It classified my mostly-bald, short hair as "shower cap". I help a coffee cup up to the camera that it called a plunger. There were some other bathroom-centric classifications as well, maybe it tries to guess the room type and common objects from the scene? FTR, I'm sitting in my open kitchen area, nothing around looks remotely like a bathroom.
I can appreciate folks coming to the defense of the demo, but the lede on what makes this special is pretty well buried to folks that aren't in this space.
If there was a blurb on the page stating that the cool bit we should be excited about isn't whether the image classification is accurate, but that there's realtime image classification running against WebGPU. That's definitely neat. However, with no context for folks clicking a random link, I don't think it's really all that off base for folks to comment on the model's functionality being comically inaccurate. At the time of writing, I had to read the bottom comment to get the understanding necessary for why this is neat.
You should add a button to switch cameras, on my computer it’s stuck on the Open Broadcaster Studio’s virtual camera (even while close) and I’m not sure how to get it use my webcam instead.
People complaining about quality here are missing the point, this is ONNX compatible inference engine written Rust, it just using 5MB SqueezeNet from 2016 for simplicity.
Question is, is it worth to invest time and effort into ONNX ?
Missing the point?
When the classifications are horribly bad, what is the point?
I can write a random phrase generator in FAR less than 5MB that would have the same overall accuracy as this.
[+] [-] unvs|2 years ago|reply
[+] [-] brk|2 years ago|reply
[+] [-] jesperwe|2 years ago|reply
[+] [-] op00to|2 years ago|reply
[+] [-] belthesar|2 years ago|reply
If there was a blurb on the page stating that the cool bit we should be excited about isn't whether the image classification is accurate, but that there's realtime image classification running against WebGPU. That's definitely neat. However, with no context for folks clicking a random link, I don't think it's really all that off base for folks to comment on the model's functionality being comically inaccurate. At the time of writing, I had to read the bottom comment to get the understanding necessary for why this is neat.
[+] [-] llarsson|2 years ago|reply
[+] [-] archerx|2 years ago|reply
[+] [-] nilicule|2 years ago|reply
[+] [-] prox|2 years ago|reply
Made me think of probably one of the great quotes in sci-fi cinema.
[+] [-] clarkmcc|2 years ago|reply
[+] [-] diimdeep|2 years ago|reply
Question is, is it worth to invest time and effort into ONNX ?
https://en.wikipedia.org/wiki/SqueezeNet
https://github.com/onnx/models?tab=readme-ov-file#image-clas...
here is the same model using tensorflowjs
https://hpssjellis.github.io/beginner-tensorflowjs-examples-...
https://t-shaped.nl/posts/running-ai-models-in-the-browser-u...
[+] [-] cchance|2 years ago|reply
[+] [-] brk|2 years ago|reply
[+] [-] FpUser|2 years ago|reply
Ah, the fact that it is written in Holy Rust instantly absolves abysmal quality.
[+] [-] Eduard|2 years ago|reply
[+] [-] kypro|2 years ago|reply
This has to be the most random and inaccurate image classification I've ever seen.
[+] [-] spoiler|2 years ago|reply
[+] [-] Netcob|2 years ago|reply
[+] [-] brainless|2 years ago|reply
[+] [-] spzb|2 years ago|reply
I get it, it's an XKCD password generator https://xkcd.com/936/
[+] [-] vmfunction|2 years ago|reply
Is the path to the rust hard coded?
[+] [-] lights0123|2 years ago|reply
[+] [-] rogue7|2 years ago|reply
[+] [-] alex_duf|2 years ago|reply
That's pretty impressive
[+] [-] pattle|2 years ago|reply
[+] [-] smusamashah|2 years ago|reply
[+] [-] geek_at|2 years ago|reply
[+] [-] radeonx700|2 years ago|reply