`tltorch`.BlockTT¶

class tltorch.BlockTT(*args, **kwargs)[source]¶

Attributes:

decomposition: Returns the factors and parameters composing the tensor in factorized form

Methods

`from_tensor`(tensor, tensorized_shape, rank, ...)	Create a factorized tensor by decomposing a full tensor
`new`(tensorized_shape, rank[, device, dtype])	Main way to create a Tensorized Matrix
`normal_`([mean, std])	Inialize the factors of the factorization such that the reconstruction follows a Gaussian distribution
`to_tensor`()	Reconstruct the full tensor from its factorized form

init_from_tensor

classmethod new(tensorized_shape, rank, device=None, dtype=None, **kwargs)[source]¶

Main way to create a Tensorized Matrix

Parameters:

tensorized_shapetuple[int]
rankint, ‘same’ or float: rank of the decomposition
n_matricestuple or int, default is (): if not (), indicates how many matrices have to be jointly factorized
factorization{‘CP’, ‘TT’, ‘Tucker’}, optional: Tensor factorization to use to decompose the tensor, by default ‘CP’

Returns:

Raises:

property decomposition¶: Returns the factors and parameters composing the tensor in factorized form

normal_(mean=0, std=1)[source]¶

Inialize the factors of the factorization such that the reconstruction follows a Gaussian distribution

Parameters:

Returns:

classmethod from_tensor(tensor, tensorized_shape, rank, **kwargs)[source]¶

Create a factorized tensor by decomposing a full tensor

Parameters:

tensortorch.tensor: tensor to factorize
shapetuple[int]: shape of the factorized tensor to create
rankint, ‘same’ or float: rank of the decomposition
factorization{‘CP’, ‘TT’, ‘Tucker’}, optional: Tensor factorization to use to decompose the tensor, by default ‘CP’

Returns:

Raises:

tltorch.BlockTT¶