Deploying a deep learning neural network on the Cyclone 10GX

[Johnny_K]

I kindly request an explanation of the exact procedure involved in taking a neural network in a .py file format and changing it to a format that is deployable on the Intel Cyclone 10GX FPGA development kit. This is to be done using the OpenVINO and FPGA AI Suite workflows. I have already gone through the user guides of both, however, I have not found any guides for the Cyclone 10GX specifically. I would highly appreciate an outline of the steps from model optimization to edge inference. 

[JohnT_Intel]

Hi,

Do you have AI Suite example design on Cyclone 10 GX? If not you will need to request for AI Suite license in order to create design for Cyclone 10 GX before we can proceed with OpenVINO.

[Johnny_K]

Hello Mr. John,

I have the free version of AI Suite with a limited number of inferences and do not have any example design for the Cyclone 10 GX. Could you kindly assist me with the next course of action. 

Thank you in advance.

[JohnT_Intel]

Hi,

Unfortunately, we do not have any example design that you can use to run on Cyclone 10 GX device. Please contact your local sales to see if they are able to help you on this.

[Johnny_K]

Would example designs for older Cyclone models work on the new Cyclone 10GX board, if so which example designs and where could I find them? 

[JohnT_Intel]

Hi,

Which older version of bitstream are you refering to? I do not observed any example design provided on Cyclone 10 GX device.

[JohnT_Intel]

Hi,

Any update?

[JohnT_Intel]

We do not receive any response from you to the previous question/reply/answer that I have provided. This thread will be transitioned to community support. If you have a new question, feel free to open a new thread to get the support from Intel experts. Otherwise, the community users will continue to help you on this thread. Thank you.