Toggle Light / Dark / Auto color theme

Toggle table of contents sidebar

anomalib.pre_processing.transforms.custom

Dataset Utils.

Module Contents

Classes

Denormalize	Denormalize Torch Tensor into np image format.
ToNumpy	Convert Tensor into Numpy Array.

class anomalib.pre_processing.transforms.custom.Denormalize(mean: Optional[List[float]] = None, std: Optional[List[float]] = None)

Denormalize Torch Tensor into np image format.

__call__(self, tensor: torch.Tensor) → numpy.ndarray

Denormalize the input.

Parameters

tensor (Tensor) – Input tensor image (C, H, W)

Returns

Denormalized numpy array (H, W, C).

__repr__(self)

Representational string.

class anomalib.pre_processing.transforms.custom.ToNumpy

Convert Tensor into Numpy Array.

__call__(self, tensor: torch.Tensor, dims: Optional[Tuple[int, Ellipsis]] = None) → numpy.ndarray

Convert Tensor into Numpy Array.

Parameters

• tensor (Tensor) – Tensor to convert. Input tensor in range 0-1.

• dims (Optional[Tuple[int, ...]], optional) – Convert dimensions from torch to numpy format. Tuple corresponding to axis permutation from torch tensor to numpy array. Defaults to None.

Returns

Converted numpy ndarray.

__repr__(self) → str

Representational string.