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

Getting started with AI on NXP i.MX8M Plus
Introduction
Overview i.MX8M Plus hardware specifications Development tools Development kit DART-MX8M-PLUS Development kit Quick getting started Yocto minimal image Flashing SD card First steps on the board
Development
Gatesgarth and Hardknott Yocto versions Downloading Yocto images for NXP based BSP Building an imx-core-image Flashing SD card Integrating multimedia software stack Installing GStreamer Installing OpenCV Integrating Artificial Intelligence software stack Installing TensorFlow Lite for NXP based images Installing R2Inference Installing GstInference Developing software for the board Building the SDK Crosscompiling apps for GStreamer, TensorFlow Lite, and OpenCV Exploring TensorFlow Lite delegates for prototyping
Neural Processing Unit
Introduction Profiling the NPU Installing gputop Setting the board on debug mode Use Case experiments: Smart Parking Introduction to the use case License Plate Detection TinyYOLO version 3 Training a model compatible with GstInference License Plate Recognition Rosetta Getting the model prototyping Bash scripts for CPU usage and time estimation Serial experiments Parallel Experiments Results
GStreamer
Exploring Rosetta element for character recognition Example pipelines Smart Parking Video inferences Image inferences Video streaming
Contact Us

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.