Re:Getting Started with Deep Learning: A Review of Available...
by sdrothrock on Thursday February 16, 2017 @02:09AM
(#13658222)
> TensorFlow, which appears to be winning chiefly on Github stars
I was under the impression that a lot of TensorFlow's reputation and image comes from the fact that it's Google-backed and -dogfooded, meaning that it will stay in active and useful development for the foreseeable future.
Re:Getting Started with Deep Learning: A Review of Available...
by curuinor on Wednesday February 15, 2017 @06:02PM
(#13656306)
Chainer is about 50k sloc of very idiomatic Python and a little dealie for emulating numpy in GPU and a bit of Cython.
TensorFlow is about 700k sloc of C++, Python, some Golang for some godawful reason, with an enormous annoying build dealie.
That was my own decision calculus, anyhow. Speed of development and complexity still matter in machine learning land, you know.
Re:Getting Started with Deep Learning: A Review of Available...
by curuinor on Wednesday February 15, 2017 @06:11PM
(#13656379)
One more objectionable fact about TF: There's a separate better documentation repo for Google insiders only. That's not kosher.
Re:Getting Started with Deep Learning: A Review of Available...
by dontreact on Wednesday February 15, 2017 @09:27PM
(#13657380)
How do you think it's better? I use both the internal and external and the only difference is that there are more Google-infra specific things internally. The external one is prettier :)
Re:Getting Started with Deep Learning: A Review of Available...
by curuinor on Thursday February 16, 2017 @03:15AM
(#13658405)
It is definitely the case that a fair few of those 700k sloc are devoted to poking at and wibbling with Google infra specific things. Which is of basically negative value if you're some rando using it.
There are also a fair few non-infra specific bits to the internal documentation.
Re:Getting Started with Deep Learning: A Review of Available...
by nnq on Thursday February 16, 2017 @10:16AM
(#13660477)
> some Golang for some godawful reason
What's the problem with Golang in TF? It's one of the nice to work in languages and I imagine that Google sees Golang as somehting that will replace Python sometime long term...
Re:Getting Started with Deep Learning: A Review of Available...
by chewxy on Wednesday February 15, 2017 @06:21PM
(#13656455)
I also wanna add Gorgonia (https://github.com/chewxy/gorgonia) - it's not quite production ready on the GPU end, but on the CPU end I've been using it for about 4 years.
Re:Getting Started with Deep Learning: A Review of Available...
by mrubashkin on Wednesday February 15, 2017 @05:45PM
(#13656133)
Hi Vonnik, thanks for the suggestions of tools for us to try out next and add to our list!
Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends.
All of the missing libs have significant advantages over TensorFlow, which appears to be winning chiefly on Github stars. Notably speed and integrations.
[0] https://deeplearning4j.org/
http://chainer.org/
https://github.com/clab/dynet
https://github.com/PaddlePaddle/Paddle