permuteLayer

Permute layer

Since R2025a

Description

A permute layer reorders the dimensions of data.

Creation

Syntax

layer = permuteLayer(dimorder)

layer = permuteLayer(dimorder,Name=name)

Description

layer = permuteLayer(dimorder) creates a permute layer and sets the DimensionOrder property.

layer = permuteLayer(dimorder,Name=name) also sets the optional Name property using a name-value argument.

Properties

Permute

DimensionOrder — Dimension order

row vector of positive integers

This property is read-only after creation.

Dimension order, specified as a row vector of positive integers. The number of elements of DimensionOrder must be greater than or equal to the number of dimensions in the layer input data.

The layer reorders the input data so that dimension i of the layer output data matches dimension DimensionOrder(i) of the layer input data.

Note

For layers that output unformatted data, the software automatically removes trailing singleton dimensions after the second index. For formatted data, the software removes only trailing singleton dimensions labeled with "U" (unspecified).

The PermuteLayer stores this property as a double.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Layer

Name — Layer name

'' (default) | character vector

Layer name, specified as a character vector. For Layer array input, the trainnet and dlnetwork functions automatically assign names to unnamed layers.

Data Types: char

NumInputs — Number of inputs

Read-only: 1 (default)

This property is read-only.

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

Data Types: double

InputNames — Input names

Read-only: {'in'} (default)

This property is read-only.

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

Data Types: cell

NumOutputs — Number of outputs

Read-only: 1 (default)

This property is read-only.

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

Data Types: double

OutputNames — Output names

Read-only: {'out'} (default)

This property is read-only.

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

Data Types: cell

Examples

Create Permute Layer

Create a permute layer that switches the first and third dimensions of 4-D data.

layer = permuteLayer([3 2 1 4])

layer = 
  PermuteLayer with properties:

              Name: ''

   Hyperparameters
    DimensionOrder: [3 2 1 4]

Algorithms

Layer Input and Output Formats

Most layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters in which each character describes the corresponding dimension of the data. The format consists of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, you can describe 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, as having the format "SSCB" (spatial, spatial, channel, batch).

PermuteLayer objects supports unformatted input data or input data with formats containing only "U" (unspecified) dimensions. When the input is unformatted, the output is unformatted. Otherwise, the output has a format of only "U" (unspecified) dimensions.

Complex Numbers

PermuteLayer objects support complex-valued input and outputs. The layer applies the same underlying operation to complex-valued input as it does to real-valued input. The layer outputs complex-valued data where applicable.

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

Usage notes and limitations:

• For code generation, the layer input data must be a formatted dlarray object.

GPU Code Generation

Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Usage notes and limitations:

• For GPU code generation, the layer input data must be a formatted dlarray object.

Version History

Introduced in R2025a