Nvidia's demo of real-time object recognition using deep learning [video] • Hacker News Board

Re: Nvidia's demo of real-time object recognition using deep learning [video]

#21

Post by zwieback » Thu, Jan 08, 2015, 8:59 PM UTC

vkhuc wrote: post #20

zwieback wrote: post #19

Cool demo but I still wonder if fundamentally this is just a brute-force approach. Wouldn't it be better to do some traditional preprocessing (e.g. recognizing rectangles, circles, etc.) and feeding higher-level descriptors into the classifier? If the net learns based on pixels you still have to somehow solve rotation and scale invariance. Or is there something new in deep-learning vs. old-school neural nets that fix…

I think they used the methods described in http://www.cs.berkeley.edu/~rbg/papers/r-cnn-cvpr.pdf

Thanks, interesting paper.

Re: Nvidia's demo of real-time object recognition using deep learning [video]

#22

Post by nl » Thu, Jan 08, 2015, 10:39 PM UTC

Here's how to do the street sign part of this yourself: https://gist.github.com/iandees/f773749c47d088705199

Re: Nvidia's demo of real-time object recognition using deep learning [video]

#23

Post by rasz_pl » Fri, Jan 09, 2015, 7:19 AM UTC

SammoJ wrote: post #11

rasz_pl wrote: post #8

@10:08 on the right merc sls classified as SUV on the left one SUV classified as two VANs Their algorithm works at about 1Hz rate when doing signs. This is ~state of the art from 20 years ago, but running on small mobile SoC at a slow rate.

Please show a paper where fine-grained vehicle classification in unconstrained images is anywhere near this performance from 20 years ago. You will not be able to, because it wasn't.

state of the art classification accuracy/range, not speed.

Re: Nvidia's demo of real-time object recognition using deep learning [video]

#24

Post by dogma1138 » Sun, Jan 11, 2015, 11:56 AM UTC

pmalynin wrote: post #12

dogma1138 wrote: post #6

Earlier quoted context omitted.

From what i can understand what's even more impressive is that it was running on a beefed up version of their latest mobile SOC and not on some 5000$ compute GPU card. Which means that this application can be both very affordable and very practical since people won't put a 300W GPU in their car.

Yeah those numbers aren't particularly accurate. GTX 980, which costs about $600, has 2048 cuda cores and 5 tflops peak, with 150 watts consumption.

Yes because some where in my sentence i was referring to a 980 or a 780ti some where? Maybe it was a Titan Z, no maybe it's still the GTX 690 Ti which is still the fastest single card they made, or maybe that statement was referring to their latest COMPUTE card the Tesla K80 which costs 5000$, and contains 2 new Kepler cores (GM210) and requires about 300 watts of juice to run....