Inference Engine overview- Hardware agnostic inference with write once deploy anywhere approach

1 Understanding various Intel® AI platforms - CPU, iGPU and VPU to achieve accelerated performance

2 CPU vs. GPU: Making the Most of Both

3 Using the integrated GPUs

4 Introducing Intel® Movidius™ Myriad™ X VPU

5 Accelerators based on Intel® Movidius™ Myriad™ X Vision Processing Unit

6 Inference Engine overview- Hardware agnostic inference with write once deploy anywhere approach

7 Demo - Inference Engine

8 Demo - Running Inference on Intel® Neural Compute Stick 2

9 Demo - Object Detection sample application walkthrough

10 Lab - OpenCV* Tutorial

11 Quiz Question

12 Lab - Classification

13 Lab - Object Detection

14 Lab - Style Transfer

15 Performance improvement with Inference Engine - Sync Mode vs Async Mode, and Throughput Mode

16 Efficient utilization of all the available compute resources using Heterogeneous and Multi- Device Plugin and boost the performance

17 Lab - Benchmark and compare performance

18 Lab - Industrial use-case : Safety Gear Detection

19 Lab - Healthcare use-case : Pneumonia Detection

20 Lab - Retail use-case: Store Aisle Monitor

21 Quiz Question

22 Quiz Question

23 Quiz Question

24 Quiz Question

25 Quiz Question

26 Quiz Question