prepkg / tensorflow-lite-raspberrypi Goto Github PK

Appreciate the linear regression example - very helpful in confirming the installation of the shared libraries.

How does one build one's own model.tflite file (other than work through the Colab exercises)? Links to other examples welcome, please, because I don't want to get lost in the weeds trying code that will not work on Raspberry Pi platforms. Thanks.

Regards.

I prefer to build from source myself.

Hello. I'm get an error:

root@orangepi3-lts:/home/orangepi# g++ main.cpp -o test -ltensorflow-lite -ldl
/usr/bin/ld: skipping incompatible //usr/local/lib/libtensorflow-lite.so when searching for -ltensorflow-lite
/usr/bin/ld: cannot find -ltensorflow-lite
collect2: error: ld returned 1 exit status

use Orange Pi3 + Debian

The installed was ok

Hi,

I try to use C++ API use this code
g++ test.cpp -o test -ltensorflow-lite -ldl -lm
and get these error message as below

/usr/bin/ld: //usr/local/lib/libtensorflow-lite.so: undefined reference to `log@GLIBC_2.29'
/usr/bin/ld: //usr/local/lib/libtensorflow-lite.so: undefined reference to `exp@GLIBC_2.29'
/usr/bin/ld: //usr/local/lib/libtensorflow-lite.so: undefined reference to `pow@GLIBC_2.29'
collect2: error: ld returned 1 exit status

do you have any suggestion?
thanks