Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: TensorFire

tenso.rs

Post reply on HN
Print view View original

31–40 of 91 posts

Re: Show HN: TensorFire

#32

Post by batmansmk »

This is awesome!

Quick question: is the code compiled from js to webgl in browser as well, or do I need to compile beforehand?

I see this as a great way to learn and teach AI without having to bring a large toolchain.

Edit : it seems it is just a runtime for now for Tensorflow models!

Re: Show HN: TensorFire

#33

Post by espadrine »

bijection wrote: post #6
zitterbewegung wrote: post #3

Really cool demo. How does this compare to https://github.com/transcranial/keras-js ? Do the authors have a licence in mind?

TensorFire is up to an order of magnitude faster than keras-js because it doesn't have to shuffle data back and forth between the gpu and cpu. Also TensorFire can run on browsers and devices that don't support OES_TEXTURE_FLOAT. We will probably release it under an MIT license.

How does it compare to WebDNN[0]? It seems like a closer comparison, especially with WebGPU.

It would be good if you had a comparative benchmark on the website.

[0]: https://mil-tokyo.github.io/webdnn/

Re: Show HN: TensorFire

#34

Post by symlinkk »

iXce wrote: post #25

> as fast as CPU TensorFlow on a desktop > You can learn more about TensorFire and what makes it fast (spoiler: WebGL) Does this mean that using a GPU in a browser through WebGL yields the same speed than a desktop CPU?

Actually it seems like WebGL is doing it even faster. Which makes sense - machine learning involves a lot of matrix math, which GPUs are made for and CPUs aren't.

Re: Show HN: TensorFire

#35

Post by dennykane »

Cool! Awesome! New MIT grads playing with JS who think "this whole deep learning thing is pretty neat"!

Most "normal" humans -- and application developers -- will just see this as "yet another webapp" running some crazy ass code in a browser tab with no apparent rhyme or reason.

We've gotta stop the insanity! We need regulation! We need: "Linux on the Web" (a web-based OS that I've been developing for the past 5 years, see it here: https://linuxontheweb.org) to start putting this kind of crazy, experimental stuff into actual use.

I'm really not trying to be too much of a jerk, but I've been working on my project for about as long as it takes to get an entire college degree, and I'm going to start needing some help here!

Re: Show HN: TensorFire

#38

Post by bijection »

espadrine wrote: post #33
bijection wrote: post #6

Earlier quoted context omitted.

TensorFire is up to an order of magnitude faster than keras-js because it doesn't have to shuffle data back and forth between the gpu and cpu. Also TensorFire can run on browsers and devices that don't support OES_TEXTURE_FLOAT. We will probably release it under an MIT license.

How does it compare to WebDNN[0]? It seems like a closer comparison, especially with WebGPU. It would be good if you had a comparative benchmark on the website. [0]: https://mil-tokyo.github.io/webdnn/

At the moment WebDNN only runs models on the GPU in Safari Technology Preview, falling back to CPU on all other platforms / browsers: https://mil-tokyo.github.io/webdnn/#compatibility

Re: Show HN: TensorFire

#40

Post by zitterbewegung »

bijection wrote: post #6
zitterbewegung wrote: post #3

Really cool demo. How does this compare to https://github.com/transcranial/keras-js ? Do the authors have a licence in mind?

TensorFire is up to an order of magnitude faster than keras-js because it doesn't have to shuffle data back and forth between the gpu and cpu. Also TensorFire can run on browsers and devices that don't support OES_TEXTURE_FLOAT. We will probably release it under an MIT license.

I'm really interested in using Smartphones / Mobile devices for inference. Can this work with react-native so that I can build it without a bridge ? I would assume I would create a webview that would load a local website.
Post reply on HN