News for hackers. Stuff that matters.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by eggy on Tuesday May 26, 2020 @12:21AM (#23307383)
I was interested until I saw you have to purchase something to train your own models. I am wondering how this compares to Darknet by Joseph Redmon [1]. You can do most of what I see on the Sod site, and train your own models. It's in C too.

[1] https://pjreddie.com/darknet/

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by qchris on Tuesday May 26, 2020 @12:55AM (#23307550)
Just a quick heads-up that Joseph Redmon isn't working on the development on Darknet any longer, and the YOLO fork by AlexeyAB [0] (now on YOLOv4) is one people should also consider using moving forward[1].

[0] https://github.com/AlexeyAB/darknet

[1] https://mobile.twitter.com/pjreddie/status/12538910781821992...

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by eggy on Tuesday May 26, 2020 @10:08AM (#23311283)
Yes, I have been following darknet for a while now. I haven't tried YOLOv4 yet. Any comments on what SOD brings to the table in comparison to darknet?
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by qchris on Tuesday May 26, 2020 @01:25PM (#23313904)
Honestly, I'm not sure. It seems like they cover slightly different fields, despite having some overlap. AFAIK, Darknet doesn't natively do a bunch of the image processing work that Sod can do, like edge detection with Canny, because if you wanted that, you'd just use OpenCV.

I'd imagine that based on the licensing, this is probably closer to the open-sourcing (well, sort of, since the commercial applications and GPU training requires a paid license) of an internal tool that the company is using on the backend of their own API-driven machine learning business. So, it covers some things that Darknet isn't really designed to do, since real-time object detection isn't the main area they're really interested in.

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by eggy on Tuesday May 26, 2020 @02:52PM (#23315028)
Real-time object detection is what YOLO does and darknet implements it, but I see where you are going with the edge detection in SOD vs. darknet. You add in OpenCV if you want to use it.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by symisc_devel on Tuesday May 26, 2020 @01:03AM (#23307589)
There is nothing to purchase at all if you want to train your own realnet models on the CPU such as Pedestrian, Car, etc. Just follow the documentation at https://sod.pixlab.io/api.html#sod_realnet_trainer on how to do so.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by eggy on Tuesday May 26, 2020 @10:07AM (#23311264)
The site says "The syntax is based on the darknet framework...".

What are the differences in capabilities? Not sure yet. I'll have to look more into it, but I was hoping somebody here could tell me if they have experience with both.

Why would I use this over darknet and the variations of Yolo - YOLOv3 or YOLOv4?

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by qubex on Tuesday May 26, 2020 @03:09AM (#23308246)
Knowing that some schools and universities are testy to use GIMP because it’s a derogatory term, I’m wondering how “SOD” will fare. “Sod off” and “you’re a real sod” are not exactly terms of endearment and are very much still in current usage (particularly by the kind of people who might be offended by using something that refers to them).
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by ploika on Tuesday May 26, 2020 @07:20AM (#23309701)
It just means "lump of turf" where I live.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by emmanueloga_ on Tuesday May 26, 2020 @03:31AM (#23308366)
I don't know, I haven't never hear "sod" as slang before, had to check urban dictionary [1]. Maybe I'm not streetwise enough :-)

1: https://www.urbandictionary.com/define.php?term=SO%20D

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by mantap on Tuesday May 26, 2020 @04:25AM (#23308638)
It's also in the real dictionary. https://dictionary.cambridge.org/dictionary/english/sod

It comes from sodomy. It's interchangeable with fuck in many contexts.

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by Y_Y on Tuesday May 26, 2020 @04:53AM (#23308772)
Except it's much milder, there's no problem with saying "sod off" on tv during the day, for example. Apparently the British Communications Regulator, Ofcom[0], sees it as "Mild language, generally of little concern", whereas fuck is "Strongest language, unacceptable pre-watershed. Seen as strong, aggressive and vulgar. Older participants more likely to consider the word unacceptable."

[0] https://www.mirror.co.uk/news/uk-news/read-what-ofcom-thinks...

