`tltorch`.DenseTensor

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

Dense tensor

Attributes:

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

Methods

`from_tensor`(tensor[, rank])	Create a factorized tensor by decomposing a dense tensor
`new`(shape[, rank, device, dtype])	Main way to create a factorized tensor
`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(shape, rank=None, device=None, dtype=None, **kwargs)[source]

Main way to create a factorized tensor

Parameters:

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

Returns:

Raises:

Examples

Create a Tucker tensor of shape (3, 4, 2) with half the parameters as a dense tensor would:

>>> tucker_tensor = FactorizedTensor.new((3, 4, 2)), rank=0.5, factorization='tucker')

classmethod from_tensor(tensor, rank='same', **kwargs)[source]

Create a factorized tensor by decomposing a dense tensor

Parameters:

tensortorch.tensor: tensor to factorize
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:

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: