mwptoolkit.module.Layer.graph_layers¶
- class mwptoolkit.module.Layer.graph_layers.GraphConvolution(in_features, out_features, bias=True)[source]¶
Bases:
Module
Simple GCN layer, similar to https://arxiv.org/abs/1609.02907
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(input, adj)[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.Layer.graph_layers.LayerNorm(features, eps=1e-06)[source]¶
Bases:
Module
Construct a layernorm module (See citation for details).
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)[source]¶
- Parameters
x (torch.Tensor) – input variable.
- Returns
output variable.
- Return type
torch.Tensor
- training: bool¶
- class mwptoolkit.module.Layer.graph_layers.MeanAggregator(input_dim, output_dim, activation=<function relu>, concat=False)[source]¶
Bases:
Module
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(inputs)[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.Layer.graph_layers.PositionwiseFeedForward(d_model, d_ff, d_out, dropout=0.1)[source]¶
Bases:
Module
Implements FFN equation.
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)[source]¶
- Parameters
x (torch.Tensor) – input variable.
- Returns
output variable.
- Return type
torch.Tensor
- training: bool¶