RaiseDoubleKeywords */

RaiseNeedMoreValuesToUnpack */

RaiseNoneIterError */

RaiseTooManyValuesToUnpack */

CheckBinaryVersion */

Class Initialyser

This dataset is small enough to be stored in-memory, so load all point clouds here

This dataset is small enough to be stored in-memory, so load all point clouds here

proto*/

proto*/

Computes accuracy of the current batch :param outputs: logits predicted by the network :param labels: labels :ret

Pools features from the closest neighbors. WARNING: this function assumes the neighbors are ordered. :param x: [n1, d] features matrix

Test method for cloud segmentation models

Validation method for cloud segmentation models

opperations

In this function you choose the results you want to plot together, to compare them as an experiment. Just return the list of log paths (lik

Frees all allocated memory chunks */

Frees all allocated memory chunks */

Frees all allocated memory chunks */

Block performing a global average over batch pooling :param x: [N, D] input features :param batch_lengths: [B] list of batch lengths

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

Initialize the kernel point positions in a sphere :return: the tensor of kernel points

Creation of kernel point via optimization of potentials. :param radius: Radius of the kernels :param num_points: points composing kern

Runs the loss on outputs of the model :param outputs: logits :param labels: labels :return: loss

* Returns a pointer to a piece of new memory of the given size in bytes * allocated from the pool. */

* Returns a pointer to a piece of new memory of the given size in bytes * allocated from the pool. */

* Returns a pointer to a piece of new memory of the given size in bytes * allocated from the pool. */

:param feature: [B, N, d] input features matrix :param interp_idx: [B, up_num_points, 1] nearest neighbour index :return: [B,

Perform a round of validation and show/save results :param net: network object :param val_loader: data loader for validati

* Find all the neighbors to \a query_point[0:dim-1] within a maximum radius. * The output is given as a vector of pairs, of which the first eleme

Compute a radius gaussian (gaussian of distance) :param sq_r: input radiuses [dn, ..., d1, d0] :param sig: extents of gaussians [d1, d

:param feature: [B, N, d] input features matrix :param pool_idx: [B, N', max_num] N' < N, N' is the selected position after pooling