coremltools

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

What is coremltools?

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

Overview of coremltools

What it is

coremltools is a Python package developed by Apple that provides supporting tools for converting, editing, and validating machine learning models to the Core ML format. It supports conversion from training libraries such as TensorFlow 1.x, TensorFlow 2.x, PyTorch, and non-neural network frameworks including scikit-learn, XGBoost, and LibSVM. The package also allows reading, writing, and optimizing Core ML models, and on macOS, verifying conversions by making predictions using Core ML.

Key features

  • Convert trained models from TensorFlow 1.x, TensorFlow 2.x, PyTorch, scikit-learn, XGBoost, and LibSVM to the Core ML format.
  • Read, write, and optimize Core ML models.
  • Verify conversion or creation on macOS by making predictions using Core ML.
  • Integrate converted Core ML models with apps using Xcode.

Use cases

coremltools is used by developers who need to integrate machine learning models into Apple apps. After converting models from popular training libraries to Core ML format, the models can be deployed on Apple devices, leveraging the CPU, GPU, and Neural Engine for on-device performance. This approach removes the need for a network connection, helps keep user data private, and maintains app responsiveness.

Getting started

To install the latest stable version using pip:shellpip install coremltoolsTo install the latest dev release:shellpip install coremltools==9.1.dev1

License and pricing

coremltools is open source under the BSD-3-Clause license.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/applecoremltools.svg)](https://yunodb.com/tools/applecoremltools?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/applecoremltools?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/applecoremltools.svg" alt="Featured on YunoDB" height="20"></a>