dlhdl.layer.sliceLayer

Slice layer

Since R2024a

Description

Use sliceLayer objects to divide the input to the layer into an equal number of groups along the channel dimension of the image.

Creation

Syntax

layer = dlhdl.layer.sliceLayer

layer = dlhdl.layer.sliceLayer('Name'=Name,Name=Value)

Description

layer = dlhdl.layer.sliceLayer creates a slice layer.

layer = dlhdl.layer.sliceLayer('Name'=Name,Name=Value) creates a slice layer with the name Name, and sets additional Groups, and GroupID properties using one or more name-value pair arguments.

Properties

Groups — Number of groups to split input features into

2 (default) | positive integer

Number of groups to split input features into, specified as a positive integer.

Example: 2

GroupID — ID of group to pass as output

2 (default) | positive integer

ID of group to pass as output, specified as a positive integer.

Example: 2

Layer

Name — Layer name

"" (default) | character vector | string scalar

Layer name, specified as a character vector or string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to layers with the name "".

The sliceLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

1 (default)

This property is read-only.

Number of inputs to the layer, returned as 1. This layer accepts a single input only.

Data Types: double

InputNames — Input names

{'in'} (default)

This property is read-only.

Input names, returned as {'in'}. This layer accepts a single input only.

Data Types: cell

NumOutputs — Number of outputs

1 (default)

This property is read-only.

Number of outputs from the layer, returned as 1. This layer has a single output only.

Data Types: double

OutputNames — Output names

{'out'} (default)

This property is read-only.

Output names, returned as {'out'}. This layer has a single output only.

Data Types: cell

Examples

Create Slice Layer

Create a slice layer with the name "slice1".

layer = dlhdl.layer.sliceLayer(Name="slice1")

layer = 
  sliceLayer with properties:

       Name: 'slice1'
     Groups: 2
    GroupId: 2
   Learnable Parameters
    No properties.
   State Parameters
    No properties.
  Show all properties

Include the slice layer in a Layer array.

 imageSize = [20 20 16];
layers = [
                imageInputLayer(imageSize,"Name","imageinput","Normalization","none")
                convolution2dLayer(3,16,"Padding","same")
                dlhdl.layer.sliceLayer(Name="slice",Groups=2,GroupID=2)
                maxPooling2dLayer(3,'Padding','same','Name','pool')]

layers = 
  4×1 Layer array with layers:

     1   'imageinput'   Image Input              20×20×16 images
     2   ''             2-D Convolution          16 3×3 convolutions with stride [1  1] and padding 'same'
     3   'slice'        dlhdl.layer.sliceLayer   dlhdl.layer.sliceLayer
     4   'pool'         2-D Max Pooling          3×3 max pooling with stride [1  1] and padding 'same'

Algorithms

Slice Layer

A slice layer is a utility layer that slices an input to the layer into a number of grouped output layers, specified by the Groups argument, along the channel dimension and outputs the group specified by the GroupID argument. For example, if the input to the slice layer is size 10-by-10-by-8 and the number of groups is two, the slice layer splits the input into two groups of size 10-by-10-by-4, and if the group ID is two, the second group of size 10-by-10-by-4 is the output of the slice layer.

Version History

Introduced in R2024a