mwptoolkit.module.Graph.graph_module¶
- class mwptoolkit.module.Graph.graph_module.Graph_Module(indim, hiddim, outdim, dropout=0.3)[source]¶
Bases:
Module
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(graph_nodes, graph)[source]¶
- Parameters
graph_nodes (torch.Tensor) – input features, shape [batch_size, node_num, in_feat_dim]
- Returns
graph_encode_features, shape [batch_size, node_num, out_feat_dim]
- Return type
torch.Tensor
- get_adj(graph_nodes)[source]¶
- Parameters
graph_nodes (torch.Tensor) – input features, shape [batch_size, node_num, in_feat_dim]
- Returns
adjacency matrix, shape [batch_size, node_num, node_num]
- Return type
torch.Tensor
- normalize(A, symmetric=True)[source]¶
- Parameters
A (torch.Tensor) – adjacency matrix (node_num, node_num)
- Returns
adjacency matrix (node_num, node_num)
- training: bool¶
- class mwptoolkit.module.Graph.graph_module.Num_Graph_Module(node_dim)[source]¶
Bases:
Module
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(node, graph1, graph2)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶
- class mwptoolkit.module.Graph.graph_module.Parse_Graph_Module(hidden_size)[source]¶
Bases:
Module
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(node, graph)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