Installing TensorFlow Lite for NXP based images

🚧 Documentation under development

The Getting started with AI on NXP i.MX8M Plus guide is currently under active development. Some sections may be incomplete or change without notice.

Questions? Contact RidgeRun or email to support@ridgerun.com.

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

Installing TensorFlow Lite for i.MX8M Plus

For Gatesgarth there are some issues related to the construction of this library, in this version TensorFlow Lite is built as a static library, but other plugins in this workflow will need TensorFlow as a shared library. NXP has solved some of these issues in the Hardknott Yocto version, so let's use it.

Please go to the local.conf at:

cd $HOME/<your image folder>/<your build directory>/conf/
cat local.conf

There you can add the following lines:

# -- TensorFlow Lite stuff --
IMAGE_INSTALL_append += " tensorflow-lite"

Enable the NNAPI and XNNPACK delegate in the recipe

The TensorFlow Lite recipe is located at:

cd <your image folder>/sources/meta-imx/meta-ml/recipes-libraries/tensorflow-lite

Ensure the recipe has the 31st line like the shown below:

EXTRA_OECMAKE += "-DTFLITE_ENABLE_XNNPACK=on -DTFLITE_ENABLE_RUY=on -DTFLITE_ENABLE_NNAPI=on ${EXTRA_OECMAKE_MX8} -DTFLITE_BUILD_EVALTOOLS=on -DTFLITE_BUILD_SHARED_LIB=on ${S}/tensorflow/lite/"

Building the image with the changes in local.conf

cd $HOME/<your image folder>

source setup-environment <your build directory>

bitbake imx-image-core

Testing the TensorFlow Lite installation

For this section, please go through the Cross-compiling apps for GStreamer, TensorFlow Lite, and OpenCV