Deployment is the final stage of the lifecycle of a model or script, where you run your models and code. Watson Machine Learning provides the tools you need to deploy an asset, such as an SPSS modeler flow, a machine learning model, or a function, depending on what tools are configured for your system.
Following deployment, you can use model management tools to evaluate your models. IBM Watson OpenScale tracks and measures outcomes from your AI models, and helps ensure they remain fair, explainable, and compliant. Watson OpenScale also detects and helps correct the drift in accuracy when an AI model is in production
Service The Watson Studio, Watson Machine Learning, Watson OpenScale, and other supplemental services are not available by default. An administrator must install these services on the IBM Cloud Pak for Data platform. To determine whether a service is installed, open the Services catalog and check whether the service is enabled
To deploy an asset, you must have a deployment space where you can organize the assets you need to create and monitor deployments. A space contains an overview of deployment status, the deployable assets, deployments, associated input and output data, and the associated environments. A deployment makes a copy of a model or script available to test and use. For example, you can create a deployment for a machine learning model so you can submit new data to a model and get a score, or prediction back.
When you promote an asset to a space, components required for a successful deployment, such as a training library, model definition, other dependent assets, or environment definition are automatically promoted as well. After promoting a model and data assets to a deployment space, you can create a deployment in the space.
For models and function code, you can also create a deployment programmatically and view the deployment in the space.