Welcome to our Support Center

Backward

Description

Execute the backward pass of the model (all layers).

Input parameters

 

Model in : model architecture.

 

Output parameters

 

Model out : model architecture.

input_loss : array

name : string, name of layer.
index : integer, index of layer.
dimension : enum, dimension of the loss derivative.

      • 2D Loss Derivate
      • 3D Loss Derivate
      • 4D Loss Derivate
      • 5D Loss Derivate
      • 6D Loss Derivate

shape : array, shape of layer.
data : variant, output layer predictions.

model_informations : cluster

Model Name : string, name of model.
Execution Time : integer, execution time of the backward.
Device : enum, device where the process is executed.

      • Native LabVIEW
      • GPU

 

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).

Tags:
Table of Contents