Hi,
Im trying to run the ROS-TFLite sample app and im running into a problem when installing TensorFlow.
I tried with pip and pip3. Any suggestions?
Zilmara
Hi,
Im trying to run the ROS-TFLite sample app and im running into a problem when installing TensorFlow.
I tried with pip and pip3. Any suggestions?
Zilmara
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Can you scrren shot your test windows? I will check your test output.
how can I paste pictures into my question. I did previously paste pictures but they didnt show up.
Hi Zilmara
You can screen shot your screen and save to somether in cloud, I can downloa it.
You may use this free cloud storage to share files.
https://app.degoo.com/moments
Following from the reply above, how could one ensure that the tflite model runs on the DSP or AIP?
I have tried:
The idea was to use the delegate presented in:
https://www.tensorflow.org/lite/performance/hexagon_delegate#add_the_sha...
but I keep getting the following error:
OSError: libhexagon_nn_skel_v66.so: wrong ELF class: ELFCLASS32
Which suggests that libhexagon_nn_skel_v66.so is not built for the rb5 aarch64 architecture.So to reiterate, I would like to know how to use TFlite runtime Python package to run the TFlite model on the DSP on the RB5.
Thanks in advance.