Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

Prepare and leverage image data with Databricks

Access this AI accelerator on GitHub

Visual AI allows you to leverage images in your models just like any other type of data. In this accelerator, you will import image files using Spark and prepare them into a data frame suitable for ingest into DataRobot. Then you will leverage DataRobot through code to rapidly train and deploy a powerful multiclass image classifier.

While there are other methods of ingesting image data into DataRobot, in this notebook you will encode the image data directly into the data frame using base64 encoding. This methodology allows you to keep all of the relevant data in a single data frame, and works well for a Databricks environment. This technique also extends widely to a wide variety of multimodal datasets.

Dive in to go from Databricks image data to a deployed classifier.

Updated September 28, 2023