Porting TensorFlow 1 models to the IPU

This document is a practical guide to porting TensorFlow 1 models to the Poplar SDK for running on the IPU.

Contents

• 1. Introduction
• 2. How to transfer an existing code base
  • 2.1. Preliminary analysis
  • 2.2. Planning the transfer
  • 2.3. Next steps
• 3. ResNeXt inference example
  • 3.1. Abridged sample code
  • 3.2. Preliminaries: getting up and running
  • 3.3. Configuring the IPU
  • 3.4. Generating a report
  • 3.5. Infeeds and outfeeds
• 4. Training with the estimator API
  • 4.1. Instantiate an estimator for the IPU
  • 4.2. Abridged code sample for the estimator
  • 4.3. Train and evaluate methods
• 5. Scoping and determining unsupported operations
• 6. Checking hardware availability
• 7. ResNeXt full code example
• 8. Trademarks & copyright