kaolin.physics.simplicits.SkinnedPoints¶

API¶

class kaolin.physics.simplicits.SkinnedPoints(pts, skinning_weights, strict_checks=True)¶

Bases: SkinnedPointsProtocol, TensorContainerBase

Points with skinning properties.

pts¶

The skinned points, of shape \((N, 3)\) (in \(m\)).

Type: torch.Tensor

skinning_weights¶

The skinning weights of the points, of shape \((N, \text{num_handles})\).

Type: torch.Tensor

__init__(pts, skinning_weights, strict_checks=True)¶

as_dict(only_tensors=False) → Dict[str, Any]¶: Return all non-None attributes as a {name: value} dict.

classmethod assert_supported(attr)¶: Raises an exception if class does not support provided attribute name.

check_other_attribute(attr, log_error=False)¶: Checks a non-tensor attribute validity; returns True if ok.

check_sanity(log_error=True)¶

Validates that all tensor attributes are correct; implement abstract methods.

Parameters: log_error (bool) – If True, logs each failed check via logger.error.
Returns: True if all checks pass, False otherwise.
Return type: bool

check_tensor_attribute(attr, log_error=False)¶: Checks tensor attribute validity; returns True if valid.

classmethod class_other_attributes()¶: Returns attribute names that are not PyTorch tensors or dicts thereof.

classmethod class_tensor_attributes()¶: Returns attribute names that are PyTorch tensors or dicts thereof.

cpu(attributes: Optional[Sequence[str]] = None)¶: Calls cpu on all or selected tensor attributes; returns a shallow copy.

cuda(device: Optional[Union[int, device, str]] = None, attributes: Optional[Sequence[str]] = None)¶: Calls cuda on all or selected tensor attributes; returns a shallow copy.

describe_attribute(attr, print_stats=False, detailed=False)¶

Outputs an informative string about an attribute; the same method used for all attributes in to_string.

Parameters

attr (str) – attribute name
print_stats (bool) – if to print statistics about values in each tensor
detailed (bool) – if to include additional information about each tensor

Returns

multi-line string with attribute information

Return type

(str)

Raises

ValueError if attr is not supported –

detach(attributes: Optional[Sequence[str]] = None)¶: Detaches all or selected tensor attributes; returns a shallow copy.

classmethod from_skinning_mod(pts: Tensor, skinning_mod: SkinningModule)¶

Constructor from a SkinningModule to be applied on the points.

Parameters

pts (torch.Tensor) – The points to be skinned, of shape \((N, 3)\) (in \(m\))
skinning_mod (SkinningModule) – The SkinningModule to be used to compute the skinning weights.

get_attributes(only_tensors=False)¶

Returns names of all attributes that are currently set to non-None value in this class instance.

Parameters: only_tensors – if true, will only include tensor attributes
Returns: list of string names
Return type: (list)

property num_handles¶: Last dimension of the skinning weights

to(*args: Any, attributes: Optional[Sequence[str]] = None, **kwargs: Any)¶

Moves or casts tensors like torch.Tensor.to() / torch.nn.Module.to().

Parameters

*args – forwarded to tensor.to(*args)
attributes (list of str, optional) – if set, only these tensor attributes are updated
**kwargs – forwarded to tensor.to(**kwargs)

Returns

shallow copy with converted tensors

Return type

PointSamples

to_string(print_stats=False, detailed=False)¶

Returns information about tensor attributes currently contained in the object.

Parameters

print_stats (bool) – if to print statistics about values in each tensor
detailed (bool) – if to include additional information about each tensor

Returns

multi-line string with attribute information

Return type

(str)