search

tensorflow / tflite-micro

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).
Apache License 2.0
1.85k stars 805 forks source link

How to add OpenCV to build successfully person detection project? #2559

Closed huytranvan2010 closed 5 months ago

huytranvan2010 commented 5 months ago

I follow this project and can run test https://github.com/tensorflow/tflite-micro/tree/main/tensorflow/lite/micro/examples/person_detection#run-the-tests-on-a-development-machine. But now I want to evaluate Tflite C array model in TFLM. So that I need OpenCV to read all images, resize images and run inference. I installed OpenCV in my PC. How can I add OpenCV to build successfully person detection project? I mean that how can I add OpenCv to makefile to build this project. Generally, for OpenCV project, I can use this guide https://docs.opencv.org/4.x/db/df5/tutorial_linux_gcc_cmake.html to build project with OpenCV via cmake. But with TFLM, I dont know to do it.

Thank you.

ddavis-2015 commented 5 months ago

@huytranvan2010

The following repository has an example of using TFLM with CMake builds for the Raspberry Pi Pico microcontroller:

https://github.com/raspberrypi/pico-tflmicro

That repo. is not part of Google or TFLM and no Google support can be provided with regards to the use of that repo.

This issue will now be closed. Please feel free to reopen the issue should you have additional comments.