models.nn.pyg_dgcnn

Module Contents

Classes

DGCNN

EdgeConv and DynamicGraph in paper `”Dynamic Graph CNN for Learning on

class models.nn.pyg_dgcnn.DGCNN(in_feats, hidden_dim, out_feats, k=20, dropout=0.5)

Bases: models.BaseModel

EdgeConv and DynamicGraph in paper “Dynamic Graph CNN for Learning on Point Clouds” <https://arxiv.org/pdf/1801.07829.pdf>__ .

in_featsint

Size of each input sample.

out_featsint

Size of each output sample.

hidden_dimint

Dimension of hidden layer embedding.

kint

Number of neareast neighbors.

static add_args(parser)

Add model-specific arguments to the parser.

classmethod build_model_from_args(cls, args)

Build a new model instance.

classmethod split_dataset(cls, dataset, args)

forward(self, batch)