SheppLoganDataset#

class deepinv.utils.phantoms.SheppLoganDataset(size=128, n_data=1, transform=None, use_dict_output=False)[source]#

Bases: Dataset

Dataset for the single Shepp-Logan phantom. The dataset has length 1.

Parameters:

  • size (int) – Size of the phantom (square) image.

  • n_data (int) – Number of phantoms to generate per sample.

  • transform (Callable) – Transformation to apply to the output image.

  • use_dict_output (bool) – Whether to return output as dict with key “x” or a bare Tensor (default: False).