featureInputLayer

Feature input layer

Since R2020b

Description

A feature input layer inputs feature data to a neural network and applies data normalization. Use this layer when you have a data set of numeric scalars representing features (data without spatial or time dimensions).

For image input, use imageInputLayer.

Creation

Syntax

layer = featureInputLayer(numFeatures)

layer = featureInputLayer(numFeatures,Name,Value)

Description

layer = featureInputLayer(numFeatures) returns a feature input layer and sets the InputSize property to the specified number of features.

layer = featureInputLayer(numFeatures,Name,Value) sets the optional properties using name-value pair arguments. You can specify multiple name-value pair arguments. Enclose each property name in single quotes.

Properties

Feature Input

InputSize — Number of features

positive integer

Number of features for each observation in the data, specified as a positive integer.

For image input, use imageInputLayer.

Example: 10

Normalization — Data normalization

'none' (default) | 'zerocenter' | 'zscore' | 'rescale-symmetric' | 'rescale-zero-one' | function handle

Data normalization to apply every time data is forward propagated through the input layer, specified as one of the following:

• 'zerocenter' — Subtract the mean specified by Mean.

• 'zscore' — Subtract the mean specified by Mean and divide by StandardDeviation.

• 'rescale-symmetric' — Rescale the input to be in the range [-1, 1] using the minimum and maximum values specified by Min and Max, respectively.

• 'rescale-zero-one' — Rescale the input to be in the range [0, 1] using the minimum and maximum values specified by Min and Max, respectively.

• 'none' — Do not normalize the input data.

• function handle — Normalize the data using the specified function. The function must be of the form Y = func(X), where X is the input data and the output Y is the normalized data.

Tip

The software, by default, automatically calculates the normalization statistics when using the trainNetwork function. To save time when training, specify the required statistics for normalization and set the ResetInputNormalization option in trainingOptions to 0 (false).

NormalizationDimension — Normalization dimension

'auto' (default) | 'channel' | 'all'

Normalization dimension, specified as one of the following:

• 'auto' – If the training option is false and you specify any of the normalization statistics (Mean, StandardDeviation, Min, or Max), then normalize over the dimensions matching the statistics. Otherwise, recalculate the statistics at training time and apply channel-wise normalization.

• 'channel' – Channel-wise normalization.

• 'all' – Normalize all values using scalar statistics.

Mean — Mean for zero-center and z-score normalization

[] (default) | column vector | numeric scalar

Mean for zero-center and z-score normalization, specified as a 1-by-numFeatures vector of means per feature, a numeric scalar, or [].

If you specify the Mean property, then Normalization must be 'zerocenter' or 'zscore'. If Mean is [], then the trainNetwork function calculates the mean. To train a dlnetwork object using a custom training loop or assemble a network without training it using the assembleNetwork function, you must set the Mean property to a numeric scalar or a numeric array.

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

StandardDeviation — Standard deviation for z-score normalization

[] (default) | column vector | numeric scalar

Standard deviation for z-score normalization, specified as a 1-by-numFeatures vector of means per feature, a numeric scalar, or [].

If you specify the StandardDeviation property, then Normalization must be 'zscore'. If StandardDeviation is [], then the trainNetwork function calculates the standard deviation. To train a dlnetwork object using a custom training loop or assemble a network without training it using the assembleNetwork function, you must set the StandardDeviation property to a numeric scalar or a numeric array.

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

Min — Minimum value for rescaling

[] (default) | column vector | numeric scalar

Minimum value for rescaling, specified as a 1-by-numFeatures vector of minima per feature, a numeric scalar, or [].

If you specify the Min property, then Normalization must be 'rescale-symmetric' or 'rescale-zero-one'. If Min is [], then the trainNetwork function calculates the minima. To train a dlnetwork object using a custom training loop or assemble a network without training it using the assembleNetwork function, you must set the Min property to a numeric scalar or a numeric array.

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

Max — Maximum value for rescaling

[] (default) | column vector | numeric scalar

Maximum value for rescaling, specified as a 1-by-numFeatures vector of maxima per feature, a numeric scalar, or [].

If you specify the Max property, then Normalization must be 'rescale-symmetric' or 'rescale-zero-one'. If Max is [], then the trainNetwork function calculates the maxima. To train a dlnetwork object using a custom training loop or assemble a network without training it using the assembleNetwork function, you must set the Max property to a numeric scalar or a numeric array.

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

SplitComplexInputs — Flag to split input data into real and imaginary components

0 (false) (default) | 1 (true)

This property is read-only.

Flag to split input data into real and imaginary components specified as one of these values:

• 0 (false) – Do not split input data.

