Must Caffe be installed for movidius SDK to work?

[idata]

Hi,

I would like to use the Movidius to run some Tensorflow object detection models. I have some issues installing the SDK. I cloned the repo but in the make install step, I run into the following error:

/usr/bin/ld: /usr/local/lib/libpython3.6m.a(object.o): relocation R_X86_64_32 against `.rodata.str1.1' can not be used when making a shared object; recompile with -fPIC

/usr/local/lib/libpython3.6m.a: error adding symbols: Bad valuecollect2: error: ld returned 1 exit statussrc/caffe/CMakeFiles/caffe.dir/build.make:3057: recipe for target 'lib/libcaffe.so.1.0.0-rc3' failedmake[3]: *** [lib/libcaffe.so.1.0.0-rc3] Error 1make[3]: Leaving directory '/opt/movidius/ssd-caffe/build'CMakeFiles/Makefile2:272: recipe for target 'src/caffe/CMakeFiles/caffe.dir/all' failedmake[2]: *** [src/caffe/CMakeFiles/caffe.dir/all] Error 2make[2]: Leaving directory '/opt/movidius/ssd-caffe/build'Makefile:127: recipe for target 'all' failedmake[1]: *** [all] Error 2make[1]: Leaving directory '/opt/movidius/ssd-caffe/build'Installation failed. Error on line 679Makefile:47: recipe for target 'install' failedmake: *** [install] Error 1

I see it's an error with the Caffe installation and since I don't plan on using Caffe, I went into ncsdk.conf and set INSTALL_CAFFE=no. This gets rid of the error and SDK installs.

However, then I tried to install the examples under the tensorflow folder with make run and run into this error:

Traceback (most recent call last): File "/usr/local/bin/mvNCProfile", line 36, in from Controllers.Scheduler import load_myriad_config, load_network File "/usr/local/bin/ncsdk/Controllers/Scheduler.py", line 24, in from Controllers.Optimizer import postParsingOptimizations, selectImplementations, streamEverythingSchedule, fixTensors, eliminateNoOps File "/usr/local/bin/ncsdk/Controllers/Optimizer.py", line 25, in from Controllers.Parsers.Parser.Conversion import Conversion File "/usr/local/bin/ncsdk/Controllers/Parsers/init.py", line 3, in from .Caffe import CaffeParser File "/usr/local/bin/ncsdk/Controllers/Parsers/Caffe.py", line 30, in import caffeModuleNotFoundError: No module named 'caffe'Makefile:30: recipe for target 'profile' failedmake[3]: *** [profile] Error 1make[3]: Leaving directory '/home/biqingqiu/ncsdk/examples/tensorflow/inception_v3'Makefile:12: recipe for target 'inception_v3/.' failedmake[2]: *** [inception_v3/.] Error 2make[2]: Leaving directory '/home/biqingqiu/ncsdk/examples/tensorflow'Makefile:12: recipe for target 'tensorflow/.' failedmake[1]: *** [tensorflow/.] Error 2make[1]: Leaving directory '/home/biqingqiu/ncsdk/examples'Makefile:57: recipe for target 'examples' failedmake: *** [examples] Error 2

Note I deleted all other examples except for the tensorflow folder. So it seems that even the tensorflow examples have dependencies on Caffe in order to run. My question is: is this true? Is there a way to use Movidius without installing Caffe? (since I have difficulty installing Caffe too). Why must tensorflow examples also depend on Caffe?

Any help is appreciated. Thanks!