Optimized Inference at the Edge with Intel® Tools and Technologies
This workshop will walk you through a computer vision workflow using the latest Intel® technologies and comprehensive toolkits including support for deep learning algorithms that help accelerate smart video applications. You will learn how to optimize and improve performance with and without external accelerators and utilize tools to help you identify the best hardware configuration for your needs. This workshop will also outline the various frameworks and topologies supported by Intel® accelerator tools.
How to Get Started
⚠️For the in-class training, the hardware and software setup part has already been done on the workshop hardware. In-class training participants should directly move to Workshop Agenda section.
In order to use this workshop content, you will need to setup your hardware and install OpenVINO™ toolkit for infering your computer vision application.
1. Hardware requirements
The hardware requirements are mentioned in the System Requirement section of the install guide
2. Operating System
These labs have been validated on Ubuntu 16.04 OS.
3. Software installation steps
a). Install OpenVINO™ toolkit
Use steps described in the install guide to install OpenVINO™ toolkit, build sample demos, build inference engine samples, install MediaSDK and OpenCL* mentioned in the the guide.
b). Install git, gflags and python libraries
sudo apt install git sudo apt install libgflags-dev sudo apt install python3-pip pip3 install -r /opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/requirements_caffe.txt
c). Compile samples
Compile in-built samples in OpenVINO™ toolkit
sudo su source /opt/intel/computer_vision_sdk/bin/setupvars.sh cd /opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/ mkdir build && cd build cmake –DCMAKE_BUILD_TYPE=Release .. make exit
d). Download models using model downloader scripts in OpenVINO™ toolkit installed folder
- Install python3 (version 3.5.2 or newer)
- Install yaml and requests modules with command:
sudo -E pip3 install pyyaml requests
- Run model downloader script to download example deep learning models
cd /opt/intel/computer_vision_sdk/deployment_tools/model_downloader sudo python3 downloader.py
e). Install Intel® System Studio, VNC viewer and Setup on development machine
Follow the guide to install Intel® System Studio and VNC viewer on your development machine.
⚠️This workshop content has been validated with OpenVINO™ toolkit version R3 (computer_vision_sdk_2018.3.343).
Intel Smart Video/Computer Vision Tools Overview
Training a Deep Learning Model
Basic End to End Object Detection Inference Example
- Lab - Hardware Heterogeneity
HW Acceleration with Intel® Movidius™ Neural Compute Stick
FPGA Inference Accelerator
- Slides - HW Acceleration with Intel® FPGA
Optimization Tools and Techniques
Advanced Video Analytics
UP2 AI Vision Development kit as Edge
Intel and the Intel logo are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries.
*Other names and brands may be claimed as the property of others