For AI agents: visit https://coremltools.readme.io/v4.0/llms.txt for an index of all pages formatted in Markdown and endpoints in OpenAPI. Append .md to any documentation page URL to get its markdown version.
Jump to Content
coremltoolsGuidesAPI ReferenceExamples
HomeGuides
GuidesAPI ReferenceExamplesCore ML FormatGithubcoremltools
Guides
Core ML FormatGithub
HomeGuides

Overview

  • Introduction
  • Installation
  • Quickstart Example
  • Migrating to This Version
  • Contributing
    • GitHub
    • Contribution Guidelines
  • Release Notes

Neural Networks

  • Unified Conversion API
  • TensorFlow 1 Conversion
    • Convert a TensorFlow 1 Image Classifier
    • Convert a TensorFlow 1 DeepSpeech Model
  • TensorFlow 2 Conversion
    • Convert TensorFlow 2 BERT Transformer Models
  • PyTorch Conversion
    • Model Tracing
    • Model Scripting
    • Convert a PyTorch Segmentation Model
  • Model Intermediate Language
  • Conversion Options
    • Image Inputs
    • Classifiers
    • Flexible Input Shapes
    • Composite Operators
    • Custom Operators
  • Quantization
  • Other Converters
    • Multi-backend Keras
    • ONNX
    • Caffe

Trees & Linear Models

  • LibSVM
  • Scikit-learn
  • XGBoost

MLModel

  • MLModel Overview
  • Model Prediction
  • Xcode Model Preview Types
  • MLModel Utilities

Updatable Models

  • Updatable Models Overview
  • Nearest Neighbor Classifier
  • Neural Network Classifier
  • Pipeline Classifier

Updatable Models Overview

Suggest Edits

Core ML allows you to personalize models using the MLUpdateTask API. Three types of models are updatable: neural networks, pipeline models, and nearest neighbors. For examples, see the following:

  • Updatable neural network classifier
  • Updatable pipeline model
  • Updatable nearest neighbors classifier

Updated over 5 years ago


What’s Next

  • Neural Network Classifier
  • Pipeline Classifier
  • Nearest Neighbor Classifier
Did this page help you?