Decolorize

class deepinv.physics.Decolorize(device='cpu', **kwargs)[source]

Bases: DecomposablePhysics

Converts RGB images to grayscale.

Follows the rec601 convention.

Images must be tensors with 3 colour (RGB) channels, i.e. [,3,,*] The measurements are grayscale images.

Parameters:

device (str) – device to use.


Examples:

Decolorize a 3x3 image:

>>> from deepinv.physics import Decolorize
>>> x = torch.ones(1, 3, 3, 3) # Define constant 3x3 RGB image
>>> physics = Decolorize()
>>> physics(x)
tensor([[[[1.0000, 1.0000, 1.0000],
          [1.0000, 1.0000, 1.0000],
          [1.0000, 1.0000, 1.0000]]]], grad_fn=<MulBackward0>)

Examples using Decolorize:

Stacking and concatenating forward operators.

Stacking and concatenating forward operators.

A tour of forward sensing operators

A tour of forward sensing operators