class ConvolutionsFactory

Bases: object

Factory responsible for creation list of specified convolution layers

build_convolutions(conv: str, num_features: int, hidden_layer: int, out_layer: int, num_layers: int, heads: int) → torch.nn.ModuleList

Produce convolutions module list based on the parameters

Parameters:

  • hidden_layer – (int): The size of hidden layer (default:64)

  • out_layer – (int): The size of output layer (default:128)

  • num_layers – (int): Number of layers in the model (default:2)

  • heads – (int): Number of heads in GAT conv (default:1)

  • num_features – (int): dimensionality of features

  • conv – (str): Either ‘GCN’, ‘GAT’ or ‘SAGE’ convolution