implementation of a custom gather operation for faster backwards. :param x: input with shape [N, D_1, ... D_d] :param idx: indexing wi

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 * i

Return a list of the stacked elements in the batch at a certain layer. If no layer is given, then return all layers

Return a list of the stacked elements in the batch at a certain layer. If no layer is given, then return all layers

Computes IoU from confusion matrices. :param confusions: ([..., n_c, n_c] np.int32). Can be any dimension, the confusion matrices sho

IsLittleEndian */

CIntFromPy */

CodeObjectCache */

* Called during search to add an element matching the criteria. * @return true if the search should be continued, false if the results are * s

* Called during search to add an element matching the criteria. * @return true if the search should be continued, false if the result

* Called during search to add an element matching the criteria. * @return true if the search should be continued, false if the results are * suf

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

* Builds the index */

* Create a tree node that subdivides the list of vecs from vind[first] * to vind[last]. The routine is called recursively on each sublist. *

* Create a tree node that subdivides the list of vecs from vind[first] * to vind[last]. The routine is called recursively on each sublist. *

* Create a tree node that subdivides the list of vecs from vind[first] * to vind[last]. The routine is called recursively on each sublist. *

Loads a previous index from a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so the * index object must be

Loads a previous index from a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so the index object must be const

Loads a previous index from a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so the * index object must be c

Load points (from test or validation split) on which the metrics should be evaluated

Pools features with the maximum values. :param x: [n1, d] features matrix :param inds: [n2, max_num] pooling indices :return: [n2

Stores the index in a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so when * loading the index object it

Stores the index in a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so when loading the index object it must

Stores the index in a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so when * loading the index object it m

Computes different metrics from confusion matrices. Smoothed over a number of epochs. :param confusions: ([..., n_c, n_c] np.int32). Can be

Write ".ply" files Parameters ---------- filename : string the name of the file to which the data is saved. A '.ply' e

BufferFormatCheck */

Import */

InitStrings */