RealToComplexLayer - Real-to-complex layer - MATLAB (original) (raw)

Real-to-complex layer

Since R2024b

Description

A real-to-complex layer converts real-valued data to complex-valued data by merging the data in a specified dimension.

Creation

Syntax

Description

`layer` = realToComplexLayer creates a real-to-complex layer. The layer merges interleaved data in the channel dimension.

example

`layer` = realToComplexLayer([Name=Value](#namevaluepairarguments)) sets properties using one or more name-value arguments.

example

Name-Value Arguments

expand all

Specify optional pairs of arguments asName1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Example: realToComplexLayer(Name="real-to-complex") creates a real-to-complex layer, and sets the name to"real-to-complex".

Data dimension to merge, specified as one of these values:

"C" — Merge the data in the "C" (channel) dimension of the layer output.
"S" — Merge the data in the "S" (spatial) dimension of the layer output. If the input data has multiple spatial dimensions, then the layer merges the interleaved data in the first spatial dimension.
"B" — Merge the data in the "B" (batch) dimension of the layer output.
"T" — Merge the data in the "T" (time) dimension of the layer output.
"U" — Merge the data in the "U" (unspecified) dimension of the layer output. If the input data has multiple"U" (unspecified) dimensions, then the layer merges the interleaved data in the first "U" (unspecified) dimension.
"last" — Merge the interleaved data in the last dimension of the layer output.
Positive integer — Merge the interleaved data in the specified dimension of the layer output.

In the layer output, the dimension specified by OperationDimension is half the size of the corresponding dimension in the layer input. That is, forn=1,...,N/2, where N is the size of the specified dimension, and X and Y represent the input and output data, respectively, Y(n) = X(2*n-1)+1i*X(2*n).

The input data must contain the specified dimension it must have size divisible by2.

The characters "S", "C", "T","B", and "U" refer to the dimension labels ofdlarray object formats. For more information, see Deep Learning Data Formats.

Layer name, specified as a character vector or a string scalar. For Layer array input, the trainnet anddlnetwork functions automatically assign names to unnamed layers.

Data Types: char | string

Properties

expand all

Data dimension to merge, specified as one of these values:

"C" — Merge the data in the "C" (channel) dimension of the layer output.
"S" — Merge the data in the "S" (spatial) dimension of the layer output. If the input data has multiple spatial dimensions, then the layer merges the interleaved data in the first spatial dimension.
"B" — Merge the data in the "B" (batch) dimension of the layer output.
"T" — Merge the data in the "T" (time) dimension of the layer output.
"U" — Merge the data in the "U" (unspecified) dimension of the layer output. If the input data has multiple"U" (unspecified) dimensions, then the layer merges the interleaved data in the first "U" (unspecified) dimension.
"last" — Merge the interleaved data in the last dimension of the layer output.
Positive integer — Merge the interleaved data in the specified dimension of the layer output.

The input data must contain the specified dimension it must have size divisible by2.

The characters "S", "C", "T","B", and "U" refer to the dimension labels ofdlarray object formats. For more information, see Deep Learning Data Formats.

Data Types: char | string

This property is read-only.

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

Data Types: double

This property is read-only.

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

Data Types: cell

This property is read-only.

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

Data Types: double

This property is read-only.

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

Data Types: cell

Examples

collapse all

Create a real-to-complex layer with the name "real-to-complex".

layer = realToComplexLayer(Name="real-to-complex")

layer = RealToComplexLayer with properties:

              Name: 'real-to-complex'

Hyperparameters OperationDimension: 'C'

Include a real-to-complex layer in a layer array.

layers = [ featureInputLayer(4) complexToRealLayer fullyConnectedLayer(4) tanhLayer realToComplexLayer]

layers = 5×1 Layer array with layers:

 1   ''   Feature Input     4 features
 2   ''   Complex-to-Real   Complex-to-real conversion along the "C" dimension.
 3   ''   Fully Connected   4 fully connected layer
 4   ''   Tanh              Hyperbolic tangent
 5   ''   Real-to-Complex   Real-to-complex conversion along the "C" dimension.

Algorithms

expand all

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).

RealToComplexLayer objects support input data of any format. The layer does not add or remove any dimensions, so it outputs data with the same format as its inputs.

RealToComplexLayer objects support complex-valued outputs.

Version History

Introduced in R2024b