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

21–30 of 91 posts

Re: Show HN: TensorFire

#21

Post by bijection »

rahimnathwani wrote: post #9
antimatter15 wrote: post #7

Hey HN! 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 :) 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 ( https://logrocket.com/ ) to help…

This looks awesome! It looks like it (like keras-js) is only for inference (running already-trained models) and not for training. Is this correct? Are the operations or memory required for training very different?

Yes, you are correct! Training benefits much more from available memory through batching and, since in many cases you only need to train once, it usually makes sense to train on beefy GPUs.

TensorFire is useful in situations where you want to perform inference, but you don't want to ship user-supplied data to your servers, either because you would run out of bandwidth, you would run out of compute power, or your users want to keep their data private.

Re: Show HN: TensorFire

#22

Post by cs702 »

bijection wrote: post #5
cs702 wrote: post #4

Where is the repo?

We're still finishing up a few things (documentation etc) and planning on releasing more stuff tomorrow. You can also sign up for the mailing list if you'd like us to email you when the repo goes live!

Great. Look forward to diving in tomorrow. Thank you for the quick reply!

Re: Show HN: TensorFire

#23

Post by mholt »

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.

Re: Show HN: TensorFire

#24

Post by plingamp »

nametube wrote: post #12

"running networks in the browser with TensorFire can be faster than running it natively with TensorFlow." could you elaborate on this statement ?. What kinds of architectures does this hold true for ?.

From the github issue referenced in the FAQ, I think they mean that because TensorFlow only natively supports CUDA, TensorFire may outperform TensorFlow on computers that have non Nvidia GPUs, such as the new MacBook Pro.

Re: Show HN: TensorFire

#25

Post by iXce »

> 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?

Re: Show HN: TensorFire

#26

Post by antimatter15 »

motoboi wrote: post #11

Could someone explains whats is going on here? What are the steps? Why those colorful artifacts appear before the final result?

It's showing a visualization of all the intermediate activations of the style transfer network. The intermediate pictures are 4D, so they're visualized as a sequence of tiles.

The network being run is defined here https://github.com/lengstrom/fast-style-transfer/blob/master...

This post provides a pretty good explanation of what's happening: https://shafeentejani.github.io/2017-01-03/fast-style-transf...

There's a sequence of 9x9 and 3x3 convolutions that transforms that one big input image into a bunch of smaller images. They're processed by a sequence of residual convolutions. Finally, these tiny tiles are merged together back into a stylized image of the same size as the original input with a few deconvolution operations.

Re: Show HN: TensorFire

#28

Post by ldenoue »

bijection wrote: post #5
cs702 wrote: post #4

Where is the repo?

We're still finishing up a few things (documentation etc) and planning on releasing more stuff tomorrow. You can also sign up for the mailing list if you'd like us to email you when the repo goes live!

Would be great to port YOLO on your library; always an impressive visual demonstration

Re: Show HN: TensorFire

#29

Post by zo1 »

>"Could not initialize WebGL, try another browser".

Happening in both Firefox and Chrome on Ubuntu. What exactly am I missing here?

Re: Show HN: TensorFire

#30

Post by fabian2k »

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.

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.

Post reply on HN