load cfg from yaml Args: fpath (str): path to the yaml file recursive (bool, optional): recursily load its parent def

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding c

iterator support

BufferGetAndValidate */

Build activation layer. Returns: nn.Module: Created activation layer.

Build a model, defined by `NAME`. Args: cfg (eDICT): Returns: Model: a constructed model specified by NAME.

CIntToPy */

Build normalization layer. Returns: nn.Module: Created normalization layer.

Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used.

CIntFromPy */

This method has no effects in this class, but raises an exception if the expected size does not match */

Returns the dim'th component of the idx'th point in the class:

Returns the dim'th component of the idx'th point in the class:

Returns the dim'th component of the idx'th point in the class:

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and returns the los

ExtTypeTest */

Helper accessor to the dataset points:

Helper accessor to the dataset points:

Helper accessor to the dataset points:

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding c

RaiseArgTupleInvalid */

BufferFallbackError */

* Builds the index */

opperations

Input: xyz: pointcloud data, [B, N, 3] npoint: number of samples Return: centroids: sampled pointcloud index, [B, npo

CPP wrapper for a grid sub_sampling (method = barycenter for points and features :param points: (N, 3) matrix of input points

Query for the \a num_closest closest points to a given point (entered as query_point[0:dim-1]). * Note that this is a short-cut method for index->

Input: points: input points data, [B, N, C] idx: sample index data, [B, S] Return: new_points:, indexed points data,

Update the confusion matrix with the given predictions.

assign one value to all elements

direct access to data (read-only)

data B N C number int

Must return the number of data points

Must return the number of data points

Must return the number of data points

Args: q [Query point]: (B, N_q, C) db [candiates of neighbors]: (B, N_db, C) k [k-neighbors]: int Return: id

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

GetBuiltinName */

CIntToPy */

Build a criterion (loss function), defined by cfg.NAME. Args: cfg (eDICT): Returns: criterion: a constructed loss functi