TuckerTensorTrain.segment

t3toolbox.tucker_tensor_train.TuckerTensorTrain.segment(start, stop)

def segment(
        self,
        start: int,  # requires stop > start
        stop:  int,  # requires stop > start
) -> 'TuckerTensorTrain':

Extract contiguous segment of this TuckerTensorTrain. Segments must have length at least one.

Parameters:

• start (int) – Starting index for segment. Requires stop > start.

• stop (int) – Stopping index for segment. Requires stop > start.

Returns:

Segment of this TuckerTensorTrain, with shape=(N(start), ..., N(stop-1)).

Return type:

TuckerTensorTrain

Raises:

ValueError – If stop <= start.

See also

TuckerTensorTrain.concatenate()

Examples

>>> import numpy as np
>>> import t3toolbox.tucker_tensor_train as t3
>>> randn = np.random.randn
>>> tucker_cores = (randn(4,14), randn(5,15), randn(6,16), randn(7,17))
>>> tt_cores = (randn(2,4,3), randn(3,5,2), randn(2,6,2), randn(2,7,4))
>>> x = t3.TuckerTensorTrain(tucker_cores, tt_cores)
>>> x01 = x.segment(1,3)
>>> print(x01.core_shapes)
(((5, 15), (6, 16)), ((3, 5, 2), (2, 6, 2)))