GRU#

GRU - 1#

Version

  • name: GRU (GitHub)

  • domain: main

  • since_version: 1

  • function:

  • support_level: SupportType.COMMON

  • shape inference: False

This version of the operator has been available since version 1.

Summary

Attributes

  • activation_alpha - FLOATS : Optional scaling values used by some activation functions. The values are consumed in the order of activation functions, for example (f, g, h) in LSTM.

  • activation_beta - FLOATS : Optional scaling values used by some activation functions. The values are consumed in the order of activation functions, for example (f, g, h) in LSTM.

  • activations - STRINGS : A list of 2 (or 4 if bidirectional) activation functions for update, reset, and hidden gates. The activation functions must be one of the activation functions specified above. Optional: See the equations for default if not specified.

  • clip - FLOAT : Cell clip threshold. Clipping bounds the elements of a tensor in the range of [-threshold, +threshold] and is applied to the input of activations. No clip if not specified.

  • direction - STRING : Specify if the RNN is forward, reverse, or bidirectional. Must be one of forward (default), reverse, or bidirectional.

  • hidden_size - INT : Number of neurons in the hidden layer

  • output_sequence - INT : The sequence output for the hidden is optional if 0. Default 0.

Inputs

Between 3 and 6 inputs.

  • X (heterogeneous) - T:

  • W (heterogeneous) - T:

  • R (heterogeneous) - T:

  • B (optional, heterogeneous) - T:

  • sequence_lens (optional, heterogeneous) - T1:

  • initial_h (optional, heterogeneous) - T:

Outputs

  • Y (optional, heterogeneous) - T:

  • Y_h (heterogeneous) - T:

Type Constraints

  • T in ( tensor(double), tensor(float), tensor(float16) ): Constrain input and output types to float tensors.

  • T1 in ( tensor(int32) ): Constrain seq_lens to integer tensor.