Finally, "real" GPUs on the Raspberry Pi 5

And here I was thinking it was about providing CUDA cores to be used by userspace programs for inference tasks...

Eh, rather a Jetson Nano or relative - a lot neater and still quite compact. But perhaps not as much firepower ... or as much plug-melty action.

- Gough

Gough Lui said:

Eh, rather a Jetson Nano or relative

Are many people using a Jetson Nano? I don't see many people posting about them on the Community.

More than you'd imagine, I'd say.

We have a good slice of our PhD candidates using them as targets for AI in embedded contexts for computer vision especially. They really fly compared to RPis for that particular use case. Hook them up to some RPi cameras (compatible CSI interface) for some fun :).

Some have even invested into the Jetson AGX or clusters of them. There are some autonomous vehicle researchers using them too - likely as things would be easier to port to Nvidia's DRIVE platform.

EDIT: Perhaps why we don't hear much here is that most of the people I've seen working with them are mostly focusing on the software, rather than the electronics side. Everything to them is code ... and this isn't the "forum" they would naturally gravitate towards. That's not to say the board isn't great for plenty of electronically-related shenanigans too.

- Gough

Right now there is a lot of movement around the  the NVIDIA Jetson on hackster.io, 

AI Innovation Challenge - Hackster.io

Several regular members of element14 participating in it.

I'm using it . Still learning how to use that (with the NVIDIA specific functions - the Jetson is basically a computer that runs Linux) stuff, but it's better and faster than a Raspberry PI.

I have the Jetson Nano developer KIT and it's not the most up to date stuff. Python is 3.6 and because of that I'm limited on the TensorFlow, Pytorch versions that I can install.

Because I still have to receive my PI5 (4GB) can't compare them yet, but as soon as I get my RPI5, I will definitely compare them.

Regarding the original post, my question goes - Why ? Why run an external GPU ? If I have the need to run something that requires a GPU, I will not use a Raspberry PI.  A Jetson Orin or something else that is specific for that task.

I'm using it . Still learning how to use that (with the NVIDIA specific functions - the Jetson is basically a computer that runs Linux) stuff, but it's better and faster than a Raspberry PI.

I have the Jetson Nano developer KIT and it's not the most up to date stuff. Python is 3.6 and because of that I'm limited on the TensorFlow, Pytorch versions that I can install.

Because I still have to receive my PI5 (4GB) can't compare them yet, but as soon as I get my RPI5, I will definitely compare them.

Regarding the original post, my question goes - Why ? Why run an external GPU ? If I have the need to run something that requires a GPU, I will not use a Raspberry PI.  A Jetson Orin or something else that is specific for that task.

feiticeir0 said:

Why ? Why run an external GPU ?

I think if you're going at something "from scratch" it can be a valid question to ask "Why?", if you're going "but I already have these components lying around" or "I'm technically curious" then it can make sense. It also furthers support for hardware in the arm linux infrastructure that may not have been there before and that could open up possibilities.

feiticeir0 said:

I have the Jetson Nano developer KIT and it's not the most up to date stuff. Python is 3.6 and because of that I'm limited on the TensorFlow, Pytorch versions that I can install.

That's cool, I'd be interested in reading more about how people put it to use, I often see the end result or reference manuals, but not many blog examples of people actually using it on the element14 Community.

As soon as I'm done with it, I can post it here.It's nothing fancy really - just read my license plate and open my garage door - this will be used - at least for a proof of concept - on my work place .

First I'm just learning how to use the NVIDIA specific functions for deep learning and ML.

NVIDIA has quite a number of tutorials for one to learn. They even offer free certification after you submit a project and be graded by them. 

cstanton said:

That's cool, I'd be interested in reading more about how people put it to use, I often see the end result or reference manuals, but not many blog examples of people actually using it.

hackster.io has many projects.

Since it's a Linux ( It runs Ubuntu 18.04 LTS) you can install TensorFlow and Pytorch and run pretty much anything that don't requires newer versions.

Newer Jetsons (and more expensive  ) run more up to date versions. 

cstanton said:

I think if you're going at something "from scratch" it can be a valid question to ask "Why?", if you're going "but I already have these components lying around" or "I'm technically curious" then it can make sense. It also furthers support for hardware in the arm linux infrastructure that may not have been there before and that could open up possibilities.

That's an really good example (and I missed it on my original reply) of - "because I can" ! 

I remember one episode of the Big Bang Theory (really really excellent series) when they guys are turning the living room lights on and off (and the stereo) using Internet by bouncing the signal through several countries and Penny asks them why and they reply - "Because we can" .

Edit media

Dimensions x Small Medium Large Custom

Subject (required) Brief Description Tags (separated by comma) Video visibility in search results Visible Hidden

Parent content

RE: Finally, "real" GPUs on the Raspberry Pi 5

Poster

Upload Preview

Ok

Cancel

feiticeir0 said:

you can install TensorFlow and Pytorch and run pretty much anything that don't requires newer versions.

I've been meaning to get my head around these myself, do you know of any beginner resources?

I've sent you a message.