Structural Similarity Index Measure (SSIM)¶

Module Interface¶

class torchmetrics.image.StructuralSimilarityIndexMeasure(gaussian_kernel=True, sigma=1.5, kernel_size=11, reduction='elementwise_mean', data_range=None, k1=0.01, k2=0.03, return_full_image=False, return_contrast_sensitivity=False, **kwargs)[source]¶

Compute Structural Similarity Index Measure (SSIM).

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

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

Parameters:

preds¶ – estimated image
target¶ – ground truth image
gaussian_kernel¶ (bool) – If True (default), a gaussian kernel is used, if False a uniform kernel is used
sigma¶ (Union[float, Sequence[float]]) – Standard deviation of the gaussian kernel, anisotropic kernels are possible. Ignored if a uniform kernel is used
kernel_size¶ (Union[int, Sequence[int]]) – the size of the uniform kernel, anisotropic kernels are possible. Ignored if a Gaussian kernel is used
reduction¶ (Literal['elementwise_mean', 'sum', 'none', None]) –
a method to reduce metric score over individual batch scores
- 'elementwise_mean': takes the mean
- 'sum': takes the sum
- 'none' or None: no reduction will be applied
data_range¶ (Union[float, tuple[float, float], None]) – the range of the data. If None, it is determined from the data (max - min). If a tuple is provided then the range is calculated as the difference and input is clamped between the values.
k1¶ (float) – Parameter of SSIM.
k2¶ (float) – Parameter of SSIM.
return_full_image¶ (bool) – If true, the full ssim image is returned as a second argument. Mutually exclusive with return_contrast_sensitivity
return_contrast_sensitivity¶ (bool) – If true, the constant term is returned as a second argument. The luminance term can be obtained with luminance=ssim/contrast Mutually exclusive with return_full_image
kwargs¶ (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Example

>>> import torch
>>> from torchmetrics.image import StructuralSimilarityIndexMeasure
>>> preds = torch.rand([3, 3, 256, 256])
>>> target = preds * 0.75
>>> ssim = StructuralSimilarityIndexMeasure(data_range=1.0)
>>> ssim(preds, target)
tensor(0.9219)

plot(val=None, ax=None)[source]¶

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 StructuralSimilarityIndexMeasure
>>> preds = torch.rand([3, 3, 256, 256])
>>> target = preds * 0.75
>>> metric = StructuralSimilarityIndexMeasure(data_range=1.0)
>>> metric.update(preds, target)
>>> fig_, ax_ = metric.plot()

>>> # Example plotting multiple values
>>> import torch
>>> from torchmetrics.image import StructuralSimilarityIndexMeasure
>>> preds = torch.rand([3, 3, 256, 256])
>>> target = preds * 0.75
>>> metric = StructuralSimilarityIndexMeasure(data_range=1.0)
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(preds, target))
>>> fig_, ax_ = metric.plot(values)

Functional Interface¶

torchmetrics.functional.image.structural_similarity_index_measure(preds, target, gaussian_kernel=True, sigma=1.5, kernel_size=11, reduction='elementwise_mean', data_range=None, k1=0.01, k2=0.03, return_full_image=False, return_contrast_sensitivity=False)[source]¶

Compute Structural Similarity Index Measure.

Parameters:

preds¶ (Tensor) – estimated image
target¶ (Tensor) – ground truth image
gaussian_kernel¶ (bool) – If true (default), a gaussian kernel is used, if false a uniform kernel is used
sigma¶ (Union[float, Sequence[float]]) – Standard deviation of the gaussian kernel, anisotropic kernels are possible. Ignored if a uniform kernel is used
kernel_size¶ (Union[int, Sequence[int]]) – the size of the uniform kernel, anisotropic kernels are possible. Ignored if a Gaussian kernel is used
reduction¶ (Literal['elementwise_mean', 'sum', 'none', None]) –
a method to reduce metric score over labels.
- 'elementwise_mean': takes the mean
- 'sum': takes the sum
- 'none' or None: no reduction will be applied
data_range¶ (Union[float, tuple[float, float], None]) – the range of the data. If None, it is determined from the data (max - min). If a tuple is provided then the range is calculated as the difference and input is clamped between the values.
k1¶ (float) – Parameter of SSIM.
k2¶ (float) – Parameter of SSIM.
return_full_image¶ (bool) – If true, the full ssim image is returned as a second argument. Mutually exclusive with return_contrast_sensitivity
return_contrast_sensitivity¶ (bool) – If true, the constant term is returned as a second argument. The luminance term can be obtained with luminance=ssim/contrast Mutually exclusive with return_full_image

Return type:

Union[Tensor, tuple[Tensor, Tensor]]

Returns:

Tensor with SSIM score

Raises:

TypeError – If preds and target don’t have the same data type.
ValueError – If preds and target don’t have BxCxHxW shape.
ValueError – If the length of kernel_size or sigma is not 2.
ValueError – If one of the elements of kernel_size is not an odd positive number.
ValueError – If one of the elements of sigma is not a positive number.

Example

>>> from torchmetrics.functional.image import structural_similarity_index_measure
>>> preds = torch.rand([3, 3, 256, 256])
>>> target = preds * 0.75
>>> structural_similarity_index_measure(preds, target)
tensor(0.9219)