Hello everyone,
I am trying to work with the TensorFlow C++ library ( tensorflow/tflite-micro: Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors). (github.com)) . I already managed to generate projects for my cortex_m4 with Makefile and could also run tests with make.
Now I wanted to move on to the next step and try the hello_world example on my microcontoller. I am using this documentation: Get started with microcontrollers | Google AI Edge | Google AI for Developers.
I get already in the first “includes”
#include "tensorflow/lite/micro/micro_mutable_op_resolver.h" #include "tensorflow/lite/micro/micro_error_reporter.h" #include "tensorflow/lite/micro/micro_interpreter.h" #include "tensorflow/lite/schema/schema_generated.h" #include "tensorflow/lite/version.h"
a lot of errors:
For my understanding those errors result from compiling Python code parts. Do I need those to just run the hello_world example?
Basically I am struggling with what files from this huge repository do I really need to run the hello world example (or an own trained model).
Can anyone help me out here with some explanation or a link to some more documentation?
Any help is welcome!
Best Regards