Deploy an ML Model with the ML Model Service
The Machine Learning (ML) model service allows you to deploy machine learning models to your machine. This can mean deploying:
- a model you trained
- a model from the registry that another user has shared publicly
- a model trained outside the Viam platform that you have uploaded to the registry privately or publicly
- a model trained outside the Viam platform that’s already available on your machine
After deploying your model, you need to configure an additional service to use the deployed model.
For example, you can configure an mlmodel vision service and a transform camera to visualize the predictions your model makes.
Supported models
Built-in models
You can use the following built-in model of the service:
| Model | Description |
|---|---|
tflite_cpu | Runs a TensorFlow Lite model that you have trained or uploaded on the CPU of your machine. |
Modular resources
Search for additional ML model models that you can add from the Viam Registry:
For configuration information, click on the model name:
Add support for other models
If none of the existing models of the ML model service fit your use case, you can create a modular resource to add support for it.
ML models must be designed in particular shapes to work with the mlmodel classification or detection model of Viam’s vision service.
Follow these instructions to design your modular ML model service with models that work with vision.
Note
For some models of the ML model service, like the Triton ML model service for Jetson boards, you can configure the service to use either the available CPU or a dedicated GPU.
Used with
Models from registry
You can search the machine learning models that are available to deploy on this service from the registry here:
Versioning for deployed models
If you upload or train a new version of a model, Viam automatically deploys the latest version of the model to the machine.
If you do not want Viam to automatically deploy the latest version of the model, you can edit the "packages" array in the JSON configuration of your machine.
This array is automatically created when you deploy the model and is not embedded in your service configuration.
You can get the version number from a specific model version by navigating to the models page finding the model’s row, clicking on the right-side menu marked with … and selecting Copy package JSON. For example: 2024-02-28T13-36-51.
The model package config looks like this:
"packages": [
{
"package": "<model_id>/<model_name>",
"version": "YYYY-MM-DDThh-mm-ss",
"name": "<model_name>",
"type": "ml_model"
}
]
API
The MLModel service supports the following methods:
| Method Name | Description |
|---|---|
Infer | Take an already ordered input tensor as an array, make an inference on the model, and return an output tensor map. |
Metadata | Get the metadata (such as name, type, expected tensor/array shape, inputs, and outputs) associated with the ML model. |
DoCommand | Send arbitrary commands to the resource. |
Close | Safely shut down the resource and prevent further use. |
Tip
The following code examples assume that you have a machine configured with an MLModel service, and that you add the required code to connect to your machine and import any required packages at the top of your code file.
Go to your machine’s CONNECT tab’s Code sample page on the Viam app for boilerplate code to connect to your machine.
Infer
Take an already ordered input tensor as an array, make an inference on the model, and return an output tensor map.
Parameters:
input_tensors(Dict[str, NDArray]): A dictionary of input flat tensors, as specified in the metadata.timeout(Optional[float]): An option to set how long to wait (in seconds) before calling a time-out and closing the underlying RPC call.
Returns:
- (
Dict[str, NDArray]): A dictionary of output flat tensors as specified in the metadata, after being run through an inference engine.
For more information, see the Python SDK Docs.
import numpy as np
my_mlmodel = MLModelClient.from_robot(robot=robot, name="my_mlmodel_service")
nd_array = np.array([1, 2, 3], dtype=np.float64)
input_tensors = {"0": nd_array}
output_tensors = await my_mlmodel.infer(input_tensors)
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.tensors(ml.Tensors): The input map of tensors, as specified in the metadata.
Returns:
- (ml.Tensors): The output map of tensors, as specified in the metadata, after being run through an inference engine.
- (error): An error, if one occurred.
For more information, see the Go SDK Docs.
myMLModel, err := mlmodel.FromRobot(robot, "my_mlmodel_service")
input_tensors := ml.Tensors{"0": tensor.New(tensor.WithShape(1, 2, 3), tensor.WithBacking(6))}
output_tensors, err := myMLModel.Infer(ctx.Background(), input_tensors)
Metadata
Get the metadata: name, data type, expected tensor/array shape, inputs, and outputs associated with the ML model.
Parameters:
timeout(Optional[float]): An option to set how long to wait (in seconds) before calling a time-out and closing the underlying RPC call.
Returns:
- (
Metadata): Name, type, expected tensor/array shape, inputs, and outputs associated with the ML model.
For more information, see the Python SDK Docs.
my_mlmodel = MLModelClient.from_robot(robot=robot, name="my_mlmodel_service")
metadata = await my_mlmodel.metadata()
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.
Returns:
- (MLMetadata): Struct containing the metadata of the model file, such as the name of the model, what kind of model it is, and the expected tensor/array shape and types of the inputs and outputs of the model.
- (error): An error, if one occurred.
For more information, see the Go SDK Docs.
myMLModel, err := mlmodel.FromRobot(robot, "my_mlmodel_service")
metadata, err := myMLModel.Metadata(ctx.Background())
DoCommand
Execute model-specific commands that are not otherwise defined by the service API.
For built-in service models, any model-specific commands available are covered with each model’s documentation.
If you are implementing your own navigation service and add features that have no built-in API method, you can access them with DoCommand.
Parameters:
command(Mapping[str, ValueTypes]): The command to execute.timeout(Optional[float]): An option to set how long to wait (in seconds) before calling a time-out and closing the underlying RPC call.
Returns:
- (Mapping[str, ValueTypes]): Result of the executed command.
Raises:
NotImplementedError: Raised if the Resource does not support arbitrary commands.
my_mlmodel = MLModelClient.from_robot(robot=robot, name="my_mlmodel_service")
my_command = {
"command": "dosomething",
"someparameter": 52
}
await my_mlmodel.do_command(my_command)
For more information, see the Python SDK Docs.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.cmd(map[string]interface{}): The command to execute.
Returns:
- (map[string]interface{}): Result of the executed command.
- (error): An error, if one occurred.
myMLModel, err := mlmodel.FromRobot(robot, "my_mlmodel_service")
resp, err := myMLModel.DoCommand(ctx, map[string]interface{}{"command": "dosomething", "someparameter": 52})
For more information, see the Go SDK Docs.
Close
Safely shut down the resource and prevent further use.
Parameters:
- None
Returns:
- None
my_mlmodel = MLModelClient.from_robot(robot, "my_mlmodel_service")
await my_mlmodel.close()
For more information, see the Python SDK Docs.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.
Returns:
- (error) : An error, if one occurred.
myMLModel, err := mlmodel.FromRobot(robot, "my_mlmodel_service")
err := myMLModel.Close(ctx)
For more information, see the Go SDK Docs.
Use the ML model service with the Viam Python SDK
To use the ML model service from the Viam Python SDK, install the Python SDK using the mlmodel extra:
pip install 'viam-sdk[mlmodel]'
You can also run this command on an existing Python SDK install to add support for the ML model service.
See the Python documentation for more information about the MLModel service in Python.
See Program a machine for more information about using an SDK to control your machine.
Next steps
To make use of your model with your machine, add a vision service or a modular resource:
Was this page helpful?
Glad to hear it! If you have any other feedback please let us know:
We're sorry about that. To help us improve, please tell us what we can do better:
Thank you!