predict

Compute deep learning network output for inference

collapse all in page

Syntax

dlY = predict(dlnet,dlX)
dlY = predict(dlnet,dlX1,...,dlXM)
[dlY1,...,dlYN] = predict(___)
[dlY1,...,dlYK] = predict(___,'Outputs',layerNames)
[___,state] = predict(___)

Description

Some deep learning layers behave differently during training and inference (prediction). For example, during training, dropout layers randomly set input elements to zero to help prevent overfitting, but during inference, dropout layers do not change the input.

To compute network outputs for inference, use the predict function. To compute network outputs for training, use the forward function. For prediction with SeriesNetwork and DAGNetwork objects, see predict.

example

dlY = predict(dlnet,dlX) returns the network output dlY during inference given the input data dlX and the network dlnet with a single input and a single output.

dlY = predict(dlnet,dlX1,...,dlXM) returns the network output dlY during inference given the M inputs dlX1, ...,dlXM and the network dlnet that has M inputs and a single output.

[dlY1,...,dlYN] = predict(___) returns the N outputs dlY1, …, dlYN during inference for networks that have N outputs using any of the previous syntaxes.

[dlY1,...,dlYK] = predict(___,'Outputs',layerNames) returns the outputs dlY1, …, dlYK during inference for the specified layers using any of the previous syntaxes.

[___,state] = predict(___) also returns the updated network state using any of the previous syntaxes.

Tip

For prediction with SeriesNetwork and DAGNetwork objects, see predict.

Examples

collapse all

Open Live Script

This example shows how to make predictions using a dlnetwork object 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 dlnetwork objects, you must split the data into mini-batches manually.

Load dlnetwork Object

Load a trained dlnetwork object and the corresponding classes.

s = load("digitsCustom.mat");
dlnet = s.dlnet;
classes = s.classes;

Load Data for Prediction

Load the digits data for prediction.

digitDatasetPath = fullfile(matlabroot,'toolbox','nnet','nndemos', ...
    'nndatasets','DigitDataset');
imds = imageDatastore(digitDatasetPath, ...
    'IncludeSubfolders',true);

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,...
    "MiniBatchSize",miniBatchSize,...
    "MiniBatchFcn", @preprocessMiniBatch,...
    "MiniBatchFormat","SSCB");

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

numObservations = numel(imds.Files);
YPred = strings(1,numObservations);

predictions = [];

% Loop over mini-batches.
while hasdata(mbq)
    
    % Read mini-batch of data.
    dlX = next(mbq);
       
    % Make predictions using the predict function.
    dlYPred = predict(dlnet,dlX);
   
    % Determine corresponding classes.
    predBatch = onehotdecode(dlYPred,classes,1);
    predictions = [predictions predBatch];
  
end

Visualize some of the predictions.

idx = randperm(numObservations,9);

figure
for i = 1:9
    subplot(3,3,i)
    I = imread(imds.Files{idx(i)});    
    label = predictions(idx(i));
    imshow(I)
    title("Label: " + string(label))
  
end

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;
end

Input Arguments

collapse all

Network for custom training loops, specified as a dlnetwork object.

Input data, specified as a formatted dlarray. For more information about dlarray formats, see the fmt input argument of dlarray.

Layers to extract outputs from, specified as a string array or a cell array of character vectors containing the layer names.

  • If layerNames(i) corresponds to a layer with a single output, then layerNames(i) is the name of the layer.

  • If layerNames(i) corresponds to a layer with multiple outputs, then layerNames(i) is the layer name followed by the character "/" and the name of the layer output: 'layerName/outputName'.

Output Arguments

collapse all

Output data, returned as a formatted dlarray. For more information about dlarray formats, see the fmt input argument of dlarray.

Updated network state, returned as a table.

The network state is a table with three columns:

  • Layer – Layer name, specified as a string scalar.

  • Parameter – Parameter name, specified as a string scalar.

  • Value – Value of parameter, specified as a numeric array object.

The network state contains information remembered by the network between iterations. For example, the state of LSTM and batch normalization layers.

Update the state of a dlnetwork using the State property.

Extended Capabilities

See Also

| | | |

Topics

Introduced in R2019b

Deep Learning Toolbox Documentation

Support