Welcome to our Support Center

GRU

Description

Defines the weights of the GRU layer selected by the index. Type : polymorphic.

 

Input parameters

 

 Model in : model architecture.
index : integer, index of layer.

 gru_weight : cluster

input_weights : array, 2D values. input_weights = [features, 3*units].
hidden_weights : array, 2D values. hidden_weights = [units, 3*units].
input_biases : array, 1D values. input_biases = [3*units].
hidden_biases : array, 1D values. hidden_biases = [3*units].

Output parameters

 

 Model out : model architecture.

Dimension

  • input_weights = [features, 3*units]

The size depends on the GRU layer input and the units parameter.
For example, if the input has a size of [batch = 10, timesteps = 8, features = 5] and units a value of 3 then input_weights will have a size of [features = 5, 3*units = 3].
Another example, if the input has a size of [batch = 15, timesteps = 8, features = 6] and units a value of 2 then input_weights will have a size of [features = 6, 3*units = 2].

 

  • hidden_weights = [units, 3*units].

The size depends on the units parameter of the GRU layer.
For example, if units has a value of 6 then hidden_weights will have a size of [units = 6, 3*units = 6].
Another example, if units has a value of 4 then hidden_weights will have a size of [units = 4, 3*units = 4].

 

  • input_biases = [3*units]

The size depends on the units parameter of the GRU layer.
For example, if units has a value of 6, then input_biases will have a size of [3*units = 6].
Another example, if units has a value of 4, then input_biases will have a size of [3*units = 4].

 

  • hidden_biases = [3*units]

The size of hidden_biases is based on the same principle as the size of input_biases.

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install HAIBAL library to run it).

Table of Contents