Main Content

compressNetworkUsingProjection

Compress neural network using projection

Since R2022b

    Description

    The compressNetworkUsingProjection function reduces the number of learnable parameters of layers by performing principal component analysis (PCA) of the neuron activations using a data set representative of the training data and then projects the learnable parameters into the subspace that maintains the highest variance in neuron activations. In some cases, this operation is equivalent to replacing layers with networks containing two or more layers with fewer learnable parameters.

    Depending on the network, projection configuration, and code generation libraries used (including library-free code generation), forward passes of a projected deep neural network can be faster when you deploy the network to embedded hardware.

    If you prune or quantize your network, then use compression using projection after pruning and before quantization.

    netProjected = compressNetworkUsingProjection(net,mbq) compresses the dlnetwork object net by replacing layers with projected layers. The function compresses layers by performing principal component analysis (PCA) of the neuron activations using the data in the minibatchqueue object mbq and projects learnable parameters into the subspace that maintains the highest variance in neuron activations. This feature requires the Deep Learning Toolbox™ Model Quantization Library support package. This support package is a free add-on that you can download using the Add-On Explorer. Alternatively, see Deep Learning Toolbox Model Quantization Library.

    example

    netProjected = compressNetworkUsingProjection(net,X1,...,XN) compresses the network using the data in the dlarray objects X1,...,XN, where N is the number of network inputs.

    netProjected = compressNetworkUsingProjection(net,npca) compresses the network using the neuronPCA object npca. The PCA step can be computationally intensive. If you expect to compress the same network multiple times (for example, when exploring different levels of compression), then you can perform the PCA step up front using a neuronPCA object.

    [netProjected, info] = compressNetworkUsingProjection(___) also returns the structure info that contains information about the projected layers, the reduction of learnable parameters, and the explained variance achieved during compression.

    [netProjected, info] = compressNetworkUsingProjection(___,Name=Value) specifies additional options using one or more name-value arguments.

    example

    Examples

    collapse all

    Load the pretrained network in dlnetJapaneseVowels and the training data in JapaneseVowelsTrainData.

    load dlnetJapaneseVowels
    load JapaneseVowelsTrainData

    Create a mini-batch queue containing the training data. To create a mini-batch queue from in-memory data, convert the sequences to an array datastore.

    adsXTrain = arrayDatastore(XTrain,OutputType="same");

    Create the minibatchqueue object.

    • Specify a mini-batch size of 16.

    • Preprocess the mini-batches using the preprocessMiniBatchPredictors function, listed in the Mini-Batch Predictors Preprocessing Function section of the example.

    • Specify that the output data has format "CTB" (channel, time, batch).

    mbq = minibatchqueue(adsXTrain, ...
        MiniBatchSize=16, ...
        MiniBatchFcn=@preprocessMiniBatchPredictors, ...
        MiniBatchFormat="CTB");

    Compress the network.

    [netProjected,info] = compressNetworkUsingProjection(net,mbq);
    Compressed network has 83.4% fewer learnable parameters.
    Projection compressed 2 layers: "lstm","fc"
    

    View the network layers.

    netProjected.Layers
    ans = 
      4x1 Layer array with layers:
    
         1   'sequenceinput'   Sequence Input    Sequence input with 12 dimensions
         2   'lstm'            Projected Layer   Projected LSTM with 100 hidden units
         3   'fc'              Projected Layer   Projected fully connected layer with output size 9
         4   'softmax'         Softmax           softmax
    

    View the projected LSTM layer. The LearnablesReduction property shows the proportion of learnables removed in the layer. The Network property contains the neural network that represents the projection.

    netProjected.Layers(2)
    ans = 
      ProjectedLayer with properties:
    
                       Name: 'lstm'
              OriginalClass: 'nnet.cnn.layer.LSTMLayer'
        LearnablesReduction: 0.8408
                  InputSize: 12
                 OutputSize: 100
    
       Hyperparameters
         InputProjectorSize: 8
        OutputProjectorSize: 7
    
       Learnable Parameters
                    Network: [1x1 dlnetwork]
    
       State Parameters
                    Network: [1x1 dlnetwork]
    
       Network Learnable Parameters
         Network/lstm/InputWeights      400x8 dlarray
         Network/lstm/RecurrentWeights  400x7 dlarray
         Network/lstm/Bias              400x1 dlarray
         Network/lstm/InputProjector    12x8  dlarray
         Network/lstm/OutputProjector   100x7 dlarray
    
       Network State Parameters
         Network/lstm/HiddenState  100x1 dlarray
         Network/lstm/CellState    100x1 dlarray
    
    Use properties method to see a list of all properties.
    
