Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Discussion related to "under the hood" OpenMV topics.
jcp13
Posts: 9
Joined: Fri May 10, 2019 12:15 pm

Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby jcp13 » Fri May 10, 2019 5:44 pm

Greetings,

I am intrigued by the OpenMV Cam H7. I would like to build my own mode, train it, and deploy it to the OpenMV Cam H7, what would be the recommended process for doing so?

Thank you in advance,

JCP13
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Sat May 11, 2019 3:43 pm

Hi, we are about to release tensor flow lite support for the system. Once this is done you can use tensor flow for all of this.

I just have to write some examples on how to train and port a model and then I can do the release.
Nyamekye,
jcp13
Posts: 9
Joined: Fri May 10, 2019 12:15 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby jcp13 » Mon May 13, 2019 6:14 pm

Great! thank you :P

By the way, do you have a rough ETA?

Cheers.
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Mon May 13, 2019 8:16 pm

Not really. I can give you a link to my branch the code is on. I don't have a small model to test with yet so it's not working as far as I know. I was trying to get the initial work with mobilenet operational but the memory manager used by google is very inefficient and they are re-writing it now to allow mobilenet to run on the H7.

Also, going on a retreat this Friday-Sunday. So, I can get back on this next week. I can give you the branch the code is on in the mean-time. I believe I'm done with it.
Nyamekye,
jcp13
Posts: 9
Joined: Fri May 10, 2019 12:15 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby jcp13 » Tue May 14, 2019 12:21 am

Again, thank you for the prompt reply. Can you provide the code branch?

Thank you.
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Tue May 14, 2019 12:36 am

It's here: https://github.com/kwagyeman/openmv/tree/kwabena/add_tf

There's a new tf module. It runs TensorFlow lite models that use depth wise convolutions and fully connected layers. Relu and pooling are part of the depthwise layers.

I have to write an example first for how to train a model, convert it, and then examples before I can release this.
Nyamekye,
jcp13
Posts: 9
Joined: Fri May 10, 2019 12:15 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby jcp13 » Tue May 14, 2019 1:04 am

Sweet! I can't wait to try out your example 8-)
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Wed May 15, 2019 12:42 am

Hi, i mentioned this on another post. But, if you could train and quanitize a tflite network this would accelerate me on this. I have a heavy email load right now which is preventing dev work.
Nyamekye,
ahpd
Posts: 1
Joined: Fri Jul 26, 2019 10:09 am

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby ahpd » Fri Jul 26, 2019 10:14 am

Hi,
Has Tensorflow lite support been completed?
If yes, how to find it? If no, when it will be released?
Thanks.
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Fri Jul 26, 2019 2:38 pm

The port has been completed. It will be released in the next firmware release. I was busy having a social life for a while but I'm putting more time into OpenMV development now again.
Nyamekye,
jcp13
Posts: 9
Joined: Fri May 10, 2019 12:15 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby jcp13 » Mon Sep 09, 2019 3:06 pm

Hi,

I hope all is well, do you have any updates on this request?

Thank you.
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Tue Sep 10, 2019 12:19 am

Me and Ibrahim are finally working on the firmware after a long while. I have to finish up DRAM support and then this will be added to the firmware.
Nyamekye,
jcp13
Posts: 9
Joined: Fri May 10, 2019 12:15 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby jcp13 » Thu Sep 12, 2019 8:00 pm

Thank you for the reply.
Question, I would like to use the Flir lepton camera for object detection, can I leverage a pre trained model or do I have to build one from scratch or can I do transfer learning with a pre trained model?

Thanks.
User avatar
kwagyeman
Posts: 3271
Joined: Sun May 24, 2015 2:10 pm

Re: Process for building custom a model, training it, and deploying it to the OpenMV Cam H7

Postby kwagyeman » Thu Sep 12, 2019 10:29 pm

You basically have to do everything from scratch right now. We will be offering TensorFlow support very soon but the tooling will be up to you still.
Nyamekye,

Return to “Technical Discussion”

Who is online

Users browsing this forum: No registered users and 3 guests