loadLiteRTModel

R2026b

Load pretrained LiteRT model file

Since R2026a

Syntax

model = loadLiteRTModel(modelFileName)

model = loadLiteRTModel(modelFileName,ExecutionMode=ExecutionMode)

Description

Add-On Required: This feature requires the MATLAB Coder Support Package for PyTorch and LiteRT Models add-on.

model = loadLiteRTModel(modelFileName) loads a pretrained LiteRT model file.

model = loadLiteRTModel(modelFileName,ExecutionMode=ExecutionMode) loads a pretrained LiteRT model file using the specified execution mode.

Examples

Load LiteRT Model

Suppose that you have a LiteRT model named siso.tflite that takes one input and returns one output. Create a LiteRTModel object.

myModel = loadLiteRTModel("siso.tflite")

Loading model...
Model loaded.

myModel = 
  LiteRTModel contained in siso.tflite: 

                          Input Specifications                       
    _________________________________________________________________

    Input     Name                    Size                     Type  
    _____    _______    _________________________________    ________
                                                                     
      1      "image"    "<variable-size> x 128 x 128 x 3"    "single"


                      Output Specifications                  
    _________________________________________________________

    Output       Name               Size               Type  
    ______    __________    _____________________    ________
                                                             
      1       "output_0"    "<variable-size> x 1"    "single"


    properties: 
        ModelPath                         -      Path to the model file
        FcnNames                          -      Names of the functions in the model
    methods: 
        invoke                            -      Performs forward inference by invoking a function in the model
        inputSpecifications               -      Returns the input specifications of the model or of a specific function in the model
        outputSpecifications              -      Returns the output specifications of the model or of a specific function in the model
        summary                           -      Displays the input and output specifications of the model or of a specific function in the model

Load LiteRT Model Using MEX Execution Mode

Suppose that you have a LiteRT model named mimo.tflite that takes multiple inputs and returns multiple outputs.

Create a LiteRTModel object by using the MEX execution mode. To use the MEX execution mode, you must install a supported C compiler. For more information about setting up the C/C++ compiler, see Installing and Configuring Prerequisite Products.

myModel = loadLiteRTModel("mimo.tflite",ExecutionMode="MEX")

Loading model...
Model loaded.

myModel = 
  LiteRTModel contained in mimo.tflite: 

                       Input Specifications                    
    ___________________________________________________________

    Input        Name                 Size               Type  
    _____    ____________    ______________________    ________
                                                               
      1      "features_a"    "<variable-size> x 16"    "single"
      2      "features_b"    "<variable-size> x 8"     "single"


                      Output Specifications                  
    _________________________________________________________

    Output       Name               Size               Type  
    ______    __________    _____________________    ________
                                                             
      1       "output_1"    "<variable-size> x 2"    "single"
      2       "output_0"    "<variable-size> x 4"    "single"


    properties: 
        ModelPath                         -      Path to the model file
        FcnNames                          -      Names of the functions in the model
    methods: 
        invoke                            -      Performs forward inference by invoking a function in the model
        inputSpecifications               -      Returns the input specifications of the model or of a specific function in the model
        outputSpecifications              -      Returns the output specifications of the model or of a specific function in the model
        summary                           -      Displays the input and output specifications of the model or of a specific function in the model

Input Arguments

modelFileName — Name of LiteRT model file

character vector | scalar string

Name of the LiteRT model file, specified as a character vector or a scalar string.

Example: "myModelName"

Example: "myfolder/myModelName"

ExecutionMode — Execution Mode

"JIT" (default) | "MEX"

Execution mode to use for MATLAB simulation behavior, specified as "JIT" or "MEX".

JIT code is incompatible with the OpenMP application interface. JIT execution mode does not support multi-threading. If you want to parallelize for-loops, use MEX execution mode. You must install a supported C compiler to use the MEX execution mode. For more information about setting up the C/C++ compiler, see Installing and Configuring Prerequisite Products.

Output Arguments

model — LiteRT model

LiteRTModel object

LiteRT model, returned as a LiteRTModel object.

Limitations

The code generator might apply optimizations that assume the absence of NaN values, which can affect NaN propagation behavior. If model inputs contain NaN values, generated code might produce different results from the reference framework.

Extended Capabilities

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

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

Version History

Introduced in R2026a