Permute Layer

R2026b

Permute layer

Since R2026b

expand all in page
  • Permute Layer block

Libraries:
Deep Learning Toolbox / Deep Learning Layers / Utility Layers

Description

The Permute Layer block reorders the dimensions of the input data.

The exportNetworkToSimulink function generates this block to represent a permuteLayer object.

Examples

expand all

Export a trained neural network to Simulink® as layer blocks.

For most workflows, you do not need to create neural networks in Simulink. Instead, import or train a neural network in MATLAB® and export it to Simulink.

Suppose that you have a trained neural network net specified as a dlnetwork object. Export the network to Simulink using the exportNetworkToSimulink function.

mdlInfo = exportNetworkToSimulink(net)

Neural network as subsystem in Simulink. The subsystem has the name "my_model". It has one input with the name "data" and one output with the name "prob_flatten_out".

The exported Simulink model represents the neural network as a subsystem. To view the layer blocks, open the subsystem. This example shows the first few blocks of a neural network.

Neural network as layer blocks in Simulink. The subsystem has one input with the name data. The data input is connected to four layer blocks in series. The layer blocks in order are Zerocenter 2D, Convolution 2D, ReLU, and Max Pooling 2D layer blocks. There are more blocks in the model which have been cropped from the screenshot.

To view and edit the layer block parameters, open the corresponding layer block mask. This example shows the parameters for the ReLU block.

Block Parameters dialog for the ReLU block.

Using the layer block parameters, you can configure aspects like data types and execution options like sample times.

Ports

Input

expand all

Input data to permute.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | fixed point
Complex Number Support: Yes

Output

expand all

Output data with dimensions reordered according to the Order parameter.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | fixed point
Complex Number Support: Yes

Parameters

expand all

To edit block parameters interactively, use the Property Inspector. From the Simulink Toolstrip, on the Simulation tab, in the Prepare gallery, select Property Inspector.

Main

Dimension order for the permutation, specified as a vector of positive integers. The vector is a permutation of the integers from 1 to the number of dimensions of the input data.

Programmatic Use

Block Parameter: Order
Type: character vector | string scalar
Values: '[2,1]' | vector of positive integers
Default: '[2,1]'

Execution

Specify the discrete interval between sample time hits or specify another type of sample time, such as continuous (0) or inherited (-1). For more options, see Types of Sample Time (Simulink).

By default, the block inherits its sample time based on the context of the block within the model.

Programmatic Use

To set the block parameter value programmatically, use the set_param (Simulink) function.

Parameter: SampleTime
Data Types: char
Values: '-1' | scalar
Default: '-1'

Programmatic Use: Add Block

To add the block programmatically, use the add_block function with one of these library block paths as the source.

"dlutilitylib/Permute Layer"

Example: add_block("dlutilitylib/Permute Layer","myModel/myBlock",MakeNameUnique="on")

For information about programmatic access to individual block parameters, see the Programmatic Use section of parameter descriptions on this page.

Version History

Introduced in R2026b

See Also

|

Topics