doi: 10.1109/LGRS.2007.896328.