Tensorflow.js – A Practical Guide

Post by williamdclt » Wed, Jun 13, 2018, 4:31 PM UTC

timr wrote: post #10

nsthorat wrote: post #7

Earlier quoted context omitted.

There are many reasons to do it in JavaScript: - Many companies and projects have their entire server-side stack in JavaScript and Node.js, and often they want to simply make a prediction through a model. It's quite a lot to ask them to pull in a python runtime just to make a prediction. TensorFlow.js with node bindings to TensorFlow C enables this type of inference with minimal overhead. - Privacy. You can make pred…

There's literally only one reason to do it in Javascript: you want to use Javascript. There are dozens of reasons why it's a terrible idea: unfortunate memory consumption, abysmal performance, poor abstractions, bad library support, and so on. Tensorflow in Python isn't exactly a stellar choice for performance, but at least you gain flexibility and nice abstractions and good high-performance math/stats library suppor…

Post by timr » Wed, Jun 13, 2018, 4:39 PM UTC

williamdclt wrote: post #12

timr wrote: post #10

Earlier quoted context omitted.

There's literally only one reason to do it in Javascript: you want to use Javascript. There are dozens of reasons why it's a terrible idea: unfortunate memory consumption, abysmal performance, poor abstractions, bad library support, and so on. Tensorflow in Python isn't exactly a stellar choice for performance, but at least you gain flexibility and nice abstractions and good high-performance math/stats library suppor…

> So this is "we don't want to use another language". Yup, which is a perfectly valid reason. > If calling out to a binary is a security problem for you You miss the point. The security problem is sending the raw data from the client to the server. > So again, this boils down to "I don't want to use Python and I'd prefer to use JS instead." Which once again, is a perfectly valid reason > Servers are expensive so host…

Post by jorgemf » Wed, Jun 13, 2018, 4:59 PM UTC

zawerf wrote: post #9

The most practical use not mentioned here is probably to import existing trained models/weights. I can see it being useful for anything that you want to run in real-time (e.g., webcams apps like https://github.com/ModelDepot/tfjs-yolo-tiny ) and can't pay a round-trip cost to server. https://js.tensorflow.org/tutorials/import-keras.html Training a model in the browser is the least practical use for tensorflow.js IMO…

Post by quadrature » Wed, Jun 13, 2018, 5:05 PM UTC

galfarragem wrote: post #3

Noob question: Can anybody tell in a few sentences of plain english what is tensorflow, how it works and why seems to be so relevant?

Post by gaius » Wed, Jun 13, 2018, 5:30 PM UTC

galfarragem wrote: post #17

s-macke wrote: post #8

Earlier quoted context omitted.

Tensorflow tries to fit the free parameters (usually millions of parameters) of a function y=f(x). The fitting algorithm gets usually thousands or millions of examples of how the output y for a given input x has to look like. For example, x can be tens of thousands of images of cats and dogs, and y can be 1 for a dog and 0 for a cat. The goal for the fitting algorithm is to find parameters that describe the concept o…

If I understand it correctly: - Tensorflow is the best tool to make the grunt work necessary to calibrate the parameters of fitting algorithms. - Models of fitting algorithms are human proposed and where the ML 'art' is. Seems to be kind of reverse engineering.