Congrats on the launch! The constraint of a ~60W compute budget for fully onboard autonomy in a GPS-denied environment is impressive, I'm curious about the 'feature-poor' aspect you mentioned. Warehouses are notorious for having repetitive scenery which usually hard for visual SLAM regarding loop closures. How do you prevent the drone from getting lost when aisle 4 looks exactly like aisle 40? Best of luck!
Start with this course: https://www.cs.cmu.edu/~16385/
Then you can check udacity and coursera courses for DL.
Try not to go directly into DL but first understand basic computer vision terms.
Very nice build indeed! I was comparing it with Lambdas build and it's pretty good on comparison, any thoughts on the Threadripper vs Intel? Also regarding the PSU, I've seen some pretty nasty reviews on that one (https://www.amazon.com/Rosewill-HERCULES-1600-Continuous-Has...). How did yours perform so far?
Pretty nice, I'm really interested in pipelines for deep learning at scale, they link to this article (https://blogs.dropbox.com/tech/2017/04/creating-a-modern-ocr...), if anyone has some other insights I'd be thankful.
So far I used TensorRT to deploy to inference servers. But there is a lot of boilerplate and something like a 'load balancer' for DL networks would be very interesting.
I guess the components. I think the sold the machine at a loss and maybe you could make some profit reselling some components, yet I am not quite sure.
Hi there, I applied and got a call, all good, then they said they will schedule a coding interview but no reply until now. Any ideas? I mean I would get it if I don't get contacted after the call, but saying that you will schedule a coding interview and then disappearing sounds a bit weird.
But the deadlines! I am sleeping so little, got too much caffeine in my system, dunno, thanks for the advice though, will try to take a nap and see some posts in 9gag
I was working with a company that sub contracted work from the US, the average pay was reasonable for the living standar but they were charging 2x to 4x more to the companies in US, thus making huge profit out of us. I felt bad for a while and left because other factors, it would be nice to have something written from that point of view.
Welp, I used to get books, papers and software from non-legal sources when I was in undegrad, because I just couldn't afford it, now that I make some money I buy most of this stuff. The thing is, without all those resources in the past I couldn't have made it to where I am now. Just my 2 cents.
Hi there Chris, I am a robotics engineer doing graduate studies, they aren't any possitions open for an intership in that area in the page, any idea if one will be open soon?
Best regards
Adds are not the problem, the problem is the problem is the quantity of Adware. I whitelist the pages and creators I want to support because I know they make a living out of that. Removing add blockers won't fix the problem, removing adware will.