GRUUnit#
GRUUnit - 1#
Version
name: GRUUnit (GitHub)
domain: main
since_version: 1
function:
support_level:
shape inference:
This version of the operator has been available since version 1.
Summary
GRUUnit computes the activations of a standard GRU, in a sequence-length aware fashion. Concretely, given the (fused) inputs X (TxNxD), the previous hidden state (NxD), and the sequence lengths (N), computes the GRU activations, avoiding computation if the input is invalid (as in, the value at X[t][n] >= seqLengths[n].
Attributes
drop_states: Bool to determine if hidden state is zeroes or passed along for timesteps past the given sequence_length. Default value is
?
.
Inputs
hidden_prev (heterogeneous) - T: The previous GRU hidden state.
gates (heterogeneous) - T: Unactivated gate outputs from forget, update, and output gates, pre- activation.
seq_lengths (heterogeneous) - T: Array of sequence lengths. len(seq_lengths) should equal batch size N.
t (heterogeneous) - T: The timestep for this operation.
Outputs
hidden (heterogeneous) - T: The new GRU hidden state calculated by this op.
Examples