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

* 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

Add points to the set, Inserts all points from [start, end] */

Add points to the set, Inserts all points from [start, end] */

Add points to the set, Inserts all points from [start, end] */

at() with range check

* Builds the index */

* Builds the index */

* Builds the index */

Method performing batch and neighbors calibration. Batch calibration: Set "batch_limit" (the maximum number of points allowed in

Timing of generator function

Timing of generator function

Timing of generator function

Timing of generator function

Shows which labels are sampled according to strategy chosen

Shows which labels are sampled according to strategy chosen

Takes the columns of the dataframe and builds a ply-like description Parameters ---------- name: str df: pandas DataFrame

Takes the columns of the dataframe and builds a ply-like description Parameters ---------- name: str df: pandas DataFrame

opperations

pc_xyz: 3D coordinates of point clouds pc_sem_ins: semantic or instance labels plot_colors: custom color list

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

This method calibrates the batch sizes while ensuring the potentials are well initialized. Indeed on a dataset like Semantic3D, befor

This method calibrates the batch sizes while ensuring the potentials are well initialized. Indeed on a dataset like Semantic3D, befor