PyTorch Model Predict

Predict responses using pretrained Python PyTorch model

Since R2024a

• 

×

Libraries:
Deep Learning Toolbox / Python Neural Networks

Description

The PyTorch Model Predict block predicts responses using a pretrained Python^® PyTorch^® 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. Your MATLAB Python environment must have the torch module installed. The PyTorch Model Predict block has been tested using Python version 3.10 and torch version 2.0.1.

Load a Python model into the block by specifying the path to a PyTorch model file that you saved in Python using torch.save() or torch.jit.save(). You can optionally load a Python function to preprocess the input data that Simulink^® passes to the Python model, and a Python function to postprocess the predicted responses from the model.

The input port In1 receives input data, optionally rearranges the input array dimensions, and converts the input data to a Python array. The preprocessing function (if specified) processes the converted data in Python and passes it to the PyTorch model. The model generates predicted responses for the input data in Python and passes the responses to the Python postprocessing function (if specified). The output port Out1 returns the predicted responses.

You can add and configure input and output ports using the Inputs and Outputs tabs of the Block Parameters dialog box (see Inputs and Outputs). The software attempts to automatically populate the table in each tab when you click the Autofill Fields From Model File button on the Specify model file tab.

Note

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

Examples

Classify Images Using PyTorch Model Predict Block

Classify images using PyTorch Model Predict block.

• Open Live Script

Predict Responses Using PyTorch Model Predict Block

Predict Responses Using PyTorch Model Predict block.

• Open Live Script

Ports

Input

In1 — Input data

numeric array

Input data, specified as a numeric array. You can rearrange the dimensions of the input data that the block passes to the Python model 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

Out1 — Predicted responses

numeric array

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

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

Load command — Load command for Python model

torch.load() (default) | torch.jit.load() | load_state_dict()

Select the load command for the Python model. The PyTorch Model Predict block supports models saved in Python using torch.save() and torch.jit.save().

Note

If you select torch.load() or load_state_dict(), you must define the PyTorch model class in a .py file before you save the model using torch.save().

Programmatic Use

Block Parameter: LoadCommandPopup

Type: character vector

Values: "torch.load()" | "torch.jit.load()" | "load_state_dict()"

Default: "torch.load()"

Path to model file or state_dict file — Name or path of Python PyTorch model file or state_dict file

untitled (default) | character vector

Specify the name or path of a Python PyTorch model file or state_dict file, or click the Browse button. You must save the file in Python using torch.save() or torch.jit.save().

Programmatic Use

Block Parameter: ModelFile

Type: character vector

Values: path to PyTorch model file | path to state_dict file

Default: "untitled"

Model class name and optional arguments (if using load_state_dict) — Model class name and optional arguments

character vector

PyTorch model class name, specified as a character vector. Specify this parameter only if Load command is load_state_dict(). You can optionally specify arguments to the model using function call format (for example, "torchvision.models.alexnet(num_classes=1000, dropout=0.2)").

Programmatic Use

Block Parameter: ModelClassName

Type: character vector

Values: PyTorch model class name | function call to PyTorch model class

Sample time (–1 for inherited) — Option to specify sample time

–1 (default) | scalar

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 PyTorch 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

Inputs — Input port properties

table

Input port properties, specified as a table. Each row of the table corresponds to an individual input port of the PyTorch Model Predict block. The software attempts to automatically populate the input port properties table when you click the Autofill Fields From Model File button on the Specify model file tab.

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 input order in the Python model (or Python preprocessing function, if specified).

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 PyTorch Model Predict block converts incoming data before passing it to Python, 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 PyTorch Model Predict block passes the rearranged array to the Python model (or Python preprocessing function, if specified).

• 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 PyTorch 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 (or Python preprocessing function, if specified). 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

Outputs — Output port properties

table

Output port properties, specified as a table. Each row of the table corresponds to an individual output port of the PyTorch Model Predict block. The software attempts to automatically populate the output port properties table when you click the Autofill Fields From Model File button on the Specify model file tab.

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 (or Python postprocessing function, if specified).

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 PyTorch 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

Pre/Post-processing

Path to Python file defining preprocess() — Name or path of Python preprocessing function file

character vector

Specify the name or path of a file defining an optional Python preprocessing function for the input data, or click the Browse button. When the PyTorch Model Predict receives data, it converts it to a NumPy array. The preprocessing function processes the converted data in Python, and then passes the data to the Python model.

The preprocessing file must define a Python function with the signature

outputList = preprocess(model,inputList)

where outputList and inputList are lists of NumPy ndarray objects, and model is the Python model object. The number of elements in inputList must match the number of input ports in the PyTorch Model Predict block. The number of elements in outputList must match the number of inputs required by the Python model. The preprocessing file can be the same as the postprocessing file specified by Path to Python file defining postprocess() if the file contains both defining functions.

Programmatic Use

Block Parameter: PreprocessingFilePath

Type: character vector

Values: Python file | path to Python file

Path to Python file defining postprocess() — Name or path of Python postprocessing function file

character vector

Specify the name or path of a file defining an optional Python postprocessing function for the output data, or click the Browse button. The PyTorch Model Predict block processes the output data from the Python model using the Python function, and then outputs the data from the block.

The postprocessing file must define a Python function with the signature

outputList = postprocess(model,inputList)

where outputList and inputList are lists of NumPy ndarray objects, and model is the model object. The number of elements in inputList must match the number of outputs in the Python model. The number of elements in outputList must match the number of output ports in the PyTorch Model Predict block. The postprocessing file can be the same as the preprocessing specified by Path to Python file defining preprocess() if the file contains both defining functions.

Programmatic Use

Block Parameter: PostprocessingFilePath

Type: character vector

Values: Python file | path to Python file

Block Characteristics

Data Types	Boolean | double | enumerated | fixed point | half | integer | single
Direct Feedthrough	yes
Multidimensional Signals	no
Variable-Size Signals	no
Zero-Crossing Detection	no

Tips

• If you encounter a Python library conflict, use the pyenv function to specify the ExecutionMode name-value argument as "OutOfProcess".

Version History

Introduced in R2024a