• 1 (true) – Split data into real and imaginary components.

When SplitComplexInputs is 1, then the layer outputs twice as many channels as the input data. For example, if the input data is complex-values with numChannels channels, then the layer outputs data with 2*numChannels channels, where channels 1 through numChannels contain the real components of the input data and numChannels+1 through 2*numChannels contain the imaginary components of the input data. If the input data is real, then channels numChannels+1 through 2*numChannels are all zero.

To input complex-valued data into a neural network, the SplitComplexInputs option of the input layer must be 1.

For an example showing how to train a network with complex-valued data, see Train Network with Complex-Valued Data.

Layer

Name — Layer name

'' (default) | character vector | string scalar

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

Data Types: char | string

NumInputs — Number of inputs

0 (default)

This property is read-only.

Number of inputs of the layer. The layer has no inputs.

Data Types: double

InputNames — Input names

{} (default)

This property is read-only.

Input names of the layer. The layer has no inputs.

Data Types: cell

NumOutputs — Number of outputs

1 (default)

This property is read-only.

Number of outputs of the layer. This layer has a single output only.

Data Types: double

OutputNames — Output names

{'out'} (default)

This property is read-only.

Output names of the layer. This layer has a single output only.

Data Types: cell

Examples

Create Feature Input Layer

Create a feature input layer with the name 'input' for observations consisting of 21 features.

layer = featureInputLayer(21,'Name','input')

layer = 
  FeatureInputLayer with properties:

                      Name: 'input'
                 InputSize: 21
        SplitComplexInputs: 0

   Hyperparameters
             Normalization: 'none'
    NormalizationDimension: 'auto'

Include a feature input layer in a Layer array.

numFeatures = 21;
numClasses = 3;
 
layers = [
    featureInputLayer(numFeatures,'Name','input')
    fullyConnectedLayer(numClasses, 'Name','fc')
    softmaxLayer('Name','sm')
    classificationLayer('Name','classification')]

layers = 
  4x1 Layer array with layers:

     1   'input'            Feature Input           21 features
     2   'fc'               Fully Connected         3 fully connected layer
     3   'sm'               Softmax                 softmax
     4   'classification'   Classification Output   crossentropyex

Combine Image and Feature Input Layers

To train a network containing both an image input layer and a feature input layer, you must use a dlnetwork object in a custom training loop.

Define the size of the input image, the number of features of each observation, the number of classes, and the size and number of filters of the convolution layer.

imageInputSize = [28 28 1];
numFeatures = 1;
numClasses = 10;
filterSize = 5;
numFilters = 16;

To create a network with two input layers, you must define the network in two parts and join them, for example, by using a concatenation layer.

Define the first part of the network. Define the image classification layers and include a flatten layer and a concatenation layer before the last fully connected layer.

layers = [
    imageInputLayer(imageInputSize,'Normalization','none','Name','images')
    convolution2dLayer(filterSize,numFilters,'Name','conv')
    reluLayer('Name','relu')
    fullyConnectedLayer(50,'Name','fc1')
    flattenLayer('name','flatten')
    concatenationLayer(1,2,'Name','concat')
    fullyConnectedLayer(numClasses,'Name','fc2')
    softmaxLayer('Name','softmax')];

Convert the layers to a layer graph.

lgraph = layerGraph(layers);

For the second part of the network, add a feature input layer and connect it to the second input of the concatenation layer.

featInput = featureInputLayer(numFeatures,'Name','features');
lgraph = addLayers(lgraph, featInput);
lgraph = connectLayers(lgraph, 'features', 'concat/in2');

Visualize the network.

plot(lgraph)

Create a dlnetwork object.

dlnet = dlnetwork(lgraph)

dlnet = 
  dlnetwork with properties:

         Layers: [9x1 nnet.cnn.layer.Layer]
    Connections: [8x2 table]
     Learnables: [6x3 table]
          State: [0x3 table]
     InputNames: {'images'  'features'}
    OutputNames: {'softmax'}
    Initialized: 1

  View summary with summary.

Extended Capabilities

C/C++ Code Generation

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

• Code generation does not support complex input and does not support 'SplitComplexInputs' option.

GPU Code Generation

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

To generate CUDA^® or C++ code by using GPU Coder™, you must first construct and train a deep neural network. Once the network is trained and evaluated, you can configure the code generator to generate code and deploy the convolutional neural network on platforms that use NVIDIA^® or ARM^® GPU processors. For more information, see Deep Learning with GPU Coder (GPU Coder).

• Code generation does not support complex input and does not support 'SplitComplexInputs' option.

Version History

Introduced in R2020b