Skip to main content
Version: 6.1

ML Studio Step-by-Step Guide

This guide provides an end-to-end ML Studio workflow using a demonstration example: configuring a runtime environment, creating and editing an algorithm, deploying and synchronizing the algorithm, writing code in Jupyter, and training and applying a model through the API and SML. For a description of the interface and its fields, see ML Studio Interface.

The screenshots use the tutorial-demo demonstration object.

The workflow is performed in the following order: configure an environment - register an algorithm - change its image if necessary - deploy the image to the environment - synchronize the algorithm - train and apply a model.

Contents​

  1. Configuring a Runtime Environment
  2. Creating an Algorithm
  3. Editing an Algorithm
  4. Deploying an Algorithm
  5. Synchronizing an Algorithm
  6. Training and Applying a Model (Jupyter + API)
  7. Training and Applying a Model Through SML (train and predict Commands)