Integrating Artificial Intelligence software stack on NXP i.MX8M Plus board

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

This section will cover some solved issues with the generation of TensorFlow Lite as a shared library, that is required by GstInference and R2Inference to compile. In order to clarify the dependency order, the sequence is like the following: R2Inference requires TensorFlow Lite (in this specific case, R2Inference supports more AI backends), and GstInference depends on the R2Inference library.

• Compiling TensorFlow Lite as a shared library for i.MX8M Plus.

• Compiling R2Inference for i.MX8M Plus.

• Compiling GstInference for i.MX8M Plus.