Predict

Predict responses using a trained deep learning neural network

Since R2020b

• 

×

Libraries:
Deep Learning Toolbox / Deep Neural Networks

Description

The Predict block predicts responses for the data at the input by using the trained network specified through the block parameter. This block allows loading of a pretrained network into the Simulink^® model from a MAT-file or from a MATLAB^® function.

Note

Use the Predict block to make predictions in Simulink. To make predictions programmatically using MATLAB code, use the minibatchpredict or predict function.

Examples

Lane and Vehicle Detection in Simulink Using Deep Learning

Use deep convolutional neural networks inside a Simulink® model to perform lane and vehicle detection. This example takes the frames from a traffic video as an input, outputs two lane boundaries that correspond to the left and right lanes of the ego vehicle, and detects vehicles in the frame.

• Open Script

Ports

Input

input — Image, feature, sequence, or time series data

numeric array

The input ports of the Predict block takes the names of the input layers of the loaded network. For example, if you specify imagePretrainedNetwork for MATLAB function, then the input port of the Predict block has the label data. Based on the network loaded, the input to the predict block can be image, sequence, or time series data.

The layout of the input depend on the type of data.

Data	Layout of Predictors
2-D images	A h-by-w-by-c-by-N numeric array, where h, w, and c are the height, width, and number of channels of the images, respectively, and N is the number of images.
Vector sequences	s-by-c matrices, where s is the sequence length, and c is the number of features of the sequences.
2-D image sequences	h-by-w-by-c-by-s arrays, where h, w, and c correspond to the height, width, and number of channels of the images, respectively, and s is the sequence length.
Features	A N-by-numFeatures numeric array, where N is the number of observations, and numFeatures is the number of features of the input data.

If the array contains NaNs, then they are propagated through the network.

Output

output — Predicted scores, responses, or activations

numeric array

The outputs port of the Predict block takes the names of the output layers of the network loaded. For example, if you specify imagePretrainedNetwork for MATLAB function, then the output port of the Predict block is labeled prob_flatten. Based on the network loaded, the output of the Predict block can represent predicted scores or responses.

The predicted scores or responses is returned as a K-by-N array, where K is the number of classes, and N is the number of observations.

If you enable Activations for a network layer, the Predict block creates a new output port with the name of the selected network layer. This port outputs the activations from the selected network layer.

The activations from the network layer is returned as a numeric array. The format of output depends on the type of input data and the type of layer output.

For 2-D image output, activations is an h-by-w-by-c-by-n array, where h, w, and c are the height, width, and number of channels for the output of the chosen layer, respectively, and n is the number of images.

For a single time-step containing vector data, activations is a c-by-n matrix, where c is the number of features in the sequence and n is the number of sequences.

For a multi time-step containing vector data, activations is a c-by-n-by-s matrix, where c is the number of features in the sequence, n is the number of sequences and s is the sequence length.

For a single time-step containing 2-D image data, activations is a h-by-w-by-c-by-n array, where n is the number of sequences, h, w, and c are the height, width, and the number of channels of the images, respectively.

Parameters

Network — Source for trained network

Network from MAT-file (default) | Network from MATLAB function

Specify the source for the trained network. Select one of the following:

• Network from MAT-file— Import a trained network from a MAT-file containing a dlnetwork object.

• Network from MATLAB function— Import a pretrained network from a MATLAB function. For example, to use a pretrained GoogLeNet, create a function pretrainedGoogLeNet in a MATLAB M-file, and then import this function.

  function net = pretrainedGoogLeNet
    net = imagePretrainedNetwork("googlenet");
  end

Programmatic Use

Block Parameter: Network

Type: character vector, string

Values: 'Network from MAT-file' | 'Network from MATLAB function'

Default: 'Network from MAT-file'

File path — MAT-file containing trained network

untitled.mat (default) | MAT-file path or name

This parameter specifies the name of the MAT-file that contains the trained deep learning network to load. If the file is not on the MATLAB path, use the Browse button to locate the file.

Dependencies

To enable this parameter, set the Network parameter to Network from MAT-file.

Programmatic Use

Block Parameter: NetworkFilePath

Type: character vector, string

Values: MAT-file path or name

Default: 'untitled.mat'

MATLAB function — MATLAB function name

squeezenet (default) | MATLAB function name

This parameter specifies the name of the MATLAB function for the pretrained deep learning network. For example, to use a pretrained GoogLeNet, create a function pretrainedGoogLeNet in a MATLAB M-file, and then import this function.

function net = pretrainedGoogLeNet
  net = imagePretrainedNetwork("googlenet");
end

Dependencies

To enable this parameter, set the Network parameter to Network from MATLAB function.

