Learn TensorFlow and deep learning, without a Ph.D. • Hacker News Board

Re: Learn TensorFlow and deep learning, without a Ph.D.

#41

Post by amelius » Tue, Jan 24, 2017, 3:15 PM UTC

pizza wrote: post #36

amelius wrote: post #34

Perhaps somebody here can help me with a sideproject that I'm working on. I'm trying to figure out the topology of a neural network that is capable of detecting the location and orientation of a given object. Say, a wrench. I don't want to use heatmaps (e.g. [1]) because they give just the location of the object and not the orientation. So the problem is basically how to choose the output quantities and how to encode…

There are algorithms for stuff just like that in OpenCV. Maybe you could find some inspiration or clarification by reading through the source code for the algorithms for a brief description?

Yes, that's a good idea, thanks!

But I was hoping for a more scientific answer. Like how do researchers approach this problem typically? And is there a strong consensus in this area among researchers?

It seems like such a general problem.

Re: Learn TensorFlow and deep learning, without a Ph.D.

#42

Post by _Wintermute » Tue, Jan 24, 2017, 8:21 PM UTC

SilentM68 wrote: post #20

Any versions of this course planned for R Programmers?

Very few people use R for deep learning.

There's a tensorflow R port, but it requires setting up a working version of tensorflow on python. So once you have that set up, all the documentation, error messages etc are for python - so you might as well just use python.

Re: Learn TensorFlow and deep learning, without a Ph.D.

#43

Post by jkestelyn » Tue, Jan 24, 2017, 8:35 PM UTC

BTW, worth mentioning that Martin (the author of this tutorial) will present it in person at Google Cloud NEXT [1] in SF on March 8.

[1] https://cloudnext.withgoogle.com/schedule#target=tensorflow-...

Re: Learn TensorFlow and deep learning, without a Ph.D.

#44

Post by RockyMcNuts » Tue, Jan 24, 2017, 9:58 PM UTC

martin_gorner wrote: post #30

RockyMcNuts wrote: post #19

Earlier quoted context omitted.

Udacity / Google course by Vanhoucke I think is the most popular for learning TensorFlow proper - https://www.udacity.com/course/deep-learning--ud730

Definitely recommended. It's the best course available in a 3 month format.

they say 3 months? I would have thought each of the 4 modules was 1-2 full days if you want to blast through it. Maybe 8 weeks of Sundays if you do it that way. But you can definitely spend a lot of time on them and on the TensorFlow docs.

LAFF or the Andrew Ng Machine Learning courses are true semester courses, but I'm not actually sure this is.

Re: Learn TensorFlow and deep learning, without a Ph.D.

#45

Post by pizza » Wed, Jan 25, 2017, 12:30 AM UTC

amelius wrote: post #41

pizza wrote: post #36

Earlier quoted context omitted.

There are algorithms for stuff just like that in OpenCV. Maybe you could find some inspiration or clarification by reading through the source code for the algorithms for a brief description?

Yes, that's a good idea, thanks! But I was hoping for a more scientific answer. Like how do researchers approach this problem typically? And is there a strong consensus in this area among researchers? It seems like such a general problem.

Hm, there are problems in the field of computer vision that might help structure your cost/training algorithm; maybe pose estimation, the perspective-n-point problem, and point-set registration.

Re: Learn TensorFlow and deep learning, without a Ph.D.

#46

Post by SilentM68 » Wed, Jan 25, 2017, 3:59 AM UTC

martin_gorner wrote: post #28

SilentM68 wrote: post #20

Any versions of this course planned for R Programmers?

Python is one of the simplest languages to learn. I do this course as a hands-on lab with people who discover Python programming at the same time as they discover neural networks. I ask them to read this "Python 3 in 15 min" primer beforehand and they are good to go: https://learnxinyminutes.com/docs/python3/

I appreciate the link. I haven't used it in a couple of years. It will be a good refresher and will look forward to the course.

Thx :)

Re: Learn TensorFlow and deep learning, without a Ph.D.

#47

Post by SilentM68 » Wed, Jan 25, 2017, 4:01 AM UTC

_Wintermute wrote: post #42

SilentM68 wrote: post #20

Any versions of this course planned for R Programmers?

Very few people use R for deep learning. There's a tensorflow R port, but it requires setting up a working version of tensorflow on python. So once you have that set up, all the documentation, error messages etc are for python - so you might as well just use python.

I understand and will try to reproduce in R what I learn in the course as I have an interest in R, too.

Thx for the info.