ML Models

Machine Learning (ML) models are mathematical models that can recognize patterns.

The ML model service runs ML models on your machines. Services like the vision service can then use the ML model services to provide your machine with information about its surroundings. The ML model service works with models trained inside and outside the Viam app:

• You can upload externally trained models on the MODELS tab in the DATA section of the Viam app.
• You can train models on data from your machines.
• You can use ML models from the Viam Registry.
• You can use a model trained outside the Viam platform that’s already available on your machine.

Available machine learning models in the registry

You can search the machine learning models that are available to deploy on this service from the registry here:

Model framework support

Viam currently supports the following frameworks:

Versions

If you deploy a model to a machine, Viam automatically assumes that this is the latest version of the model and that you would always like to deploy the latest version of the model to the machine. If you train a new version of that model, Viam will automatically deploy the new version to the machine and replace the old version.

If you do not want Viam to automatically deploy the latest version of the model, you can change packages configuration in the JSON machine configuration. The model package config looks like this:

{
  "package": "<model_id>/<model_name>",
  "version": "YYYY-MM-DDThh-mm-ss",
  "name": "<model_name>",
  "type": "ml_model"
}

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.

If you need to make changes to a model, you can edit or delete it on its page which you can access from the MODELS tab.

Next steps

Use the ML model service to deploy a machine learning model to your machine:

ML Model Service

Deploy machine learning models to a machine and use the vision service to detect or classify images or to create point clouds of identified objects.

Train computer vision models

Use your image data to create and label a dataset and train a computer vision ML model.

Follow one of these tutorials to see ML models in action:

Helmet Monitor

Get an email alert if people are not wearing hard hats.

Colored Object Follower

Instructions for detecting and following a colored object with a rover, like a SCUTTLE robot.

AI Companion Robot

Add object detection, speech recognition, natural language processing, and speech synthesis capabilities to a machine.