Main Content

Custom Python Model Predict

Predict responses using pretrained custom Python model

Since R2024a

expand all in page
  • Custom Python Model Predict Block Icon

Libraries:
Statistics and Machine Learning Toolbox / Deep Learning Toolbox / Python Models / Python Neural Networks

Description

The Custom Python Model Predict block predicts responses using a pretrained custom Python® model running in the MATLAB® Python environment. MATLAB supports the reference implementation of Python, often called CPython. If you use a Mac or Linux® platform, you already have Python installed. If you use Windows®, you need to install a distribution, such as those found at https://www.python.org/downloads/. For more information, see Configure Your System to Use Python. The Custom Python Model Predict block has been tested using Python version 3.10.

Load a custom Python model into the block by specifying the path to a Python file that defines load_model() and predict() functions. The Custom Python Model Predict block calls the load_model() function once in Python with arguments you specify in Arguments to load_model(), and then calls the predict() function at every simulation step. The input port In1 receives input data, and the output port Out1 returns predicted responses for the input data. You can add input and output ports using the Inputs and Outputs tabs of the Block Parameters dialog box (see Inputs and Outputs).

Note

You cannot run the Custom Python Model Predict block in Rapid Accelerator mode.

Examples

Predict Responses Using Custom Python Model in Simulink

Predict Responses Using Custom Python Model in Simulink

Use the Custom Python Model Predict block for prediction in Simulink®. The block accepts an observation (consisting of predictor data and a noisy response), and sends it to a custom Python® model that is configured for prediction. The block executes the custom model in Python and returns the predicted response and mean squared error for the observation.

Ports

Input

expand all

Input data, specified as a numeric array. You can rearrange the dimensions of the input data that the block passes to the Python predict() function by specifying a permutation vector on the Inputs tab of the Block Parameters dialog box (see Inputs).

Data Types: single | double | half | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | Boolean | fixed point

Output

expand all

Predicted responses, returned as a numeric array. You can rearrange the dimensions of the output data returned by the Python model by specifying a permutation vector on the Outputs tab of the Block Parameters dialog box (see Outputs).

Data Types: single | double | half | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | Boolean

Parameters

expand all

To edit block parameters interactively, use the Property Inspector. From the Simulink® Toolstrip, on the Simulation tab, in the Prepare gallery, select Property Inspector.

Specify model file

Specify the name or path of a Python model file, or click the Browse button. The file must contain the definitions of two functions: load_model() and predict(), and can optionally contain a reset_model() function.

  • The load_model() function must have the signature

    model = load_model(input1,input2, ...)
    where model can have any Python datatype, and the input arguments correspond to the list entries in Arguments to load_model().

  • The predict() function must have the signature

    outputList = predict(model,inputList)
    where model is the model object returned by load_model(). inputList is a NumPy ndarray whose elements correspond to the block input ports specified on the Inputs tab of the Block Parameters dialog box. outputList is an array whose elements correspond to the outputs of the predict() function.

  • If model is a Python stateful model, you can define a reset_model() function, which must have the signature

    updated_model = reset_model(model)
    where model is the model object returned by load_model(), and updated_model is a copy of model with its state updated. If you define a reset_model() function, the Custom Python Model Predict block calls the reset_model() function in Python after calling load_model().

Programmatic Use

Block Parameter: PythonModulePath
Type: character vector
Values: Python file | path to Python file
Default: "untitled"

Specify a comma-separated list of strings or numeric arrays that the Custom Python Model Predict block passes to the load_model() function specified by Path to Python file defining load_model() and predict().

Programmatic Use

Block Parameter: LoadModelArgs
Type: comma-separated list
Values: string | numeric array

Specify the discrete interval between sample time hits or specify another type of sample time, such as continuous (0) or inherited (–1). For more options, see Types of Sample Time (Simulink).

By default, the Custom Python Model Predict block inherits sample time based on the context of the block within the model.

Programmatic Use

Block Parameter: SampleTime
Type: string scalar or character vector
Values: scalar
Default: "–1"

Inputs

Input port properties, specified as a table. Each row of the table corresponds to an input port of the Custom Python Model Predict block. Double-click a table cell entry to edit its value, and use the Up and Down buttons to reorder the table rows. Add and delete input ports by clicking the New and Delete buttons, respectively. If you specify multiple input ports, their order must correspond to the inputList order in the Python predict() function (see Path to Python file defining load_model() and predict()).

The table has the following columns:

  • Input Name — Block input port label, specified as a character vector. The block does not pass the input port label to the Python model.

  • Python Datatype — Python or NumPy datatype to which the Custom Python Model Predict block converts incoming data before passing it to the Python predict() function, specified as a character vector. The block supports the Python numeric datatypes "int" and "float", and the NumPy numeric datatypes "float16", "float32", "float64", "int8", "uint8", "int16", "uint16", "int32", "uint32", "int64", and "uint64". The default value is "float32".

  • Permutation to Python — New dimension arrangement for the input data, specified as a numeric vector with unique positive integer elements that represent the dimensions of the input data (see permute). For example, if the input data is a 2D matrix, you can specify [2 1] to switch the row and column dimensions. The Custom Python Model Predict block passes the rearranged array to the Python model.

  • Python NumDims — Number of dimensions for the input data, specified as a nonnegative integer. The default value is "inherit", which corresponds to the dimensionality of the Simulink input signal. The Custom Python Model Predict block converts the input data in Simulink to a Python array with the specified dimensions, and then passes the data to the Python predict() function. The input data cannot contain more dimensions than the specified number, unless the extra dimensions are singletons. The block does not pass these extra singleton dimensions to Python. If the input data has fewer dimensions than the specified number, the block adds trailing singleton dimensions, as needed.

Programmatic Use

Block Parameter: InputTable
Type: cell array

Outputs

Output port properties, specified as a table. Each row of the table corresponds to an individual output port of the Custom Python Model Predict block. Double-click a table cell entry to edit its value, and use the Up and Down buttons to reorder the table rows. Add or delete output ports by clicking the New and Delete buttons, respectively. If you specify multiple output ports, their order must correspond to the output order in the Python model.

The table has the following columns:

  • Output Name — Block output port label, specified as a character vector.

  • Permutation from Python — New dimension ordering for the array that the Custom Python Model Predict block passes to the output port, specified as a numeric vector with unique positive integer elements (see permute).

  • Max MATLAB Dim Sizes — Maximum size of the block output along each dimension, specified as an array of positive integers. Specify this parameter only if your Python model is capable of returning variable-sized output during a single simulation run.

Programmatic Use

Block Parameter: OutputTable
Type: cell array

Block Characteristics

Data Types

Boolean | double | enumerated | fixed point | half | integer | single

Direct Feedthrough

yes

Multidimensional Signals

yes

Variable-Size Signals

yes

Zero-Crossing Detection

no

Version History

Introduced in R2024a

See Also

Blocks