Skip to content

awshlabs/reinvent19Inf1Lab

Repository files navigation

Reinvent Inf1 Lab: Hands-on Deep Learning Inference with Amazon EC2 Inf1 Instance

Note: We simplified this lab into a new repository. https://github.com/awshlabs/Jul2020-Inf1Lab

Abstract:

In this workshop, you gain hands-on experience with Amazon EC2 Inf1 instances, powered by custom AWS Inferentia chips. Amazon EC2 Inf1 instances offer low-latency, high-throughput, and cost-effective machine learning inference in the cloud. This workshop walks you through taking a trained deep learning model to deployment on Amazon EC2 Inf1 instances by using AWS Neuron, an SDK for optimizing inference using AWS Inferentia processors.

Overview:

Please follow the labs in sequence.

Lab 1. Launch a C5 Instance, install the Neuron development environment, Custom compile a pre-trained model to target the Inferentia Neuron Processor.
Lab 2. Launch an Inf1 Instance, install Neuron run-time and development environment, test and model serve the compiled ResNet package.
Lab 3. Compile on C5 and launch a load test run on Inf1 Instance.
Lab 4. Debug and profile your model on Inf1 Instance.

Slides:

Reinvent workshop slides at at: slides Directory

About

Re:Invent Inf1 Instance Lab

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •