`tltorch`.TuckerTensor¶

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

Tucker Factorization

Parameters:

Attributes:

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

Methods

`from_tensor`(tensor[, rank, fixed_rank_modes])	Create a factorized tensor by decomposing a dense tensor
`init_from_tensor`(tensor[, unsqueezed_modes, ...])	Initialize the tensor factorization from a tensor
`new`(shape, rank[, fixed_rank_modes, device, ...])	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

classmethod new(shape, rank, fixed_rank_modes=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', fixed_rank_modes=None, **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:

init_from_tensor(tensor, unsqueezed_modes=None, unsqueezed_init='average', **kwargs)[source]¶

Initialize the tensor factorization from a tensor

Parameters:

tensortorch.Tensor: full tensor to decompose
unsqueezed_modesint list: list of modes for which the rank is 1 that don’t correspond to a mode in the full tensor essentially we are adding a new dimension for which the core has dim 1, and that is not initialized through decomposition. Instead first tensor is decomposed into the other factors. The unsqueezed factors are then added and initialized e.g. with 1/dim[i]
unsqueezed_init‘average’ or float: if unsqueezed_modes, this is how the added “unsqueezed” factors will be initialized if ‘average’, then unsqueezed_factor[i] will have value 1/tensor.shape[i]

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:

tltorch.TuckerTensor¶