Skip to content

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

Train-time image augmentation

Train-time image augmentation is a processing step in the DataRobot blueprint that creates new images for training by randomly transforming existing images, thereby increasing the size of (i.e., "augmenting") the training data. These sections describe components of augmentation, the process in which each image is transformed.

Topic Describes...
About augmented models Read an overview of augmention.
Augmentation lists Store all the parameter settings for a given augmentation strategy.
Use case examples See examples of leveraging domain knowledge to craft a beneficial augmentation strategy.

Updated October 26, 2021