Main Content

Make Predictions Using Model Function

This example shows how to make predictions using a model function by splitting data into mini-batches.

For large data sets, or when predicting on hardware with limited memory, make predictions by splitting the data into mini-batches. When making predictions with SeriesNetwork or DAGNetwork objects, the predict function automatically splits the input data into mini-batches. For model functions, you must split the data into mini-batches manually.

Create Model Function and Load Parameters

Load the model parameters from the MAT file digitsMIMO.mat. The MAT file contains the model parameters in a struct named parameters, the model state in a struct named state, and the class names in classNames.

s = load("digitsMIMO.mat");
parameters = s.parameters;
state = s.state;
classNames = s.classNames;

The model function model, listed at the end of the example, defines the model given the model parameters and state.

Load Data for Prediction

Load the digits data for prediction.

digitDatasetPath = fullfile(matlabroot,'toolbox','nnet','nndemos', ...
imds = imageDatastore(digitDatasetPath, ...
    'IncludeSubfolders',true, ...

numObservations = numel(imds.Files);

Make Predictions

Loop over the mini-batches of the test data and make predictions using a custom prediction loop.

Use minibatchqueue to process and manage the mini-batches of images. Specify a mini-batch size of 128. Set the read size property of the image datastore to the mini-batch size.

For each mini-batch:

  • Use the custom mini-batch preprocessing function preprocessMiniBatch (defined at the end of this example) to concatenate the data into a batch and normalize the images.

  • Format the images with the dimensions 'SSCB' (spatial, spatial, channel, batch). By default, the minibatchqueue object converts the data to dlarray objects with underlying type single.

  • Make predictions on a GPU if one is available. By default, the minibatchqueue object converts the output to a gpuArray if a GPU is available. Using a GPU requires Parallel Computing Toolbox™ and a CUDA® enabled NVIDIA® GPU with compute capability 3.0 or higher.

miniBatchSize = 128;
imds.ReadSize = miniBatchSize;

mbq = minibatchqueue(imds,...
    "MiniBatchFcn", @preprocessMiniBatch,...

Loop over the minibatches of data and make predictions using the predict function. Use the onehotdecode function to determine the class labels. Store the predicted class labels.

doTraining = false;

Y1Predictions = [];
Y2Predictions = [];

% Loop over mini-batches.
while hasdata(mbq)
    % Read mini-batch of data.
    dlX = next(mbq);
    % Make predictions using the predict function.
    [dlY1Pred,dlY2Pred] = model(parameters,dlX,doTraining,state);
    % Determine corresponding classes.
    Y1PredBatch = onehotdecode(dlY1Pred,classNames,1);
    Y1Predictions = [Y1Predictions Y1PredBatch];
    Y2PredBatch = extractdata(dlY2Pred);
    Y2Predictions = [Y2Predictions Y2PredBatch];


View some of the images with their predictions.

idx = randperm(numObservations,9);
for i = 1:9
    I = imread(imds.Files{idx(i)});
    hold on
    sz = size(I,1);
    offset = sz/2;
    thetaPred = Y2Predictions(idx(i));
    plot(offset*[1-tand(thetaPred) 1+tand(thetaPred)],[sz 0],'r--')
    hold off
    label = string(Y1Predictions(idx(i)));
    title("Label: " + label)

Model Function

The function model takes the model parameters parameters, the input data dlX, the flag doTraining which specifies whether to model should return outputs for training or prediction, and the network state state. The network outputs the predictions for the labels, the predictions for the angles, and the updated network state.

function [dlY1,dlY2,state] = model(parameters,dlX,doTraining,state)

% Convolution
weights = parameters.conv1.Weights;
bias = parameters.conv1.Bias;
dlY = dlconv(dlX,weights,bias,'Padding','same');

