PSNR

class deepinv.loss.metric.PSNR(max_pixel=1, **kwargs)[source]

Bases: Metric

Peak Signal-to-Noise Ratio (PSNR) metric.

Calculates the PSNR \(\text{PSNR}(\hat{x},x)\) where \(\hat{x}=\inverse{y}\). If the tensors have size (B, C, H, W), then the PSNR is computed as

\[\text{PSNR} = \frac{20}{B} \log_{10} \frac{\text{MAX}_I}{\sqrt{\|\hat{x}-x\|^2_2 / (CHW) }}\]

where \(\text{MAX}_I\) is the maximum possible pixel value of the image (e.g. 1.0 for a normalized image).

To set the max pixel on the fly (as is the case in fastMRI evaluation code), set max_pixel=None.

Note

By default, no reduction is performed in the batch dimension.

Example:

>>> import torch
>>> from deepinv.loss.metric import PSNR
>>> m = PSNR()
>>> x_net = x = torch.ones(3, 2, 8, 8) # B,C,H,W
>>> m(x_net, x)
tensor([80., 80., 80.])
Parameters:
  • max_pixel (float) – maximum pixel value. If None, uses max pixel value of x.

  • complex_abs (bool) – perform complex magnitude before passing data to metric function. If True, the data must either be of complex dtype or have size 2 in the channel dimension (usually the second dimension after batch).

  • reduction (str) – a method to reduce metric score over individual batch scores. mean: takes the mean, sum takes the sum, none or None no reduction will be applied (default).

  • norm_inputs (str) – normalize images before passing to metric. l2``normalizes by L2 spatial norm, ``min_max normalizes by min and max of each input.

metric(x_net, x, *args, **kwargs)[source]

Calculate metric on data.

Override this function to implement your own metric. Always include args and kwargs arguments.

Parameters:
  • x_net (torch.Tensor) – Reconstructed image \(\hat{x}=\inverse{y}\) of shape (B, ...) or (B, C, ...).

  • x (torch.Tensor) – Reference image \(x\) (optional) of shape (B, ...) or (B, C, ...).

Return torch.Tensor:

calculated metric, the tensor size might be (1,) or (B,).