So I made a program to acquire data from the ToF sensor VL53L0X from St. I was able to send the data go edge impulse with data forwarder and trained a model that will recognize gestures moving your hand from left to right and right to left.
I am ready to deploy…
I tried creating a project in cubeMX with an M4 NUCLEO-F401RE board. configured my UART, I2C and added the generated CMSIS-PACK and then i created a project using STM32CubeIDE
I added the code lines per
https://docs.edgeimpulse.com/docs/using-cubeai
Hit build but i get this errors
c:\st\stm32cubeide_1.7.0\stm32cubeide\plugins\com.st.stm32cube.ide.mcu.externaltools.gnu-tools-for-stm32.9-2020-q2-update.win32_2.0.0.202105311346\tools\arm-none-eabi\bin\ld.exe: ./Middlewares/Third_Party/EdgeImpulse_Gestures_MachineLearning/edgeimpulse/tflite-model/trained_model_compiled.o: in function `trained_model_init(void* (*)(unsigned int, unsigned int))': C:/Users/jorge/OneDrive/Documents/2.- Keil STM32 Projects/edgeimpulse/M4 new/deploytest on m4/Debug/../Middlewares/Third_Party/EdgeImpulse_Gestures_MachineLearning/edgeimpulse/tflite-model/trained_model_compiled.cpp:346: undefined reference to `tflite::Register_FULLY_CONNECTED()' c:\st\stm32cubeide_1.7.0\stm32cubeide\plugins\com.st.stm32cube.ide.mcu.externaltools.gnu-tools-for-stm32.9-2020-q2-update.win32_2.0.0.202105311346\tools\arm-none-eabi\bin\ld.exe: C:/Users/jorge/OneDrive/Documents/2.- Keil STM32 Projects/edgeimpulse/M4 new/deploytest on m4/Debug/../Middlewares/Third_Party/EdgeImpulse_Gestures_MachineLearning/edgeimpulse/tflite-model/trained_model_compiled.cpp:347: undefined reference to `tflite::Register_SOFTMAX()' collect2.exe: error: ld returned 1 exit status make: *** [makefile:121: deploytest on m4.elf] Error 1
Then my next question is that on this project we just copy the features of an existent classifier
what is the next step.?
To which function, do I need to feed my sensor data so that the model will give the output?