Core ML Tools

Use Core ML Tools (coremltools) to convert machine learning models from third-party libraries to the Core ML format. This Python package contains the supporting tools for converting models from training libraries such as the following:

• TensorFlow 1.x
• TensorFlow 2.x
• PyTorch
• Non-neural network frameworks:
  • scikit-learn
  • XGBoost
  • LibSVM

With coremltools, you can:

• Convert trained models to the Core ML format.
• Read, write, and optimize Core ML models.
• Verify conversion/creation (on macOS) by making predictions using Core ML.

After conversion, you can integrate the Core ML models with your app using Xcode.

Install

The latest stable version is available from https://pypi.org/project/coremltools/

To install it use pip or the Python package manager of your choice.

pip install coremltools

To install the latest dev release:

pip install coremltools==9.1.dev1

Core ML

Core ML is an Apple framework to integrate machine learning models into your app. Core ML provides a unified representation for all models. Your app uses Core ML APIs and user data to make predictions, and to fine-tune models, all on the user’s device. Core ML optimizes on-device performance by leveraging the CPU, GPU, and Neural Engine while minimizing its memory footprint and power consumption. Running a model strictly on the user’s device removes any need for a network connection, which helps keep the user’s data private and your app responsive.

Resources

To install coremltools, see Installing Core ML Tools. For more information, see the following:

• Release Notes
• Guide and examples
• API Reference
• Core ML Specification
• Building from Source
• Contribution Guidelines