Programmatic Use

Block Parameter: NetworkFunction

Type: character vector, string

Values: MATLAB function name

Default: 'squeezenet'

Mini-batch size — Size of mini-batches

128 (default) | positive integer

Size of mini-batches to use for prediction, specified as a positive integer. Larger mini-batch sizes require more memory, but can lead to faster predictions.

Programmatic Use

Block Parameter: MiniBatchSize

Type: character vector, string

Values: positive integer

Default: '128'

Predictions — Output predicted scores or responses

on (default) | off

Enable output ports that return predicted scores or responses.

Programmatic Use

Block Parameter: Predictions

Type: character vector, string

Values: 'off' | 'on'

Default: 'on'

Input data formats — Input data format of dlnetwork

character vector | string

This parameter specifies the input data format expected by the trained dlnetwork.

Data format, specified as a string scalar or a character vector. Each character in the string must be one of the following dimension labels:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, for an array containing a batch of sequences where the first, second, and third dimension correspond to channels, observations, and time steps, respectively, you can specify that it has the format "CBT".

You can specify multiple dimensions labeled "S" or "U". You can use the labels "C", "B", and "T" once each, at most. The software ignores singleton trailing "U" dimensions after the second dimension.

For more information, see Deep Learning Data Formats.

By default, the parameter uses the data format that the network expects.

Dependencies

To enable this parameter, set the Network parameter to Network from MAT-file to import a trained dlnetwork object from a MAT-file.

Programmatic Use

Block Parameter: InputDataFormats

Type: character vector, string

Values: For a network with one or more inputs, specify text in the form of: "{'inputlayerName1', 'SSC'; 'inputlayerName2', 'SSCB'; ...}". For a network with no input layer and multiple input ports, specify text in the form of: "{'inputportName1/inport1, 'SSC'; 'inputportName2/inport2, 'SSCB'; ...}".

Default: Data format that the network expects. For more information, see Deep Learning Data Formats.

Activations — Output network activations for a specific layer

layers of the network

Use the Activations list to select the layer to extract features from. The selected layers appear as an output port of the Predict block.

Programmatic Use

Block Parameter: Activations

Type: character vector, string

Values: character vector in the form of '{'layerName1',layerName2',...}'

Default: ''

Tips

• You can accelerate your simulations with code generation taking advantage of the Intel^® MKL-DNN library. For more details, see Acceleration for Simulink Deep Learning Models.

Extended Capabilities

C/C++ Code Generation

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

Usage notes and limitations:

• To generate generic C code that does not depend on third-party libraries, in the Configuration Parameters > Code Generation general category, set the Language parameter to C.

• To generate C++ code, in the Configuration Parameters > Code Generation general category, set the Language parameter to C++. To specify the target library for code generation, in the Code Generation > Interface category, set the Target Library parameter. Setting this parameter to None generates generic C++ code that does not depend on third-party libraries.

• For a list of networks and layers supported for code generation, see Networks and Layers Supported for Code Generation (MATLAB Coder).

GPU Code Generation

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

Usage notes and limitations:

• The Language parameter in the Configuration Parameters > Code Generation general category must be set to C++.

• For a list of networks and layers supported for CUDA^® code generation, see Supported Networks, Layers, and Classes (GPU Coder).

• To learn more about generating code for Simulink models containing the Predict block, see Code Generation for a Deep Learning Simulink Model That Performs Lane and Vehicle Detection (GPU Coder).

Version History

Introduced in R2020b

R2024a: SeriesNetwork and DAGNetwork are not recommended

Starting in R2024a, the SeriesNetwork and DAGNetwork objects are not recommended. This recommendation means that SeriesNetwork and DAGNetwork inputs to the Predict block are not recommended. Use the dlnetwork objects instead. dlnetwork objects have these advantages:

• dlnetwork objects are a unified data type that supports network building, prediction, built-in training, visualization, compression, verification, and custom training loops.

• dlnetwork objects support a wider range of network architectures that you can create or import from external platforms.

• The trainnet function supports dlnetwork objects, which enables you to easily specify loss functions. You can select from built-in loss functions or specify a custom loss function.

• Training and prediction with dlnetwork objects is typically faster than LayerGraph and trainNetwork workflows.

Simulink block models with dlnetwork objects behave differently. The predicted scores are returned as a K-by-N matrix, where K is the number of classes, and N is the number of observations. If you have an existing Simulink block model with a SeriesNetwork or DAGNetwork object, follow these steps to use a dlnetwork object instead:

1. Convert the SeriesNetwork or DAGNetwork object to a dlnetwork using the dag2dlnetwork function.

2. If the input to your block is a vector sequence, transpose the matrix using a transpose block to a size s-by-c, where s is the sequence length, and c is the number of features of the sequences.

3. Transpose the predicted scores using a transpose block to an N-by-K array, where N is the number of observations, and K is the number of classes.