IEI Technology Mustang-V100-MX8, User Manual

Page: 34 / 64

Mustang-V100-MX8
Page 26
Note:
The paths in this section assume you used the default installation directory to install the
Intel Distribution of OpenVINO toolkit. If you installed the software to a directory other than
/opt/intel/, update the directory path with the location where you installed the toolkit to.
If you installed the product as a root user, you must switch to the root mode before you
continue: sudo –i
4.5.1 Run the Image Classification Demo
1. Go to the Inference Engine demo directory:
cd /opt/intel/computer_vision_sdk/deployment_tools/demo
2. Set environment variables and run the Image Classification demo:
1) Set your environment variables:
source /opt/intel/computer_vision_sdk/bin/setupvars.sh
2) Modify .sh content:
sudo gedit demo_squeezenet_download_convert_run.sh
Search MYRIAD and modify to HDDL then save
3) Assign Mustang-V100-MX8 (-d HDDL) and run demo
/demo_squeezenet_download_convert_run.sh -d HDDL
3. The Image Classification demo uses the Model Optimizer to convert a SqueezeNet
model to .bin and .xml Intermediate Representation (IR) files. The Inference Engine
component uses these files.
For a brief description of the Intermediate Representation .bin and .xml files, see
Configuring the Model Optimizer.
This demo creates the directory /home/<user>/inference_engine_samples/.
This demo uses car.png in the demo directory. When the demo completes, you will
see the label and confidence for the top-10 categories: