phlower.PhlowerTensor

class phlower.PhlowerTensor(tensor, dimension_tensor=None, is_time_series=False, is_voxel=False)

Bases: IPhlowerTensor

Tensor object which can be with physics dimenstion tensor.

Methods

__init__(tensor[, dimension_tensor, ...])
as_pattern(pattern)
backward()
clone()
coalesce()
detach()
from_pattern(tensor[, dimension_tensor, pattern])
indices()
n_vertices()	Returns the number of vertices.
numel()
numpy()
rank()	Returns the tensor rank.
rearrange(pattern, **axes_length)
reshape(shape[, is_time_series, is_voxel])
size()
to([device, non_blocking, dtype])
to_numpy()
to_tensor()
to_vertexwise()	Convert to vertexwise 2D tensor which has (n_vertices, -1) shape.
transpose(dim0, dim1)
values()

Attributes

device
dimension
dtype
has_dimension
is_sparse
is_time_series
is_voxel
shape
shape_pattern

Parameters:

• tensor (torch.Tensor)

• dimension_tensor (PhlowerDimensionTensor | None)

• is_time_series (bool)

• is_voxel (bool)

n_vertices()

Returns the number of vertices.

Return type:

int

rank()

Returns the tensor rank.

Return type:

int

to_vertexwise()

Convert to vertexwise 2D tensor which has (n_vertices, -1) shape.

Returns:

PhlowerTensor

Vertexwise PhlowerTensor object.

resultant_patternstr

Pattern of the resultant shape. Can be used for rearrange.

Return type:

vertexwise_tensor