% Batch normalization, ReLU
offset = parameters.batchnorm1.Offset;
scale = parameters.batchnorm1.Scale;
trainedMean = state.batchnorm1.TrainedMean;
trainedVariance = state.batchnorm1.TrainedVariance;

if doTraining
    [dlY,trainedMean,trainedVariance] = batchnorm(dlY,offset,scale,trainedMean,trainedVariance);
    % Update state
    state.batchnorm1.TrainedMean = trainedMean;
    state.batchnorm1.TrainedVariance = trainedVariance;
    dlY = batchnorm(dlY,offset,scale,trainedMean,trainedVariance);

dlY = relu(dlY);

% Convolution, batch normalization (Skip connection)
weights = parameters.convSkip.Weights;
bias = parameters.convSkip.Bias;
dlYSkip = dlconv(dlY,weights,bias,'Stride',2);

offset = parameters.batchnormSkip.Offset;
scale = parameters.batchnormSkip.Scale;
trainedMean = state.batchnormSkip.TrainedMean;
trainedVariance = state.batchnormSkip.TrainedVariance;

if doTraining
    [dlYSkip,trainedMean,trainedVariance] = batchnorm(dlYSkip,offset,scale,trainedMean,trainedVariance);
    % Update state
    state.batchnormSkip.TrainedMean = trainedMean;
    state.batchnormSkip.TrainedVariance = trainedVariance;
    dlYSkip = batchnorm(dlYSkip,offset,scale,trainedMean,trainedVariance);

% Convolution
weights = parameters.conv2.Weights;
bias = parameters.conv2.Bias;
dlY = dlconv(dlY,weights,bias,'Padding','same','Stride',2);

% Batch normalization, ReLU
offset = parameters.batchnorm2.Offset;
scale = parameters.batchnorm2.Scale;
trainedMean = state.batchnorm2.TrainedMean;
trainedVariance = state.batchnorm2.TrainedVariance;

if doTraining
    [dlY,trainedMean,trainedVariance] = batchnorm(dlY,offset,scale,trainedMean,trainedVariance);
    % Update state
    state.batchnorm2.TrainedMean = trainedMean;
    state.batchnorm2.TrainedVariance = trainedVariance;
    dlY = batchnorm(dlY,offset,scale,trainedMean,trainedVariance);

dlY = relu(dlY);

% Convolution
weights = parameters.conv3.Weights;
bias = parameters.conv3.Bias;
dlY = dlconv(dlY,weights,bias,'Padding','same');

% Batch normalization
offset = parameters.batchnorm3.Offset;
scale = parameters.batchnorm3.Scale;
trainedMean = state.batchnorm3.TrainedMean;
trainedVariance = state.batchnorm3.TrainedVariance;

if doTraining
    [dlY,trainedMean,trainedVariance] = batchnorm(dlY,offset,scale,trainedMean,trainedVariance);
    % Update state
    state.batchnorm3.TrainedMean = trainedMean;
    state.batchnorm3.TrainedVariance = trainedVariance;
    dlY = batchnorm(dlY,offset,scale,trainedMean,trainedVariance);

% Addition, ReLU
dlY = dlYSkip + dlY;
dlY = relu(dlY);

% Fully connect, softmax (labels)
weights = parameters.fc1.Weights;
bias = parameters.fc1.Bias;
dlY1 = fullyconnect(dlY,weights,bias);
dlY1 = softmax(dlY1);

% Fully connect (angles)
weights = parameters.fc2.Weights;
bias = parameters.fc2.Bias;
dlY2 = fullyconnect(dlY,weights,bias);


Mini-Batch Preprocessing Function

The preprocessMiniBatch function preprocesses the data using the following steps:

  1. Extract the data from the incoming cell array and concatenate into a numeric array. Concatenating over the fourth dimension adds a third dimension to each image, to be used as a singleton channel dimension.

  2. Normalize the pixel values between 0 and 1.

function X = preprocessMiniBatch(data)    
    % Extract image data from cell and concatenate
    X = cat(4,data{:});
    % Normalize the images.
    X = X/255;

See Also

| | | | | | | | | |

Related Topics