How to deploy a new model created from the EIQ toolkit to a target device.

[_asif_muhammed_]

Hi Everyone,

I am kind of new to EIQ toolkit and just started to learn about machine learning. I have created a small dataset, labelled them and is playing around.

I am trying to deploy a model to imx8mplus based development board supplied by technexion.

I have connected the board to my linux pc using ethernet and i am able to ping and all from it. Connection does not have an issue.

While trying to add the target device I have given a name and URI as "http://192.168.10.1:10182". after that I tried to scan the devices so as to get more information about the device. 

Is there any particular application that we should run on the target device for this functionality to be working?

Any help or pointers would be highly helpful. Thank you in advance.

IMX8MPLUS  

@joanxie It would be great if you could please look into this. Thanks in advance.

[joanxie]

you also can refer to the enclosed file

[_asif_muhammed_]

Hi Joanxie,
Thank you for taking the time to assist me.
I have already reviewed the FAQs and userguides, however, I was unable to find any relevant information on how to set up my IMX8MP reference board as a remote device.

[joanxie · Accepted solution]

I don't use this remote device in the toolkit before, but refer to the user guide, he i.MX 8MPlus EVK must be connected to the network and it must be running an SSH server. I'm  not sure this is useful for your case or not, you can try it

[_asif_muhammed_]

As per my understanding, I have not been running the SSH server on the board. I will definitely check that out. Thank you for the insight.

[joanxie]

you can refer to the FAQ as below:

"https://community.nxp.com/t5/eIQ-Machine-Learning-Software/eIQ-FAQ/ta-p/1099741"

refer to the topic "I’m new to AI/ML and don’t know how to create a model, what can I do?"

and

How do I use my GPU when training with eIQ Toolkit?

eIQ Toolkit 1.0.5 is using TensorFlow version is 2.3.2, so to use the GPU when training you will need to install cuDNN v7.6 and CUDA 10.2. If you have newer versions of those tools installed on your PC you may need to uninstall them first.