RandomMaskGenerator

class deepinv.physics.generator.RandomMaskGenerator(img_size: Tuple, acceleration: int = 4, center_fraction: float | None = None, rng: Generator | None = None, device='cpu', *args, **kwargs)

Bases: BaseMaskGenerator

Generator for MRI Cartesian acceleration masks using random uniform undersampling.

Generate a mask of vertical lines for MRI acceleration with fixed sampling in low frequencies (center of k-space) and random uniform undersampling in the high frequencies.

Supports k-t sampling, where the mask is selected randomly across time.

The mask is repeated across channels and randomly varies across batch dimension.

For parameter descriptions see deepinv.physics.generator.mri.BaseMaskGenerator

---

Examples:

Random k-t mask generator for a 8x64x64 video:

>>> from deepinv.physics.generator import RandomMaskGenerator
>>> generator = RandomMaskGenerator((2, 8, 64, 64), acceleration=8, center_fraction=0.04) # C, T, H, W
>>> params = generator.step(batch_size=1)
>>> mask = params["mask"]
>>> mask.shape
torch.Size([1, 2, 8, 64, 64])

get_pdf() → Tensor

Create one-dimensional uniform probability density function across columns, ignoring any fixed sampling columns.

Return torch.Tensor:

unnormalised 1D vector representing pdf evaluated across mask columns.

sample_mask(mask: Tensor) → Tensor

Given empty mask, sample lines according to child class sampling strategy.

This must be implemented in child classes. Time dimension is specified but can be ignored if needed.

Parameters:

mask (torch.Tensor) – empty mask of shape (B, C, T, H, W)

Return torch.Tensor:

sampled mask of shape (B, C, T, H, W)

Examples using RandomMaskGenerator:

A tour of forward sensing operators

A tour of forward sensing operators

Self-supervised MRI reconstruction with Artifact2Artifact

Self-supervised MRI reconstruction with Artifact2Artifact