Customizing Watson Machine Learning deployment runtimes

Create custom Watson Machine Learning deployment runtimes with libraries and packages that are required for your deployments.

If your model requires custom components such as extenal libraries, packages, user-defined transformers, estimators, or user-defined tensors, you can create a custom software specification that is derived from a predefined base specification. Python functions and Python scripts also support custom software specifications.

You can also customize the behavior of package managers.

For more information, see Customizing runtimes with external libraries and packages.

Additionally, you can build custom images based on deployment runtime images that are available in IBM Watson Machine Learning. The images contain preselected open source libraries and selected IBM libraries.

You do this by creating a custom Docker image and adding libraries and packages that are required for your deployments. You can then use the custom image to deploy your Watson Machine Learning assets.

By building custom images, you can optimize the standard software configuration of a runtime for your application needs. You can also use custom images in air-gapped environments with requirements that forbid you to show any operations to the Internet.

For more information, see Building custom images.

Parent topic: Deploying and managing assets