sequenceFoldingLayer

Sequence folding layer

Since R2019a

Description

A sequence folding layer converts a batch of image sequences to a batch of images. Use a sequence folding layer to perform convolution operations on time steps of image sequences independently.

To use a sequence folding layer, you must connect the miniBatchSize output to the miniBatchSize input of the corresponding sequence unfolding layer. For an example, see Create Network for Video Classification.

Creation

Syntax

layer = sequenceFoldingLayer

layer = sequenceFoldingLayer('Name',Name)

Description

layer = sequenceFoldingLayer creates a sequence folding layer.

layer = sequenceFoldingLayer('Name',Name) creates a sequence folding layer and sets the optional Name property using a name-value pair. For example, sequenceFoldingLayer('Name','fold1') creates a sequence folding layer with the name 'fold1'. Enclose the property name in single quotes.

Properties

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

1 (default)

This property is read-only.

Number of inputs of the layer. This layer accepts a single input only.

Data Types: double

InputNames — Input names

{"in"} (default)

This property is read-only.

Input names of the layer. This layer accepts a single input only.

Data Types: cell

NumOutputs — Number of outputs

2 (default)

Number of outputs of the layer.

The layer has two outputs:

• 'out' – Output feature map corresponding to reshaped input.

• 'miniBatchSize' – Size of the mini-batch passed into the layer. This output must be connected to the 'miniBatchSize' input of the corresponding sequence unfolding layer.

Data Types: double

OutputNames — Output names

{'out','miniBatchSize'} (default)

Output names of the layer.

The layer has two outputs:

• 'out' – Output feature map corresponding to reshaped input.

• 'miniBatchSize' – Size of the mini-batch passed into the layer. This output must be connected to the 'miniBatchSize' input of the corresponding sequence unfolding layer.

Data Types: cell

Examples

Create Sequence Folding Layer

Create a sequence folding layer with name the 'fold1'.

layer = sequenceFoldingLayer('Name','fold1')

layer = 
  SequenceFoldingLayer with properties:

           Name: 'fold1'
     NumOutputs: 2
    OutputNames: {'out'  'miniBatchSize'}

Create Network for Video Classification

Create a deep learning network for data containing sequences of images, such as video and medical image data.

• To input sequences of images into a network, use a sequence input layer.

• To apply convolutional operations independently to each time step, first convert the sequences of images to an array of images using a sequence folding layer.

• To restore the sequence structure after performing these operations, convert this array of images back to image sequences using a sequence unfolding layer.

• To convert images to feature vectors, use a flatten layer.

You can then input vector sequences into LSTM and BiLSTM layers.

Define Network Architecture

Create a classification LSTM network that classifies sequences of 28-by-28 grayscale images into 10 classes.

Define the following network architecture:

• A sequence input layer with an input size of [28 28 1].

• A convolution, batch normalization, and ReLU layer block with 20 5-by-5 filters.

• An LSTM layer with 200 hidden units that outputs the last time step only.

• A fully connected layer of size 10 (the number of classes) followed by a softmax layer and a classification layer.

To perform the convolutional operations on each time step independently, include a sequence folding layer before the convolutional layers. LSTM layers expect vector sequence input. To restore the sequence structure and reshape the output of the convolutional layers to sequences of feature vectors, insert a sequence unfolding layer and a flatten layer between the convolutional layers and the LSTM layer.

inputSize = [28 28 1];
filterSize = 5;
numFilters = 20;
numHiddenUnits = 200;
numClasses = 10;

layers = [ ...
    sequenceInputLayer(inputSize,'Name','input')
    
    sequenceFoldingLayer('Name','fold')
    
    convolution2dLayer(filterSize,numFilters,'Name','conv')
    batchNormalizationLayer('Name','bn')
    reluLayer('Name','relu')
    
    sequenceUnfoldingLayer('Name','unfold')
    flattenLayer('Name','flatten')
    
    lstmLayer(numHiddenUnits,'OutputMode','last','Name','lstm')
    
    fullyConnectedLayer(numClasses, 'Name','fc')
    softmaxLayer('Name','softmax')
    classificationLayer('Name','classification')];

Convert the layers to a layer graph and connect the miniBatchSize output of the sequence folding layer to the corresponding input of the sequence unfolding layer.

lgraph = layerGraph(layers);
lgraph = connectLayers(lgraph,'fold/miniBatchSize','unfold/miniBatchSize');

View the final network architecture using the plot function.

figure
plot(lgraph)

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

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

Version History

Introduced in R2019a