Mustang-V100-MX8
Page 27
This demo is complete. Continue to the next section to run the Inference Pipeline demo.
4.5.2 Run the Inference Pipeline Demo
1. While still in /opt/intel/computer_vision_sdk/deployment_tools/demo/,
run the
Inference Pipeline demo
.
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_security_barrier_camera.sh –d HDDL
4. This demo uses car.png in /opt/intel/computer_vision_sdk/deployment_tools/demo/ to
show an inference pipeline. This demo uses three pre-trained models. The demo
uses vehicle recognition in which vehicle attributes build on each other to narrow in on
a specific attribute. The demo works as follows:
1) An object is identified as a vehicle.
2) This identification is used as input to the next model, which identifies specific
vehicle attributes, including the license plate.
3) The attributes identified as the license plate are used as input to the third model,
which recognizes specific characters in the license plate.
For more information about the demo, see the Security Camera Sample.
Summary of Contents for Mustang-V100-MX8
Page 2: ...Mustang V100 MX8 Page II Revision Date Version Changes January 17 2019 1 00 Initial release ...
Page 8: ......
Page 9: ...Mustang V100 MX8 Page 1 Chapter 1 1 Introduction ...
Page 14: ...Mustang V100 MX8 Page 6 Chapter 2 2 Unpacking ...
Page 17: ...Mustang V100 MX8 Page 9 Chapter 3 3 Hardware Installation ...
Page 24: ...Mustang V100 MX8 Page 16 Chapter 4 4 OpenVINO Toolkit Installation Linux ...
Page 37: ...Mustang V100 MX8 Page 29 Chapter 5 5 OpenVINO Toolkit Installation Windows 10 ...
Page 58: ...Mustang V100 MX8 Page 50 Appendix A A Regulatory Compliance ...
Page 60: ...Mustang V100 MX8 Page 52 B Product Disposal Appendix B ...
Page 62: ...Mustang V100 MX8 Page 54 Appendix C C Hazardous Materials Disclosure ...