Dear all;
I have purchased the TurboX AI Kit (https://developer.qualcomm.com/hardware/thundercomm-turbox-ai-kit) because it was listed in AWS as a recommended device (https://devices.amazonaws.com/detail/a3G0h0000076szbEAA/Thundercomm-Turb...).
Among the characteristics I was looking for, AWS lists the possibility to use C/C++, Java, Python as programming languages and Ubuntu as the OS.
However, my TurboX AI Kit came preinstalled with Android 8 and I cannot find the instructions to install Ubuntu and use the Neural Processing SDK.
In particular, I am looking for information and examples about how to:
- Install Ubuntu in the TurboX AI kit (SDA845) and run the next items using Ubuntu OS
- Install and run Python (and/or miniconda) for Ubuntu in the AI kit
- Run neural networks converted to tensorflow lite in the GPU (Python preferably or C++)
- Perform video encoding using the DSP (Python preferably or C++)
- Run existing Qualcomm models properly leveraging the hardware
Any help about any of these items is appreciated - so far, I am unable to find useful resources at all. Our stack is fully developed for Ubuntu and it would be a gigantic work to port to Android, not to mention I'm interested in developing a dedicated device that requires more flexibility than Android usually allows.
Thanks in advance
In thundercomm device spec https://www.thundercomm.com/app_en/product/1536844968290219, the os is Android 8.
Please check with thundercomm whether they have another working software for Ubuntu.