Shift

class deepinv.transform.Shift(*args, shift_max=1.0, **kwargs)[source]

Bases: Transform

Fast integer 2D translations.

Generates n_trans randomly shifted versions of 2D images with circular padding.

See deepinv.transform.Transform for further details and examples.

Parameters:
  • shift_max (float) – maximum shift as fraction of total height/width.

  • n_trans (int) – number of transformed versions generated per input image.

  • rng (torch.Generator) – random number generator, if None, use torch.Generator(), defaults to None

Examples using Shift:

Image transforms for equivariance & augmentations

Image transforms for equivariance & augmentations

Image transformations for Equivariant Imaging

Image transformations for Equivariant Imaging