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

TensorFlow: open-source library for machine intelligence

tensorflow.org

Post reply on HN
Print view View original

121–130 of 211 posts

Re: TensorFlow: open-source library for machine intelligence

#121

Post by sandGorgon »

vrv wrote: post #7
Schiphol wrote: post #2

> The TensorFlow Python API requires Python 2.7 The whole scientific Python stack is available for Python 3. This seems like a somewhat backwards thing to do -- or perhaps the requirement is intended to mean at least 2.7? Edit: added context Edited again: More careful wording

We're looking to support Python 3 -- there are a few changes we are aware of that are required, and we welcome contributions to help! Tracking here: https://github.com/tensorflow/tensorflow/issues/1

is this compatible with pypy (or plan to be). Pypy is such an awesome project, done on such a small budget that it needs some well deserved love !

Re: TensorFlow: open-source library for machine intelligence

#123

Post by varelse »

chubot wrote: post #115
varelse wrote: post #86

Earlier quoted context omitted.

Might one conclude that this influential opinion might have created a big old stinky career mess for someone in the field that took many months to clean up and cost one a fair chunk of change to do so? So perhaps one could be forgiven for noting such a disruptive change in viewpoint? Now we all must own our choices and one was very silly, stupid, and naive to blindly accept a position at Google, but everyone makes mi…

Uh, so what happened? Were you working on a GPU project at Google before management came around to this way of thinking, and it got canned? That sucks, but that kind of thing happens a lot. It's not that surprising. Google wanted a homogeneous infrastructure for a long time. But a new application (neural networks) motivated a new infrastructure (GPUs in clusters). There was that Stanford paper everyone talks about wh…

I'm done ranting about Google and GPUs at last. From a technical standpoint, I believe TensorFlow vindicates my viewpoint and that's enough for me. This is closure I really needed, OK? And besides, now I can concentrate my energy on asking WTH happened to Android performance between 4.x and 5.x J/K?

And from a professional standpoint, I moved on and fixed the damage I let them inflict on my career. I eventually built exactly what I was told couldn't and shouldn't be done with GPUs.

But back then, the argument Google made to me was that too much of the workloads I wanted to run on GPUs were serialized (hence brawny versus wimpy). And from a classical parallel algorithms perspective, they were correct. The problem is that from a GPU programming perspective, they weren't even wrong(tm). And at the time, I had ~5 years of CUDA programming (very early adopter) and 30,000+ lines of CUDA code to back that up whereas the people I tried to convince had zero such experience so there was just no way. My argument boiled down to TLDR: O(n^2) or higher probably belongs on GPUs. Would anyone disagree these days?

Re: TensorFlow: open-source library for machine intelligence

#124

Post by levesque »

an4rchy wrote: post #76

I tried going through the site and also the comments but couldn't wrap my head around what this library actually is. It sounds awesome based on the response/comments. Can anyone explain this to a layman?

It is a library for the optimization of machine learning algorithms, similar to Theano. You write a model you want to optimize as a graph of symbolic expressions, and the library will compile this graph to be executed on a target platform (could be CPU, GPU). This is really neat because you essentially wrote your program in Python and now it's going to be running as optimized C++ code (or as optimized kernels on your GPU).

The fact that you defined your model as a symbolic graph means you can derive gradient equations automatically, hence ridding you of a rather tedious step in optimization. With such tools, the workflow for a practitioner is much simpler: 1-code models as graphs of symbolic expressions, and 2-define objective functions (ex. for a regression problem, your objective would be the root mean squared error, plus some regularization). Disclaimer: I did not look at the code, but from what I understand it is pretty much the same as Theano (which I've been using a lot lately).

Re: TensorFlow: open-source library for machine intelligence

#125

Post by arcanus »

1ris wrote: post #83
kragen wrote: post #11

Earlier quoted context omitted.

This "backwards" meme doesn't make any sense. Python 2 and Python 3 are different languages that happen to share the same name, a lot of syntax, and near-source compatibility, but they've been developed concurrently for ten years now. It's kind of like C and C++. If the current Python 2 team (which is part of the Python Software Foundation) abandons it, probably somebody else will take over maintenance, because it se…

Python 2 is dead.

Like it or not, it is very much not dead.

