TuckerTensorTrain.stack#

static t3toolbox.tucker_tensor_train.TuckerTensorTrain.stack(xx)#

def stack(
        xx, # array-like structure of nested tuples containing TuckerTensorTrains
) -> 'TuckerTensorTrain':  # (stacked_tucker_cores, stacked_tt_cores)

Stacks an array-like tree of TuckerTensorTrains into one stacked TuckerTensorTrain.

Parameters:: xx (Array-like tree of nested tuples with TuckerTensorTrain leafs) – TuckerTensorTrains to be stacked. All TuckerTensorTrains must have the same shape and ranks.
Returns:: Stacked TuckerTensorTrain.
Return type:: TuckerTensorTrain

Examples

>>> import numpy as np
>>> import t3toolbox.tucker_tensor_train as t3
>>> import t3toolbox.corewise as cw
>>> x = t3.TuckerTensorTrain.randn((14,15,16), (4,6,2), (1,4,2,1), stack_shape=(3,5))
>>> xx = x.unstack()
>>> print(len(xx))
3
>>> print(len(xx[0]))
5
>>> x2 = t3.TuckerTensorTrain.stack(xx)
>>> print(cw.corewise_norm(cw.corewise_sub(x.data, x2.data)))
0.0