Welcome to our Support Center

PReLU 5D

Description

Defines the weight of the PReLU5D layer selected by the index. Type : polymorphic.

 

Input parameters

 

index : integer, index of layer.
alpha : array, 4D alpha values. alpha = [input_dim1, input_dim2, input_dim3, input_dim4].

 

Output parameters

 

weights : cluster

index : integer, index of layer.
weights : variant, weights values.

Dimension

  • alpha = [input_dim1, input_dim2, input_dim3, input_dim4]

Its size depends on the input of theΒ PReLUΒ layer.
For example, if the layer has an entry [batch_size = 10, input_dim1 = 7, input_dim2 = 5, input_dim3 = 3, input_dim4 = 2] then alpha will have a size [input_dim1 = 7, input_dim2 = 5, input_dim3 = 3, input_dim4 = 2].
The size can also depend on the β€œshared_axis” parameter that you set to the PReLU layer. Each axis specified in this param is represented by a 1 in the weights.
For example, if you set the parameter with the values [2], alpha will have a size [input_dim1 = 7, 1, input_dim3 = 3, input_dim4 = 2].
Another example, if you define the parameter with the values [2, 3], alpha will have a size [input_dim1 = 7, 1, 1, input_dim4 = 2].

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