GRU

 Graphs in : cluster, ONNX model architecture.

X (heterogeneous) – T : object, the input sequences packed (and potentially padded) into one 3-D tensor with the shape of [seq_length, batch_size, input_size].
W (heterogeneous) – T : object, the weight tensor for the gates. Concatenation of W[zrh] and WB[zrh] (if bidirectional) along dimension 0. This tensor has shape [num_directions, 3*hidden_size, input_size].
R (heterogeneous) – T : object, the recurrence weight tensor. Concatenation of R[zrh] and RB[zrh] (if bidirectional) along dimension 0. This tensor has shape [num_directions, 3*hidden_size, hidden_size].
B (optional, heterogeneous) – T : object, the bias tensor for the gates. Concatenation of [Wb[zrh], Rb[zrh]] and [WBb[zrh], RBb[zrh]] (if bidirectional) along dimension 0. This tensor has shape [num_directions, 6*hidden_size]. Optional: If not specified – assumed to be 0
sequence lens (optional, heterogeneous) – T1 : optional tensor specifying lengths of the sequences in a batch. If not specified – assumed all sequences in the batch to have length seq_length. It has shape [batch_size].
initial_h (optional, heterogeneous) – T : object, optional initial value of the hidden. If not specified – assumed to be 0. It has shape [num_directions, batch_size, hidden_size].

 Parameters : cluster,

activation alpha : array, 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. Default values are the same as of corresponding ONNX operators.For example with LeakyRelu, the default alpha is 0.01.
Default value “empty”.
activation beta : array, 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. Default values are the same as of corresponding ONNX operators.
Default value “empty”.
activations : array, 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.
Default value “empty”.
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.
Default value “0”.
direction : enum, specify if the RNN is forward, reverse, or bidirectional. Must be one of forward (default), reverse, or bidirectional.
Default value “forward”.
hidden size : integer, number of neurons in the hidden layer.
Default value “0”.
layout : enum, the shape format of inputs X, initial_h and outputs Y, Y_h. If 0, the following shapes are expected: X.shape = [seq_length, batch_size, input_size], Y.shape = [seq_length, num_directions, batch_size, hidden_size], initial_h.shape = Y_h.shape = [num_directions, batch_size, hidden_size]. If 1, the following shapes are expected: X.shape = [batch_size, seq_length, input_size], Y.shape = [batch_size, seq_length, num_directions, hidden_size], initial_h.shape = Y_h.shape = [batch_size, num_directions, hidden_size].
Default value “seq_length, batch_size, input_size”.
linear_before_reset : boolean, when computing the output of the hidden gate, apply the linear transformation before multiplying by the output of the reset gate.
Default value “False”.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.

 Graphs out : cluster, ONNX model architecture.

Y (optional, heterogeneous) – T : object, a tensor that concats all the intermediate output values of the hidden. It has shape [seq_length, num_directions, batch_size, hidden_size].
Y_h (optional, heterogeneous) – T : object, the last output value of the hidden. It has shape [num_directions, batch_size, hidden_size].