Shortcuts

Multi-Scale SSIM

Module Interface

class torchmetrics.MultiScaleStructuralSimilarityIndexMeasure(gaussian_kernel=True, kernel_size=11, sigma=1.5, reduction='elementwise_mean', data_range=None, k1=0.01, k2=0.03, betas=(0.0448, 0.2856, 0.3001, 0.2363, 0.1333), normalize='relu', **kwargs)[source]

Compute MultiScaleSSIM, Multi-scale Structural Similarity Index Measure, which is a generalization of Structural Similarity Index Measure by incorporating image details at different resolution scores.

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

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

Parameters
  • gaussian_kernel (bool) – If True (default), a gaussian kernel is used, if false a uniform kernel is used

  • kernel_size (Union[int, Sequence[int]]) – size of the gaussian kernel

  • sigma (Union[float, Sequence[float]]) – Standard deviation of the gaussian kernel

  • 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 (Optional[float]) – Range of the image. If None, it is determined from the image (max - min)

  • k1 (float) – Parameter of structural similarity index measure.

  • k2 (float) – Parameter of structural similarity index measure.

  • betas (Tuple[float, ...]) – Exponent parameters for individual similarities and contrastive sensitivies returned by different image resolutions.

  • normalize (Literal[‘relu’, ‘simple’, None]) – When MultiScaleStructuralSimilarityIndexMeasure loss is used for training, it is desirable to use normalizes to improve the training stability. This normalize argument is out of scope of the original implementation [1], and it is adapted from https://github.com/jorge-pessoa/pytorch-msssim instead.

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

Returns

Tensor with Multi-Scale SSIM score

Raises
  • ValueError – If kernel_size is not an int or a Sequence of ints with size 2 or 3.

  • ValueError – If betas is not a tuple of floats with lengt 2.

  • ValueError – If normalize is neither None, ReLU nor simple.

Example

>>> from torchmetrics import MultiScaleStructuralSimilarityIndexMeasure
>>> import torch
>>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42))
>>> target = preds * 0.75
>>> ms_ssim = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0)
>>> ms_ssim(preds, target)
tensor(0.9627)

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

Functional Interface

torchmetrics.functional.multiscale_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, betas=(0.0448, 0.2856, 0.3001, 0.2363, 0.1333), normalize='relu')[source]

Compute MultiScaleSSIM, Multi-scale Structual Similarity Index Measure, which is a generalization of Structual Similarity Index Measure by incorporating image details at different resolution scores.

Parameters
  • preds (Tensor) – Predictions from model of shape [N, C, H, W]

  • target (Tensor) – Ground truth values of shape [N, C, H, W]

  • kernel_size (Union[int, Sequence[int]]) – size of the gaussian kernel

  • sigma (Union[float, Sequence[float]]) – Standard deviation of the gaussian kernel

  • 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 (Optional[float]) – Range of the image. If None, it is determined from the image (max - min)

  • k1 (float) – Parameter of structural similarity index measure.

  • k2 (float) – Parameter of structural similarity index measure.

  • betas (Tuple[float, ...]) – Exponent parameters for individual similarities and contrastive sensitivies returned by different image resolutions.

  • normalize (Optional[Literal[‘relu’, ‘simple’]]) – When MultiScaleSSIM loss is used for training, it is desirable to use normalizes to improve the training stability. This normalize argument is out of scope of the original implementation [1], and it is adapted from https://github.com/jorge-pessoa/pytorch-msssim instead.

Return type

Tensor

Returns

Tensor with Multi-Scale 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 import multiscale_structural_similarity_index_measure
>>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42))
>>> target = preds * 0.75
>>> multiscale_structural_similarity_index_measure(preds, target, data_range=1.0)
tensor(0.9627)

References

[1] Multi-Scale Structural Similarity For Image Quality Assessment by Zhou Wang, Eero P. Simoncelli and Alan C. Bovik MultiScaleSSIM

Read the Docs v: latest
Versions
latest
stable
v0.11.1
v0.11.0
v0.10.3
v0.10.2
v0.10.1
v0.10.0
v0.9.3
v0.9.2
v0.9.1
v0.9.0
v0.8.2
v0.8.1
v0.8.0
v0.7.3
v0.7.2
v0.7.1
v0.7.0
v0.6.2
v0.6.1
v0.6.0
v0.5.1
v0.5.0
v0.4.1
v0.4.0
v0.3.2
v0.3.1
v0.3.0
v0.2.0
v0.1.0
Downloads
pdf
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.