TuckerTensorTrain.unstack

t3toolbox.tucker_tensor_train.TuckerTensorTrain.unstack()

def unstack(self): # returns an array-like structure of nested tuples containing TuckerTensorTrains

If this object contains multiple stacked T3s, this unstacks them into an array-like tree of nested tuples with the same “tree shape” as self.stack_shape.

Returns:

Unstacked TuckerTensorTrain.

Return type:

Array-like tree of nested tuples with TuckerTensorTrain leafs

See also

TuckerTensorTrain.stack(), TuckerTensorTrain.stack_shape

Examples

>>> import numpy as np
>>> import t3toolbox.tucker_tensor_train as t3
>>> np.random.seed(0)
>>> x = t3.TuckerTensorTrain.randn((14,15,16), (4,5,6), (1,3,2,1), stack_shape=(3,5))
>>> unstacked_x = x.unstack()
>>> print([len(s) for s in unstacked_x])    # nested tuples mirror stack_shape=(3,5)
[5, 5, 5]
>>> tucker13 = tuple([B[1,3] for B in x.tucker_cores])   # build slice (1,3) by hand
>>> tt13 = tuple([G[1,3] for G in x.tt_cores])
>>> x13 = t3.TuckerTensorTrain(tucker13, tt13)
>>> print(bool((x13 - unstacked_x[1][3]).norm() < 1e-11))   # matches unstacked leaf [1][3]
True