Machine Learning

ML training

Viam includes a built-in machine learning (ML) service which provides your machine with the ability to learn from data and adjust its behavior based on insights gathered from that data. Common use cases include:

  • Object detection and classification which enable machines to detect people, animals, plants, or other objects with bounding boxes, and to perform actions when they are detected.
  • Speech recognition, natural language processing, and speech synthesis, which enable machines to verbally communicate with us.

However, your machine can make use of machine learning with nearly any kind of data.

Viam natively supports TensorFlow Lite ML models as long as your models adhere to the model requirements.

Use machine learning with your machine

Collect data 1. Collect

Start by collecting data from your cameras, sensors, or any other source on your machine with the data management service. You can view the data on the Data tab.

Label data 2. Create a Dataset and Label

Once you have collected data, label your data and create a dataset in preparation for training machine learning models.

Train models 3. Train or upload an ML model

Use your labeled data to train your own models for object detection and classification using data from the data management service or add an existing model.

4. Deploy your ML model

To make use of ML models with your machine, use the built-in ML model service to deploy and run the model.

Configure a service 5. Configure a service

For object detection and classification, you can use the vision service, which provides an ml model detector and an ml model classifier model.

For other usage, you can use a modular resource to integrate it with your machine.

Deploy your model 6. Test your detector or classifier

Test your mlmodel detector or classifier.