UniformTuckerTensorTrain.load

static t3toolbox.uniform_tucker_tensor_train.UniformTuckerTensorTrain.load(file, use_jax=False)

def load(
        file,                   # path or open file object to read the .npz from
        use_jax: bool = False,  # supercore type; the masks always come back numpy (host) bool
) -> 'UniformTuckerTensorTrain':

Load from a .npz file written by save().

The supercores follow use_jax; the masks stay numpy (host) bool (a jax mask is a tracer under jit and breaks the layer; docs/contributor/uniform_pytree_composition.md). See save() for an example.

Parameters:

use_jax (bool)

Return type:

UniformTuckerTensorTrain