Skip to main content
Ctrl+K

Guide to Core ML Tools

API Reference

  • coremltools API Reference
  • Core ML Model Format

Overview

  • What Is Core ML Tools?
  • Installing Core ML Tools
  • Getting Started
  • New Features
  • Core ML Tools FAQs
  • Examples
  • Contributing

Unified Conversion

  • Core ML Tools API Overview
  • Converting Deep Learning Models
    • Source and Conversion Formats
    • Load and Convert Model Workflow
    • Convert Models to ML Programs
    • Convert Models to Neural Networks
    • Comparing ML Programs and Neural Networks
    • Typed Execution
    • Typed Execution Workflow Example
  • Converting from TensorFlow
    • TensorFlow 1 Workflow
    • Converting a TensorFlow 1 Image Classifier
    • Converting a TensorFlow 1 DeepSpeech Model
    • TensorFlow 2 Workflow
    • Converting TensorFlow 2 BERT Transformer Models
  • Converting from PyTorch
    • PyTorch Conversion Workflow
    • Model Tracing
    • Model Scripting
    • Converting a Natural Language Processing Model
    • Converting a torchvision Model from PyTorch
    • Converting a PyTorch Segmentation Model
  • Conversion Options
    • New Conversion Options
    • Model Input and Output Types
    • Image Input and Output
    • Classifiers
    • Flexible Input Shapes
    • Composite Operators
    • Custom Operators
    • Graph Passes
  • Model Intermediate Language

Optimization

  • Optimizing Models
    • Overview
    • Optimization Workflow
    • Accuracy and Performance
  • Optimize API Overview
    • optimize.coreml API Overview
    • optimize.torch API Overview
    • Converting Compressed Source Models
  • Pruning
    • Pruning Overview
    • Post-Training Pruning
    • Training-Time Pruning
    • Pruning During Training Tutorial
  • Palettization
    • Palettization Overview
    • Post-Training Palettization
    • Training-Time Palettization
    • Palettization During Training Tutorial
  • Linear 8-Bit Quantization
    • Quantization Overview
    • Post-Training Quantization
    • Training-Time Quantization
    • Linear Quantization During Training Tutorial
  • Compressing Neural Network Weights

Other Converters

  • LibSVM
  • Scikit-learn
  • XGBoost

MLModel

  • MLModel Overview
  • Xcode Model Preview Types
  • MLModel Utilities
  • Model Prediction
  • Updatable Models
    • Neural Network Classifier
    • Pipeline Classifier
    • Nearest Neighbor Classifier
  • .rst

Pruning

Pruning#

This section describes optimizations using training-time and post-training pruning, and considerations on model size and performance:

  • Pruning Overview
  • Post-Training Pruning
  • Training-Time Pruning
  • Pruning During Training Tutorial

previous

Converting Compressed Source Models

next

Pruning Overview

By Apple

© Copyright 2023, Apple Inc.