Welcome to our Support Center

ConvLSTM1D

Description

Defines the weights of the ConvLSTM1D layer selected by the name. Type : polymorphic.

 

Input parameters

 

Β name :Β string,Β name of layer.
Β kernel :Β array,Β 3D values. kernel = [4*n_filters, channels, size].
Β recurrent_kernel :Β array,Β 3D values. recurrent_kernel = [4*n_filters, n_filters, size].
Β bias :Β array,Β 1D values. bias = [4*n_filters].

 

Output parameters

 

weights : cluster

Β name :Β string,Β name of layer.
weights : variant, weights values.

Dimension

  • kernel = [4*n_filters, channels, size]

The kernel size depends on the input of theΒ ConvLSTM1DΒ layer and the parameters n_filters and size of the ConvLSTM1D cell.
For example, if the input of the layer has a size of [samples = 10, time = 8, channels = 5, rows = 2], n_filters a value of 6 and size the value 3, then kernel will have a size of [4*n_filters = 6, channels = 5, size = 3].

 

  • recurrent_kernel = [4*n_filters, n_filters, size].

The size of recurrent_kernel depends on the parameters n_filters and size of the ConvLSTM1D cell.
For example, if n_filters has a value of 6 and size the value 3, then recurrent_kernel will have a size of [4*n_filters = 6, n_filters = 6, size = 3].

 

  • bias = [4*n_filters].

The size of bias depends on the parameter n_filters of the ConvLSTM1D cell.
For example, if n_filters has a value of 6 then the bias size will be [4*n_filters = 6].

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