Can't speak for industry standards, but a little bit ago I worked on aerial object recognition and we used YOLO + NVIDA Jetson. Jetson seemed like the best GPU accelerated hardware that was light enough to mount to a smallish drone.
this post was submitted on 08 Nov 2023
1 points (100.0% liked)
Machine Learning
1 readers
1 users here now
Community Rules:
- Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
- Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
- Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
- Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.
founded 1 year ago
MODERATORS
Jetson family.
You should also check out the Coral TPU boards, they are more efficient for models.
For CV, Jetson family! The following source has a high level overview of challenges and solutions when deploying NVIDIA TAO on Jetson devices.
IMX500
In the company I work, we have a couple of Jetsons laying around for development
Speck from SynSense
No one has mentioned this yet, but ESP32-S and -H are convenient low power platforms.
Normally Jetson Xavier NX and I believe Mobilenet, but I'm not involved with our edge CV models
we recently switched from Jetson Xavier to Jetson Orin boxes.
And we have a suite of algos. Yolov5 for bboxes, SoloV2 for masks, and Efficientnet for classification. We also use them for image capturing but that's a bit overkill. They have a full web app stack with db etc and our product's UI running on them + the inference engine. So pretty capable little boxes.
this is very informative. is there any incentive for you guys to try out new architectures? yolov5 and solov2 are already 4+ years old.
You can deploy computer vision model pretty much on anything, depending on your requirements (model size/inference time).
I see you put some wildly different boards there (pico4ml is Cortex M0 based and is extremely low power, but really can only run tiny models all the way to Jetson series, which are GPU enabled MPU-based boards). That probably means you have no clear idea on what models you are going to be running - and that really should be a starting point.
But since you mentioned "manufacturing robots, drones, autonomous robots"", then I can tell you that Pico4ML and likely Raspberry Pi are out of question. Jetson Nano is getting EoLd and Nvidia is moving to Orin - that one is very capable, but also very expensive and power-hungry.
To see some other options, there is a nice list here https://docs.edgeimpulse.com/docs/development-platforms/fully-supported-development-boards (Disclaimer: I work for EI - but you don't have to use them).
Also, I have a YT channel on Edge ML and Robotics https://www.youtube.com/c/hardwareai