Model inference on ARM M4F

[gcmike]

Hi there.
Great work on the project! I have made successful progress with mac os. But I was wondering if the trained model, say minst-cnn.kan, could be transferred to ARM M4F chip for inference? There would definitely be data input and output processing. But apart from that, is it possible to use the trained model on ARM? Thanks in advance!

[attractivechaos]

I have no experience with ARM CPUs. Is M4F little endian or big endian? If it is big endian, model generated on x86 won't work, though the issue should be fixable. If it is little endian, data file should work with the CPU, in principle.

[gcmike]

I am currently aiming at nRF52832, which has a cortex M4F on board along with ble function. From what I found here (http://infocenter.nordicsemi.com/index.jsp?topic=%2Fcom.nordic.infocenter.nrf52832.ps.v1.1%2Fcpu.html), the last table showed that it implements little endian. Is this the correct info?

[shipleyxie]

@gcmike i am intersted in you WORK too , have you finished this work?