Re:TensorFlow: open-source library for machine intelligence
by maccam912 on Monday November 09, 2015 @11:05AM
(#10533776)
As far as I can tell, this may not be faster than theano/torch, but it doesn't sound like it'll be slower. It takes a similar approach of sending all the big computation stuff out to efficient implementations. The "slow" language code is simply building up a graph of work to be done by the efficient implementations.
Re:TensorFlow: open-source library for machine intelligence
by chimtim on Monday November 09, 2015 @12:07PM
(#10534206)
Do 10% speedups really matter for its success, if both libraries are ultimately calling into CUDNN? I do not think so.
Right now, Torch/Caffe adoption is really good with lots of research code being released for it (even from within Google DeepMind). So it will be interesting to see how this catches up amongst the research and developer community.
Re:TensorFlow: open-source library for machine intelligence
by dchichkov on Monday November 09, 2015 @06:33PM
(#10536603)
As a side note, it feels like the front page picture of interactive computational graph is a bit misleading - looks like the interface is still using Python (or C++), not fancy GUI... But yes, it looks very similar to a great tool from Yoshua Bengio's group - Theano. So, great! Another amazing tool to take away the grind of doing ML projects!
One thing find I found interesting is the ability to use the software you designed in research directly in production (without having to rewrite the whole thing in java)
That said, I'm excited to see Google release this. Hopefully it would encourage Facebook or Baidu to also release