graph2mat.bindings.torch.TorchGraph2Mat

class graph2mat.bindings.torch.TorchGraph2Mat(*args, numpy: ~types.ModuleType = <module 'torch' from '/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/site-packages/torch/__init__.py, self_interactions_list=torch.nn.modules.container.ModuleList, interactions_dict=torch.nn.modules.container.ModuleDict, **kwargs)[source]

Bases: Graph2Mat, Module

Wrapper for Graph2Mat to make it use torch instead of numpy.

It also makes Graph2Mat a torch.nn.Module, and it makes it store the list of node block functions as a torch.nn.ModuleList and the dictionary of edge block functions as a torch.nn.ModuleDict.

Parameters:: **kwargs – Additional arguments passed to the Graph2Mat class.

See also

Graph2Mat: The class that TorchGraph2Mat extends. Its documentation contains a more detailed explanation of the inner workings of the class.

Methods

Attributes

`basis_table`	The table holding all information about the basis.
`self_interactions`	List of self interaction functions (which compute node blocks).
`interactions`	Dictionary of interaction functions (which compute edge blocks).
`graph2mat_table`	The basis table used internally by graph2mat
`types_to_graph2mat`	The mapping of types from the original basis to the graph2mat basis.
`edge_types_to_graph2mat`	The mapping of edge types from the original basis to the graph2mat basis.
`basis_filters`	If the `basis_grouping` is "max", this is a mask that is used to select the values for the original basis from the new grouped basis.
`node_filters`	If the `basis_grouping` is "max", mask to select values from node operations This has shape (n_point_types, dim_new_basis, dim_new_basis).
`edge_filters`	If the `basis_grouping` is "max", mask to select values from edge operations This has shape (n_edge_types, dim_new_basis, dim_new_basis).
`training`