Open topic with navigation
To add an object to a database of objects, you can:
Perform training in separate steps. Create a new (empty) object, then add training images, and then train Media Server, using separate actions. You can also add metadata to the object and configure training options, but these are optional steps. You might want to perform training in this way if you are building a front end application that responds to user input.
Perform training in a single action. You might use this approach when writing a script to train Media Server from a collection of images and metadata.