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by SomeoneFromCA on Tuesday May 26, 2020 @12:25PM (#23313100)
Darknet does not sound good either. You know, like the other Darknet.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by emmanueloga_ on Tuesday May 26, 2020 @03:33AM (#23308376)
It seems like they go out of their way to hide the real identity of the ppl behind this (feels like a solo developer). Why would someone do this?

http://symisc.net/contact.html

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by n_t on Tuesday May 26, 2020 @05:03AM (#23308835)
It is indeed interesting! I had some use case in mind so I tried to find more about company. sysmic is owned by Pixlab, but both have zero info about people involved. Interestingly, even their linkedin page (../company/pixlabio) doesn't lists any individual and given the work they are doing, I doubt it's single person effort. Well, someone mentioned darknet project, looking into that instead.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by enriquto on Tuesday May 26, 2020 @03:47AM (#23308458)
> Why would someone do this?

Maybe they regard it as a hobby side project. Or maybe not everybody wants to attract public attention to all of their activities.

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by MaxBarraclough on Tuesday May 26, 2020 @05:41AM (#23309010)
I don't have an answer, but it's not always a bad sign. This guy was a powerhouse in the Ruby community, for instance, and was anonymous for as long as he was active there: https://en.wikipedia.org/wiki/Why_the_lucky_stiff
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by ricardo81 on Tuesday May 26, 2020 @08:52AM (#23310472)
Could just be a privacy conscious individual, though visibility does indeed help peace of mind
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by badpun on Tuesday May 26, 2020 @07:12AM (#23309631)
They are a commercial operation. If this is indeed a single guy, by obfuscating that, he can fool some people into thinking that they're dealing with a larger organization (and hence be more willing to hand over money).
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by symisc_devel on Tuesday May 26, 2020 @09:17PM (#23318383)
You are wrong. Symisc is an independent software vendor with a distributed team of ~14 collaborators and offices in Texas, Luxembourg and Tunis.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by stefan_ on Monday May 25, 2020 @09:40PM (#23306662)
So this is like the printer model, sell the printer (library) for free and charge for the toner (model).
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by skanga on Monday May 25, 2020 @10:16PM (#23306851)
Can you develop your own models?
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by lcampbell on Monday May 25, 2020 @10:24PM (#23306894)
Doesn't seem like it. The GPU module required for training CNNs is sold separately[1]:

> A GPU capable special SOD release which is not available to the public is required in order to train your own CNN model.

There are some bits included for training "RealNet" models[2] but I'm not sure what those are or how they work. The documentation suggests that RealNet models can be trained in reasonable timeframes with a CPU.

[1] https://sod.pixlab.io/cnn_train.html

[2] https://sod.pixlab.io/c_api/sod_realnet_train_start.html

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by stbtrax on Tuesday May 26, 2020 @02:31AM (#23308053)
What kind of embedded processor is this meant for? cortex-m3 low level or more like a cortex A class?
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by person_of_color on Monday May 25, 2020 @11:25PM (#23307120)
Click. No Q16.16. Close tab.
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by johanam on Monday May 25, 2020 @11:42PM (#23307203)
Can you elaborate what you mean by this?
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by baocin on Tuesday May 26, 2020 @02:18AM (#23307993)
"Q16.16" seems to refer to fixed floating point precision (https://en.wikipedia.org/wiki/Q_(number_format)). The parent comment is unhappy that SOD doesn't support floats with 16 integer bits and 16 fractional bits. I'm unsure why lack of support for 32 bit floats is such a problem considering that SOD is suppose to run on such resource constrained devices. Is there a particular domain where this is necessary?
Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by boomlinde on Tuesday May 26, 2020 @09:28AM (#23310826)
> "Q16.16" seems to refer to fixed floating point precision

Floating is the opposite of fixed in this context. The GP is unhappy that it doesn't support fixed point numbers of a common fixed point number format.

This is not just nitpicking, because the difference in time and implementation cost between floating and fixed point can be huge on systems where floating point operations aren't offloaded to a pipelined FPU. Fixed point arithmetic on the other hand, even if your hardware doesn't support it directly, can easily be implemented in terms of integers.

Re:Sod – An Embedded Computer Vision and Machine Learning Ti... by toohotatopic on Tuesday May 26, 2020 @02:09AM (#23307932)