PReLU 3D

Public technical reference documentation from Graiphic. For current SOTA installation and toolkit guides, visit the documentation center.

Description

Returns the PReLU3D layer weights. Type : polymorphic.

Documentation illustration (illustration unavailable in the archive).

Input parameters

weights : cluster

index : integer, index of layer.
name : string, name of layer.
Documentation illustration (illustration unavailable in the archive). weight : variant, weight of layer.

Documentation illustration (illustration unavailable in the archive).

Output parameters

weights_info : cluster

index : integer, index of layer.
name : string, name of layer.
weights : cluster

alpha : array, 2D values. alpha = [input_dim1, input_dim2].

Documentation illustration (illustration unavailable in the archive).

Dimension

alpha = [input_dim1, input_dim2]

Its size depends on the input of the PReLU layer.
For example, if the layer has an entry [batch_size = 10, input_dim1 = 7, input_dim2 = 5] then alpha will have a size [input_dim1 = 7, input_dim2 = 5].
The size can also depend on the “shared_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 [1], alpha will have a size [1, input_dim2 = 5].
Another example, if you define the parameter with the values [1, 2], alpha will have a size [1, 1].

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).