    

    Mini-Batch Predictors Preprocessing Function

    The preprocessMiniBatchPredictors function preprocesses a mini-batch of predictors by extracting the sequence data from the input cell array and truncating them along the second dimension so that they have the same length.

    Note: Do not pad sequence data when doing the PCA step for projection as this can negatively impact the analysis. Instead, truncate mini-batches of data to have the same length or use mini-batches of size 1.

    function X = preprocessMiniBatchPredictors(dataX)
    
    X = padsequences(dataX,2,Length="shortest");
    
    end

    To determine the maximum possible compression, set the LearnablesReductionGoal option to 1 or the ExplainedVarianceGoal option to 0.

    Load the pretrained network in dlnetJapaneseVowels and the training data in JapaneseVowelsTrainData.

    load dlnetJapaneseVowels
    load japaneseVowelsTrainData

    Create a mini-batch queue containing the training data. To create a mini-batch queue from in-memory data, convert the sequences to an array datastore.

    adsXTrain = arrayDatastore(XTrain,OutputType="same");

    Create the minibatchqueue object.

    • Specify a mini-batch size of 16.

    • Preprocess the mini-batches using the preprocessMiniBatchPredictors function, listed in the Mini-Batch Predictors Preprocessing Function section of the example.

    • Specify that the output data has format "CTB" (channel, time, batch).

    miniBatchSize = 16;
    
    mbq = minibatchqueue(adsXTrain, ...
        MiniBatchSize=miniBatchSize, ...
        MiniBatchFcn=@preprocessMiniBatchPredictors, ...
        MiniBatchFormat="CTB");

    Compress the network. To determine the maximum possible compression, set the LearnablesReductionGoal option to 1.

    [netProjected,info] = compressNetworkUsingProjection(net,mbq,LearnablesReductionGoal=1);
    Compressed network has 96.9% fewer learnable parameters.
    Projection compressed 2 layers: "lstm","fc"
    

    View the proportion of total number of network learnables removed by inspecting the LearnablesReduction property of the information structure.

    info.LearnablesReduction
    ans = 0.9690
    

    Mini-Batch Predictors Preprocessing Function

    The preprocessMiniBatchPredictors function preprocesses a mini-batch of predictors by extracting the sequence data from the input cell array and truncating them along the second dimension so that they have the same length.

    Note: Do not pad sequence data when doing the PCA step for projection as this can negatively impact the analysis. Instead, truncate mini-batches of data to have the same length or use mini-batches of size 1.

    function X = preprocessMiniBatchPredictors(dataX)
    
    X = padsequences(dataX,2,Length="shortest");
    
    end

    Input Arguments

    collapse all

    Neural network, specified as an initialized dlnetwork object.

    Mini-batch queue that outputs data for each input of the network, specified as a minibatchqueue object.

    The PCA step typically works best when using the full training set. However, any dataset that is representative of the training data distribution suffices. The input data must contain two or more observations and sequences must contain two or more time steps.

    Note

    Do not pad sequence as this can negatively impact the analysis. Instead, truncate mini-batches of data to have the same length or use mini-batches of size 1.

    Input data, specified as a formatted dlarray.

    For more information about dlarray formats, see the fmt input argument of dlarray.

    The PCA step typically works best when using the full training set. However, any dataset that is representative of the training data distribution suffices. The input data must contain two or more observations and sequences must contain two or more time steps.

    Note

    Do not pad sequence as this can negatively impact the analysis. Instead, truncate mini-batches of data to have the same length or use mini-batches of size 1.

    Neuron principal component analysis, specified as a neuronPCA object.

    Name-Value Arguments

    Specify optional pairs of arguments as Name1=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: netProjected = compressNetworkUsingProjection(net,mbq,VerbosityLevel="off") compresses the network using projection and disables the command line display.

    Names of layers to compress, specified as a string array, cell array of character vectors, or a character vector containing a single layer name.

    The software, by default, compress all the layers in the network that support projection.

    The compressNetworkUsingProjection function supports projecting these layers:

    Data Types: string | cell

    Target proportion of neuron activation variance explained by the remaining principal components of each projected layer, specified as a value between 0 (maximum compression) and 1 (project layers with minimal compression).