Re: TensorFlow: open-source library for machine intelligence

#127

Post by davmre »

samuell wrote: post #119

Interesting! I wrote in a draft post back in late 2013 [1], that asked: "What if one could have a fully declarative “matrix language” in which all data transformations ever needed could be declaratively defined in a way that is very easy to comprehend?" I'm now pondering whether TensorFlow isn't quite an answer to this question? [1] Posted the draft now for reference: http://bionics.it/posts/matrix-transformation-as-…

The idea of representing a program by a declarative computation graph of matrix transformations has been big in deep learning research for a few years. Theano [1] is the canonical example, though more recently the space has gotten bigger with other frameworks including CGT [2] and now TensorFlow. The computational graph abstraction is really nice in part because it gives you very straightforward automatic differentiation, which dovetails very nicely with the trend in machine learning of casting a wide range of algorithms as (stochastic) gradient ascent on some loss function.

[1] http://deeplearning.net/software/theano/

[2] http://rll.berkeley.edu/cgt/

Re: TensorFlow: open-source library for machine intelligence

#128

Post by zer0nes »

jheriko wrote: post #70

i really wish people would stop calling multidimensional arrays tensors. there is already well defined language for this. multidimensional array is fine, psuedotensor is fine. tensor is confusing if you have any previous background with tensor calculus before the word became machine learning flavour of the month. still. this does look pretty cool overall. processing large volumes of data is becoming increasingly less…

Tensor is a much better term than multidimensional array:

- It's not as verbose

- The concept of tensor has linear algebra operations associated with it while multidimensional array is just a programming term without any attached Math operations.

Re: TensorFlow: open-source library for machine intelligence

#129

Post by varelse »

robbyetor wrote: post #104
varelse wrote: post #92

Earlier quoted context omitted.

Actually lasagne is pretty good, I wasn't targeting you (but then you're pretty good at winning kaggle competitions so perhaps there's a connection there, no?)... I'm thinking mostly of Theano, which, from a performance standpoint, appears to have died the death of a thousand inexperienced cooks in the kitchen. The ~1000x performance regressions that it invokes when a junior data scientist goes off the rails and ends…

Pixel's Law? what s that? can' t find it on google...

Interesting, it does appear to be gone...

Basically, old NVIDIA marketing material used to state that GPUs double in performance every year or so whilst Moore's Law is slowing down w/r to CPU performance because clock speeds have been the same for a long time

This strictly isn't true because core count, SIMD width and vector unit counts in CPUs have all been increasing. However, from the perspective of a single-threaded C application, this is indeed so. CUDA/OpenCL OTOH automagically subsume multi-core, multi-threading, and SIMD into the language itself so the hypothetical "single-threaded" CUDA app just keeps getting better(tm).

The reality though (IMO of course) is that Intel promises and delivers backwards-compatibility at the expense of free performance beer. In contrast, NVIDIA delivers performance at the expense of 100% backwards-compatibility beer for optimized code (but read each GPU's whitepaper and spend a week refactoring your code per GPU generation and you get both, also IMO and of course experience). Of course, to be fair, if you refactor your code every time they improve AVX/SSE, CPUs are a lot mightier than what Python/Javascript/R usually imply.

Re: TensorFlow: open-source library for machine intelligence

#130

Post by cossatot »

vegabook wrote: post #99
1ris wrote: post #83

Earlier quoted context omitted.

Python 2 is dead.

hmmm. Google does not seem to agree. Your assertion is a wish not a fact. Dogmatic 3.x people are being shown, yet again, the uncomfortable, brutal truth, that 3.x is not happening in science. Seriously. If you're advising someone considering Python on the 2 v 3 question today, how can you not tell them that possibly one of the most important new machine learning libraries, only works on 2.7.

First off, 3.x is happening in science. I'm a scientist, and I use 3.x, and as of this fall, every single scientific package that I use has been ported to 3.x. Using @ for matrix multiplication is also a pretty big deal to me.

It's worth remembering that most scientists don't do any machine learning, because it's not all that useful in many domains. A lot of science is trying to find an explanatory model for the observations. Machine learning is much better at finding a good predictive model for the observations that may not offer any insight to what is happening behind the scenes.

Post reply on HN