Image Classifier

Classify data using a trained deep learning neural network

expand all in page

Library:
深度学习工具箱/深神经膜ral Networks

Description

TheImage Classifierblock predicts class labels 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.

Limitations

TheImage Classifierblock does not support sequence networks and multiple input and multiple output networks (MIMO).
TheImage Classifierblock does not support MAT-file logging.

Ports

Input

expand all

`image`— Image or feature data
numeric array

Ah-by-w-by-c-by-Nnumeric array, whereh,w, andcare the height, width, and number of channels of the images, respectively, andNis the number of images.

AN-by-numFeaturesnumeric array, whereNis the number of observations andnumFeaturesis the number of features of the input data.

If the array containsNaNs, then they are propagated through the network.

Output

expand all

`ypred`— Predicted class labels
enumerated

Predicted class labels with the highest score, returned as aN-by-1 enumerated vector of labels, whereNis the number of observations.

`scores`— Predicted class scores
matrix

Predicted scores, returned as aN-by-Kmatrix, whereNis the number of observations, andKis the number of classes.

`labels`— Class labels for predicted scores
matrix

Labels associated with the predicted scores, returned as aN-by-Kmatrix, whereNis the number of observations, andKis the number of classes.

Parameters

expand all

`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 aSeriesNetwork,DAGNetwork, ordlnetworkobject.
Network from MATLAB function— Import a pretrained network from a MATLAB function. For example, by using thegooglenetfunction.

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 theBrowsebutton to locate the file.

Dependencies

要启用该参数,设置Networkparameter toNetwork 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, usegooglenetfunction to import the pretrained GoogLeNet model.

Dependencies

要启用该参数,设置Networkparameter toNetwork 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'

`Resize input`— Resize input dimensions
`on`(default) |`从`

Resize the data at the input port to the input size of the network.

Programmatic Use

Block Parameter:ResizeInput

Type:character vector, string

Values:'off'|'on'

Default:'on'

`Classification`— Output predicted label with highest score
`on`(default) |`从`

Enable output portypredthat outputs the label with the highest score.

Programmatic Use

Block Parameter:Classification

Type:character vector, string

Values:'off'|'on'

Default:'on'

`Predictions`— Output all scores and associated labels
`从`(default) |`on`

Enable output portsscoresandlabelsthat output all predicted scores and associated class labels.

Programmatic Use

Block Parameter:Predictions

Type:character vector, string

Values:'off'|'on'

Default:'off'

Model Examples

Classify Images in Simulink Using GoogLeNet

Classify an image in Simulink® using theImage Classifierblock. The example uses the pretrained deep convolutional neural network GoogLeNet to perform the classification.

Classify ECG Signals in Simulink Using Deep Learning

Use wavelet transforms and a deep learning network within a Simulink (R) model to classify ECG signals. This example uses the pretrained convolutional neural network from theClassify Time Series Using Wavelet Analysis and Deep Learningexample of the Wavelet Toolbox™ to classify ECG signals based on images from the CWT of the time series data. For information on training, see Classify Time Series Using Wavelet Analysis and Deep Learning (Wavelet Toolbox).

Extended Capabilities

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

Usage notes and limitations:

TheLanguageparameter in theConfiguration Parameters>Code Generationgeneral category must be set toC++.
For ERT-based targets, theSupport: variable-size signalsparameter in theCode Generation>Interfacepane must be enabled.
For a list of networks and layers supported for code generation, seeNetworks and Layers Supported for Code Generation(MATLAB Coder).

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

Usage notes and limitations:

TheLanguageparameter in theConfiguration Parameters>Code Generationgeneral category must be set toC++.
For a list of networks and layers supported for CUDA^®code generation, seeSupported Networks, Layers, and Classes(GPU Coder).
To learn more about generating code for Simulink models containing theImage Classifierblock, seeCode Generation for a Deep Learning Simulink Model to Classify ECG Signals(GPU Coder).

Image Classifier

Description

Limitations