Integrating your Watson Machine Learning models into Core ML apps

From straightforward machine learning models to complex neural networks, you can build and train your models using IBM Watson Machine Learning. With Core ML, you can then build iOS apps that use those trained models on your device.



  1. Design and build a model or neural network using a framework that is supported with Core ML by Watson Machine Learning.
    See: Supported frameworks.

  2. Train the model using the experiment builder in IBM Watson Studio so that your model appears in the Assets page of your project with a STATUS of "trained".



After training a model in Watson Studio, you can download the Core ML model (.mlmodel) file for your trained model:

  1. On the Assets page of your project, find your trained model in the Models section. From the ACTIONS menu for that model, select "Deploy". (This takes you to the Deployments tab of the model details page.)

  2. In the Deployments tab of the model details page, click Add Deployment.

  3. Fill in deployment details:

  4. Click Save.

  5. In the Implementation area of the deployment details page that opens, click button labeled Download Core ML model.

  6. Uncompress the downloaded file to get the Core ML model (.mlmodel) file, which is always named "model.mlmodel" by default.