MatchingData

class MatchingData(target, template, template_mask=None, target_mask=None, invert_target=False, rotations=None)

Bases: object

Contains data required for template matching.

Parameters:

targetnp.ndarray or tme.density.Density

Target data.

templatenp.ndarray or tme.density.Density

Template data.

target_masknp.ndarray or tme.density.Density, optional

Target mask data.

template_masknp.ndarray or tme.density.Density, optional

Template mask data.

invert_targetbool, optional

Whether to invert the target before template matching.

rotations: np.ndarray, optional

Template rotations to sample. Can be a single (d, d) or a stack (n, d, d) of rotation matrices where d is the dimension of the template.

Examples

The following achieves the minimal definition of a MatchingData instance.

>>> import numpy as np
>>> from tme.matching_data import MatchingData
>>> target = np.random.rand(50,40,60)
>>> template = target[15:25, 10:20, 30:40]
>>> matching_data = MatchingData(target=target, template=template)

Conversion

MatchingData.to_backend()

Transfer and convert types of internal data arrays to the current backend.

Attributes and underlying data

MatchingData.target	Return the target.
MatchingData.template	Return the reversed template.
MatchingData.target_mask	Return the target mask.
MatchingData.template_mask	Return the reversed template mask.
MatchingData.rotations	Return stored rotation matrices.

Utilities

MatchingData.subset_array(arr, arr_slice, ...)	Extract a subset of the input array according to the given slice and apply padding.
MatchingData.subset_by_slice([target_slice, ...])	Subset class instance based on slices.
MatchingData.set_matching_dimension([...])	Configure batch dimensions for target and template