(jetson nano) vs (Raspberry pi5 8g + hailo 26 TOP)

Discussion
, , ,
1

I’m reaching out to inquire about the best hardware solution for my object detection project. I’m aiming for a minimum of 10 FPS, high accuracy, and stable results.
models I think they can meet my requirments: Yolov5su, Yolov5m6u.

I’ve read that the Jetson Nano offers good performance and power efficiency, while the Raspberry Pi with Hailo accelerator seems to have a more complex setup and less community support.

I’m a bit confused about which option would be the most suitable for my needs. I would appreciate your expert advice on this matter.

Thank you for your time and assistance.

Best regards,

2

Hailo isn’t officially supported by Ultralytics. Some people did get it working in the community, but it wasn’t straightforward. For Jetson, Ultralytics has several guides and also TensorRT support with int8 quantization which can help quite a bit with the FPS.

3

maybe you are right, but its possible to export the trained model as onnx, then convert it to .hef model that can work on hailo. as this video explaining step by step. Am I correct?

4

I’m not really sure how it’s done.

5

An NVIDIA Jetson would be something that would be more than capable of getting 10 FPS, although keep in mind that the Jetson Nano is a very old device and is not getting updated. If you go that route, you should considered something more recent for continued support and updates, as you will be reliant on the JetPack versions from NVIDIA (only critical if you want to update, if you don’t feel you’ll want updates then it won’t matter).

The RPi might be able to run a small model with 10-15 FPS without an accelerator. If I recall correctly, NCNN models performed best when tested by our embedded engineer. So maybe try that first? Depending on your needs, there are other options for embedded devices that could suffice. If you’re aiming to get it done in a budget and space isn’t an issue, maybe find a used PC with a decent CPU and get a used NVIDIA GPU (probably 2060 or higher).

6

Hi,

Thank you for your reply.

Actually, the space constraints are critical. I can’t use a PC larger than the Jetson Nano, and the Jetson Nano is almost big.

As I understand it, you recommend using the Raspberry Pi 5 with an accelerator first.

Can you suggest a model that can run on a Raspberry Pi 5 8GB with a Hailo-8 26 TOPS accelerator?

As I mentioned, 10-15 FPS is sufficient for my needs, but I require high accuracy and stability.

Thanks,

7

Actually, I think you should test without an accelerator to start. I would suggest YOLO11n exported to NCNN format per Raspberry Pi - Ultralytics YOLO Docs

1 Like
8

Additionally use half=True and the smallest imgsz possible (that would work for your application) and see how this performs. If you’re able to get what you need without an accelerator, it would be the simplest way to deploy. If you require an accelerator, you’ll have to check with the Hailo docs/repo on how to get it working, but AFAIK they have some conversion you can run for a model so that it is compatible with their platform.

1 Like