Deep Learning With DeepLens

AI, Machine Learning and IoT projects are becoming ever more important for enterprises and startups alike. These advanced technologies have been the key innovation engine for businesses such as Amazon Go, Alexa, Amazon Robotics. In this one-day workshop, we will cover the scenarios of AI and IoT working together.

  • Building and training deep learning models in the cloud using Amazon SageMaker.
  • Deploying AI models to devices like the AWS DeepLens.

We will provide a hands-on learning experience by build an end-to-end systems for face detection, recognition and verification. The workshop is designed for developers that are curious about these new technologies with no ML background assumed.

Basic requirement: Hands-on experience with python, and basic understanding of AWS services such as S3 and Lambda.

Agenda

09:00 AM - 11:00 AM

Get to know your Device

  • Register you DeepLens device
  • Object detection with DeepLens
  • Hot Dog or Not Hog Dog - Edit a pre-trained model in SageMaker and deploy on DeepLens (Optional Homework)

11:00 AM - 01:00 PM

End-to-end solution for face detection, recognition and verification

  • Face detection with DeepLens
  • Rekognition
  • Approval Workflow (Optional Homework)
  • Bring it all together (Optional Homework)

01:00 PM - 02:00 PM

Sage Maker overview

  • Launch your notebook instance and open its Jupyter interface
  • Amazon Algorithms - Reliable ML in Scale
  • Training Models with a Training Job
  • Tuning Models with Hyper-parameter Optimization (HPO)
  • Hosting Inference Endpoint

02:00 PM - 03:00 PM

Build your own Image Classification and Deploy it to DeepLens Additional project ideas/Hackathon