Creating deployments from a space (Watson Machine Learning)

Use the tools available from a deployment space to deploy and run models and scripts. The types of deployment available for a model and the type of input supported depends on the model framework.

The types of deployments are:

• Online Also called Web service, this deployment loads the model or Python code when the deployment is created to generate predictions online, in real time.
• Batch to process batches of input submitted from a data file, a connection to a data repository such as a database, or connected data in a storage repository such as a Cloud Object Storage bucket. Batch deployments can be run on demand or on a schedule.

• Core ML downloads the code required to deploy on an iOS device.

• App to make R Shiny apps available for use by users with a link to the endpoint.

For details, see Supported frameworks.