Modified based on _PointnetSAModuleBase and PointnetSAModuleMSG with extra support for returning point indices for getting their GT votes

r"""Allows the model to jointly attend to information from different representation subspaces. See reference: Attention Is All You Need .

Calculating Average Precision

Calculating Average Precision

r"""Propigates the features of one set to another Parameters ---------- mlp : list Pointnet module parameters bn : bool

Absolute pos embedding, learned.

Gradually warm-up(increasing) learning rate in optimizer. Proposed in 'Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour'. Args:

r""" Backbone network for point cloud feature learning. Based on Pointnet++ single-scale grouping network. Parameters

r"""Pointnet set abstrction layer with multiscale grouping Parameters ---------- npoint : int Number of features radii : list

r""" Groups all features Parameters ---------

Modified based on _PointnetSAModuleBase and PointnetSAModuleMSG learnable feature propagation layer.

r"""Pointnet set abstrction layer Parameters ---------- npoint : int Number of features radius : float Radius of ball

Modified based on _PointnetSAModuleBase and PointnetSAModuleMSG with extra support for returning point indices for getting their GT votes

r""" Groups with a ball query of radius Parameters --------- radius : float32 Radius of ball nsample : int32 Maxi

Sigmoid focal cross entropy loss.