Root Mean Squared Error Using Sliding Window

Module Interface

class torchmetrics.image.RootMeanSquaredErrorUsingSlidingWindow(window_size=8, **kwargs)

Computes Root Mean Squared Error (RMSE) using sliding window.

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

• preds (Tensor): Predictions from model of shape (N,C,H,W)

• target (Tensor): Ground truth values of shape (N,C,H,W)

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

• rmse_sw (Tensor): returns float scalar tensor with average RMSE-SW value over sample

Parameters:

• window_size (int) – Sliding window used for rmse calculation

• kwargs (Dict[str, Any]) – Additional keyword arguments, see Advanced metric settings for more info.

Example

>>> from torch import rand
>>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
>>> preds = rand(4, 3, 16, 16)
>>> target = rand(4, 3, 16, 16)
>>> rmse_sw = RootMeanSquaredErrorUsingSlidingWindow()
>>> rmse_sw(preds, target)
tensor(0.4158)

Raises:

ValueError – If window_size is not a positive integer.

plot(val=None, ax=None)

Plot a single or multiple values from the metric.

Parameters:

• val (Union[Tensor, Sequence[Tensor], None]) – Either a single result from calling metric.forward or metric.compute or a list of these results. If no value is provided, will automatically call metric.compute and plot that result.

• ax (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

Tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value
>>> import torch
>>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
>>> metric = RootMeanSquaredErrorUsingSlidingWindow()
>>> metric.update(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16))
>>> fig_, ax_ = metric.plot()

>>> # Example plotting multiple values
>>> import torch
>>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
>>> metric = RootMeanSquaredErrorUsingSlidingWindow()
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16)))
>>> fig_, ax_ = metric.plot(values)

Functional Interface

torchmetrics.functional.image.root_mean_squared_error_using_sliding_window(preds, target, window_size=8, return_rmse_map=False)

Compute Root Mean Squared Error (RMSE) using sliding window.

Parameters:

• preds (Tensor) – Deformed image

• target (Tensor) – Ground truth image

• window_size (int) – Sliding window used for rmse calculation

• return_rmse_map (bool) – An indication whether the full rmse reduced image should be returned.

Return type:

Union[Tensor, None, Tuple[Optional[Tensor], Tensor]]

Returns:

RMSE using sliding window (Optionally) RMSE map

Example

>>> from torch import rand
>>> from torchmetrics.functional.image import root_mean_squared_error_using_sliding_window
>>> preds = rand(4, 3, 16, 16)
>>> target = rand(4, 3, 16, 16)
>>> root_mean_squared_error_using_sliding_window(preds, target)
tensor(0.4158)

Raises:

ValueError – If window_size is not a positive integer.