sub_modules

Implementation of nn.Modules for temporal fusion transformer.

Classes

AddNorm(input_size[, skip_size, trainable_add])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
GateAddNorm(input_size[, hidden_size, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
GatedLinearUnit(input_size[, hidden_size, ...])	Gated Linear Unit
GatedResidualNetwork(input_size, ...[, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
InterpretableMultiHeadAttention(n_head, d_model)	Interpretable Multi-Head Attention module.
PositionalEncoder(d_model[, max_seq_len])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
ResampleNorm(input_size[, output_size, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
ScaledDotProductAttention([dropout, scale, ...])	Scaled Dot-Product Attention.
TimeDistributed(module[, batch_first])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
TimeDistributedInterpolation(output_size[, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
VariableSelectionNetwork(input_sizes, ...[, ...])	Calculate weights for num_inputs variables which are each of size input_size