Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Mnist Neural network visualization in Odin and Raylib. All cubes now have an opacity based on their activation/weight. I think the codebase is almost ready to be made public

48,202 Aufrufe • vor 2 Jahren •via X (Twitter)

10 Kommentare

Profilbild von Jack Wind
Jack Windvor 2 Jahren

This is awesome - how much work would be needed to make this library compatible with any torch compatible neural net?

Profilbild von Bones
Bonesvor 2 Jahren

I'd say for small models it should be simple, but if you have millions of nodes the viz wouldn't be able to handle it, it would require a lot more optimizations

Profilbild von hyena
hyenavor 2 Jahren

these sorts of tools would’ve been great in my ml classes, consider continuing building educational visualizations like this / collaborating with professors if that interests you. you’re a great dev bones

Profilbild von Bones
Bonesvor 2 Jahren

Thanks :) One of my older projects was discovered by a professor somehow, and they’re actually using it. But I’m still not sure how to make my work more visible to the academic community though

Profilbild von Covix
Covixvor 2 Jahren

absolutely love this, great stuff mr bones

Profilbild von Mystique
Mystiquevor 2 Jahren

Startup idea, "ViziGrad"... dynamic model visualization (or modeling in general) as a service... MaaS. Go to the landing page, upload your weights, view the mapping... like an MRI machine, but for NNets.

Profilbild von p
pvor 2 Jahren

@yacineMTB Wow, what a beauty!

Profilbild von Andy Mckee (Hanuman)
Andy Mckee (Hanuman)vor 2 Jahren

I need a total hour tally for the time you spent on this

Profilbild von Bones
Bonesvor 2 Jahren

i don't have an exact hour count, i've been working on this in my free hours for about a month now

Profilbild von tom
tomvor 2 Jahren

impressive, as always

Ähnliche Videos