Adding Intelligence to the Edge devices with Cloud IoT

Cloud IoT Edge is the software that extends Google Cloud’s powerful data processing and machine learning capabilities to gateways, cameras, and end devices, making IoT applications smarter, more secure and more reliable. It lets you execute ML models trained in Google Cloud on the Edge TPU or on GPU- and CPU-based accelerators. In this session, we will discuss how to execute ML models in Edge devices and how machine learning at the edge benefits businesses.

Repo: https://github.com/ksivamuthu/cloud-edge-tpu-demo

Transcript

1. Adding Intelligence to the Edge Devices with Cloud IoT OHIO DEVFEST NOV 2, 2019
2. Agenda Cloud IoT Introduction Adding Intelligence to the Edge Devices Coral Dev board & USB Accelerator Demo
3. HELLO! I’m SivamuthuKumar Architect - Computer Enterprises Inc Orlando, FL #Cloud #Mobile #IoT ksivamuthu
4. IoT INTERNET OF THINGS
5. IoT is the concept of connecting any device to the Internet and to other connected devices
6. Sensors / Actuators Connectivity Applications Custom-made by certified hardware partners Stable and Robust IoT environment Use the collected data to optimize your processes
9. It is predicted that there will be 41.6 billion connected IoT devices, or "things," generating 79.4 zettabytes (ZB) of data in 2025 This Photo by Unknown Author is licensed under CC BY-NC-ND
10. Cloud IoT Core DATA INGESTION AND DEVICE MANAGEMENT
11. Cloud IoTCore Bi-directional communication with billions of IoT devices ◦ Device-to-cloud telemetry data, cloud-to-device command, track message delivery Work with familiar platform and protocols ◦ HTTP, MQTT protocols and clients Security Enhanced Solutions ◦ Individual identities and credentials for each of connected devices. Automate device provisioning to accelerate IoT deployment ◦ Register and provision devices with zero touches, in a highly secure and scalable way. Logging and Monitoring ◦ Audit logs and device logs
13. Cloud ML Fully managed service Preprocess and Orchestrate ML Workflow as Dataflow pipeline Analyze data and develop ML models in Datalab Training at scale using TensorFlow Batch and online predictions using REST at scale
14. ML Processing Units
16. Cloud IoT Edge
17. Why ML at Edge? LATENCY BANDWIDTH PRIVACY CONNECTIVITY EXECUTION COST
19. Features of Cloud IoT Edge ML Inference at the Edge Edge TPU support Local compute Run on Android Things and Linux-based OS Securely connect devices to the cloud Work seamlessly with Cloud for hassle free device provisioning
20. Edge TPU GOOGLE’S PURPOSE-BUILT ASIC DESIGNED TO RUN INFERENCE AT THE EDGE.
21. Edge TPU Development Kits Google Coral Dev Board USB Accelerator An individual Edge TPU is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt).
22. Demo RASPBERRY PI4 AND CORAL USB ACCELERATOR
23. Cloud IoT Edge –Three parts Hardware Coral Dev board / USB Accelerator Edge TPU Runtime TFLite Models ( Compatible with Edge TPU )
24. Hardware ØAny Linux computer x86-64 or ARM64 system architecture ØOne available USB Port ØGoogle’s Coral USB Accelerator
25. Edge TPU Runtime
26. Edge TPU Delegates Install the TensorFlow Lite runtime Library Run the python Interpreter API with experimental Edge delegates. TF Lite API or Edge TPU API:
27. Boat Classification
28. Object Detection
31. Key Takeaways High speed ML inference using Edge TPU on low power devices. Cloud AutoML to train and export into TFLite and TFLite Edge optimized models. Retrain / Transfer Learning using AutoML or on your own and compile into Edge TPU TFLite models Edge TPU with Coral SoM or USB Accelerator ( USB3.0 & Host computing)
32. Reference Demo: https://github.com/ksivamuthu/cloud-edge-tpu-demo Slides: https://speakerdeck.com/ksivamuthu/adding-intelligence- to-the-edge-devices-with-cloud-iot Cloud IoT Core: https://cloud.google.com/iot-core/ Coral Dev Kit & Accelerator: https://coral.withgoogle.com/products/accelerator/
33. Thank you ksivamuthu