Getting started with AI on NXP i.MX8M Plus - Neural Processing Unit - Use Case experiments: Smart Parking - Parallel Experiments

From RidgeRun Developer Wiki





Previous: Neural Processing Unit/Use Case experiments: Smart Parking/Serial experiments Index Next: Neural Processing Unit/Use Case experiments: Smart Parking/Results




Purpose of Parallel experiments

The main goal of these experiments is to measure the execution time performance and CPU usage knowing that the resources are being shared between each stage of the Smart Parking application. Delegates such as NNAPI and XNNPACK are going to be used as a comparison between them and the CPU performance.

This experiment consists of executing each Smart Parking stage in parallel, the License Plate Detection by TinyYOLO v3 and the License Plate Recognition by Rosetta model at the same time.

Initial conditions:

  • The stages are executed at the same time.
  • 100 warmup inference iterations.
  • 1 valid inference iteration.
Previous: Neural Processing Unit/Use Case experiments: Smart Parking/Serial experiments Index Next: Neural Processing Unit/Use Case experiments: Smart Parking/Results