v2.1

Table of Contents

  • Overview
  • Installation
  • QuickStart
  • Auto (Hyper-parameter) Tuning
  • Neural Architecture Search
  • Model Compression
    • Overview
    • Quick Start
    • Pruning
    • Quantization
    • Utilities
    • Advanced Usage
      • Framework
      • Customize a new algorithm
      • Automatic Model Compression
    • API Reference
  • Feature Engineering
  • References
  • Use Cases and Solutions
  • Research and Publications
  • FAQ
  • How to Contribute
  • Change Log
NNI
  • Docs »
  • Model Compression »
  • Advanced Usage
  • Edit on GitHub

Advanced UsageΒΆ

  • Framework
    • Compressor
    • Pruner
    • Quantizer
    • Multi-GPU support
  • Customize a new algorithm
    • Customize a new pruning algorithm
    • Customize a new quantization algorithm
  • Automatic Model Compression
    • First, model compression with NNI
    • Then, make this automatic
Next Previous

© Copyright 2021, Microsoft Revision ef9a7993.

Built with Sphinx using a theme provided by Read the Docs.