Welcome to our Support Center
Updated

Float Initializer

Description

Creates a graph initializer of type float32. The tensor values are defined directly in the parameters and stored as a fixed variable inside the graph.

 

Input parameters

 

 Parameters : cluster

flattened_float_data : array, stores the explicit list of numeric values for the initializer, in a flattened one-dimensional format.
shape : array, defines the true shape of the initializer tensor.
Training : cluster, these parameters only have an effect in a training graph.

type : enum, defines how the initializer behaves when the graph is used in training mode. It determines whether the tensor is treated as a constant, as trainable weights, or as frozen weights. During inference, it makes no difference whether the type is Constant, Train Weights, or Frozen Weights.
Regularizer : cluster, regularizer function applied to the weights matrix.

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

 

 

Output parameters

 

 Graph out : object, ONNX model architecture.

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 Deep Learning library to run it).

Table of Contents