Hey HN!<p>We're really excited to finally share this with you all! This is the first of a series of demos that we're working to release this week, and we're hoping you'll keep us to that promise :)<p>Sorry if it doesn't work on your computer! There's still a few glitches and browser compatibility problems that we need to iron out, and we're collecting some telemetry data with LogRocket (<a href="https://logrocket.com/" rel="nofollow">https://logrocket.com/</a>) to help us do so (so you all know what kind of data is being collected).<p>We'll open source the library under an MIT license once we finish writing up the API docs, and fixing these bugs.
TensorFire was a finalist of AI Grant. Applications for the next batch are open now! Get $2,500 to work on your AI project: <a href="https://aigrant.org" rel="nofollow">https://aigrant.org</a>.<p>It should only take five minutes or so to apply.
Really cool demo. How does this compare to <a href="https://github.com/transcranial/keras-js" rel="nofollow">https://github.com/transcranial/keras-js</a> ? Do the authors have a licence in mind?
This is amazing. I can't use GPU Tensorflow (natively) on my Macbook Pro because it doesn't have an NVIDIA graphics card. But I can... in the browser! Honestly didn't see that one coming.
Well done! Also important to note this project is one of the 10 recipients of the Spring 2017 AI Grants[1].<p>[1] <a href="https://aigrant.org/#finalists" rel="nofollow">https://aigrant.org/#finalists</a>
Really cool - just want to point out that the flashing rectangles might trigger epilepsy. I'm not sure if they're intended, but on Chrome on Linux I get a bunch of 1 frame brightly colored rectangles flashing before the result. Might want to disable that or put a warning to avoid an accident.<p>That said, well done, very impressive project!
"running networks in the browser with TensorFire can be faster than running it natively with TensorFlow."<p>could you elaborate on this statement ?. What kinds of architectures does this hold true for ?.
I've played around with doing some computation in WebGL, but it was rather tedious and difficult with my limited knowledge about the topic. It's possible, but you can't even rely on floating point texture to be available on all systems, especially mobile. And for anything more complicated, you probably need to be able to render to floating point textures, which is even more rare than support for plain floating point textures.<p>This only makes it more impressive when people do cool computational stuff in WebGL, but I'd wish there were some easier ways for non-experts in shader programming to do some calculations in WebGL.
Hmm, this seems to lock up & crash my whole browser (Chrome 59, windows, nvidia graphics) when I try to run any of the examples. It gets past Downloading Network, then gets about 5% through Compiling before getting stuck.
It is with great pleasure that I may present to you, Denali:<p><a href="https://imgur.com/gallery/ASRQg" rel="nofollow">https://imgur.com/gallery/ASRQg</a>
Didn't work here, just a bunch of colored squares on Safari, Chrome or Firefox. The latter actually managed to hang my machine. I could ssh to it but kill -9 wouldn't terminate Firefox.
Had to force reboot the machine, haven't done that in years.<p>Amazing and scary, this WebGL thing is.<p>iMac 2011, latest OS<p>Edit: worked on MacBookAir
This is awesome!<p>Quick question: is the code compiled from js to webgl in browser as well, or do I need to compile beforehand?<p>I see this as a great way to learn and teach AI without having to bring a large toolchain.<p>Edit : it seems it is just a runtime for now for Tensorflow models!
I get an SSL error SEC_ERROR_UNKNOWN_ISSUER when I try to load this page. I tried removing https from the URL but then it's blocked by OpenDNS with message "This domain is blocked due to a security threat"
Whenever I click on an image in the lower left corner it compiles the kittens. This shouldn't be like this, right? The NN is supposed to take example I'm choosing. (?)<p>And, as everyone else mentioned already: f<i></i>*ing wow!
Inference speed looks brilliant. Eager to read the source!<p>(Also, somehow I had a feeling before even reading that this project was by the people who made Project Naptha etc. Have you written/talked about this anywhere earlier?)
> as fast as CPU TensorFlow on a desktop<p>> You can learn more about TensorFire and what makes it fast (spoiler: WebGL)<p>Does this mean that using a GPU in a browser through WebGL yields the same speed than a desktop CPU?
Seriously cool. Great work. I did get a glitch every now and then in the rendered output (say 1 out of 5 times) using Safari 10.1.2, MBP touchbar 2016 15", Radeon Pro 460 4096 MB.
Is the end goal to allow people to donate computing power for training? (a la Folding@home or SETI@home except just by visiting a webpage)<p>If so that's amazingly clever!
I guess WebGL is now the "good enough" cross-platform vendor neutral replacement for CUDA.<p>Tensorflow should add a WebGL backend that runs in NodeJS.
hey, stop it.<p>i'm running 55.0b13 (64-bit) firefox on windows 10 and clicking on that demo froze the browser, froze my box - hard reboot.<p>whatever you're doing some of it's wrong. bad wrong.