    If you specify the ExplainedVarianceGoal option, then you must not specify the LearnablesReductionGoal option.

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

    Target proportion of total number of network learnables to remove, specified as a nonnegative scalar less than or equal to 1.

    If you specify the LearnablesReductionGoal option, then you must not specify the ExplainedVarianceGoal option. If you do not specify the LearnablesReductionGoal option, then the function compresses the network using the ExplainedVarianceGoal option.

    If LearnablesReductionGoal is greater than the maximum possible reduction in learnables, then the function removes the maximum possible proportion of learnables. Use the neuronPCA function to determine the possible range of reduction in learnables.

    If LearnablesReductionGoal is smaller than the maximum possible reduction in learnables, then the function removes at least the proportion of learnables specified by LearnablesReductionGoal. If removing a greater proportion of learnables does not reduce the explained variance, then the function automatically removes a higher proportion of learnables. For example, if you specify a learnables reduction goal of 0.2, and if the explained variance is the same for learnables reductions between 0.2 and 0.5, then the function removes 50% of learnables.

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

    Verbosity level, specified as one of these values:

    • "summary" — Display a summary of the compression algorithm.

    • "steps" — Display information about the steps of the compression algorithm.

    • "iterations" — Display information about the iterations of the compression algorithm.

    • "off" — Do not display information.

    Since R2023b

    Flag to unpack projected layers, specified as one of these values:

    • 0 (false) — Do not unpack projected layers. The function replaces projectable layers with ProjectedLayer objects.

    • 1 (true) — Unpack projected layers. The function replaces projectable layers with the network that is equivalent to the projection.

    Output Arguments

    collapse all

    Projected network, returned as a dlnetwork object.

    After you compress the network using projection, you can fine-tune the network to help regain predictive accuracy lost by the compression process. For an example, see Compress Neural Network Using Projection.

    Projection information, returned as a structure with these fields:

    • LearnablesReduction — Proportion of total number of network learnables removed

    • ExplainedVariance — Proportion of neuron activation variance explained by principal components

    • LayerNames (since R2023b) — Names of projected layers

    Tips

    • Code generation does not support ProjectedLayer objects. To replace ProjectedLayer objects in a neural network with the equivalent neural network that represents the projection, use the unpackProjectedLayers function or set the UnpackProjectedLayers option of the compressNetworkUsingProjection function to 1 (true).

    Algorithms

    collapse all

    Projected Layer

    To compress a deep learning network, you can use projected layers. A projected layer is a type of deep learning layer that enables compression by reducing the number of stored learnable parameters. The layer introduces learnable projector matrices Q, replaces multiplications of the form Wx, where W is a learnable matrix, with the multiplication WQQx, and stores Q and W=WQ instead of storing W. Projecting x into a lower dimensional space using Q typically requires less memory to store the learnable parameters and can have similarly strong prediction accuracy.

    For some types of layers, you can represent a projected layer as a neural network containing two or more layers with fewer learnable parameters. For example, you can represent a projected convolution layer as three convolution layers that perform the input projection, convolution, and the output projection operations independently. When you compress a network using the compressNetworkUsingProjection function, the software replaces layers that support projection with ProjectedLayer objects that contain the equivalent neural network. To replace ProjectedLayer objects in a neural network with the equivalent neural network that represents the projection, use the unpackProjectedLayers function or set the UnpackProjectedLayers option of the compressNetworkUsingProjection function to 1 (true).

    The compressNetworkUsingProjection function supports projecting these layers:

    The compressNetworkUsingProjection function replaces projectable layers with ProjectedLayer objects. A ProjectedLayer object contains information about the projection operation and contains the neural network that represents the projection.

    The neural network that represents the projection depends on the type of layer:

    Original LayerNetwork

    convolution1dLayer (since R2024b)

    Network containing two or three convolution1dLayer objects
    convolution2dLayerNetwork containing two or three convolution2dLayer objects
    fullyConnectedLayerNetwork containing two fullyConnectedLayer objects
    lstmLayerNetwork containing a single lstmProjectedLayer object
    gruLayerNetwork containing a single gruProjectedLayer object

    References

    [1] "Compressing Neural Networks Using Network Projection." Accessed July 20, 2023. https://www.mathworks.com/company/technical-articles/compressing-neural-networks-using-network-projection.html.

    Extended Capabilities

    Version History

    Introduced in R2022b

    expand all