mindspore.nn.MSSSIM

class mindspore.nn.MSSSIM(max_val=1.0, power_factors=(0.0448, 0.2856, 0.3001, 0.2363, 0.1333), filter_size=11, filter_sigma=1.5, k1=0.01, k2=0.03)[source]

Returns MS-SSIM index between two images.

Its implementation is based on Wang, Zhou, Eero P. Simoncelli, and Alan C. Bovik. Multiscale structural similarity for image quality assessment. Signals, Systems and Computers, 2004.

\[\begin{split}l(x,y)&=\frac{2\mu_x\mu_y+C_1}{\mu_x^2+\mu_y^2+C_1}, C_1=(K_1L)^2.\\ c(x,y)&=\frac{2\sigma_x\sigma_y+C_2}{\sigma_x^2+\sigma_y^2+C_2}, C_2=(K_2L)^2.\\ s(x,y)&=\frac{\sigma_{xy}+C_3}{\sigma_x\sigma_y+C_3}, C_3=C_2/2.\\ MSSSIM(x,y)&=l^\alpha_M*{\prod_{1\leq j\leq M} (c^\beta_j*s^\gamma_j)}.\end{split}\]
Parameters

  • max_val (Union[int, float]) – The dynamic range of the pixel values (255 for 8-bit grayscale images). Default: 1.0.

  • power_factors (Union[tuple, list]) – Iterable of weights for each scal e. Default: (0.0448, 0.2856, 0.3001, 0.2363, 0.1333). Default values obtained by Wang et al.

  • filter_size (int) – The size of the Gaussian filter. Default: 11.

  • filter_sigma (float) – The standard deviation of Gaussian kernel. Default: 1.5.

  • k1 (float) – The constant used to generate c1 in the luminance comparison function. Default: 0.01.

  • k2 (float) – The constant used to generate c2 in the contrast comparison function. Default: 0.03.

Inputs:

  • img1 (Tensor) - The first image batch with format ‘NCHW’. It must be the same shape and dtype as img2.

  • img2 (Tensor) - The second image batch with format ‘NCHW’. It must be the same shape and dtype as img1.

Outputs:

Tensor, the value is in range [0, 1]. It is a 1-D tensor with shape N, where N is the batch num of img1.

Raises

  • TypeError – If max_val is neither int nor float.

  • TypeError – If power_factors is neither tuple nor list.

  • TypeError – If k1, k2 or filter_sigma is not a float.

  • TypeError – If filter_size is not an int.

  • ValueError – If max_val or filter_sigma is less than or equal to 0.

  • ValueError – If filter_size is less than 0.

  • ValueError – If length of shape of img1 or img2 is not equal to 4.

Supported Platforms:

Ascend

Examples

>>> import numpy as np
>>> import mindspore.nn as nn
>>> from mindspore import Tensor
>>> net = nn.MSSSIM(power_factors=(0.033, 0.033, 0.033))
>>> img1 = Tensor(np.ones((1, 3, 128, 128)).astype(np.float32))
>>> img2 = Tensor(np.ones((1, 3, 128, 128)).astype(np.float32))
>>> output = net(img1, img2)
>>> print(output)
[1.]