It is somewhat similar to bitcoin... bitcoin core, bitcoin cash, bitcoin gold, bitcoin this, bitcoin that. Also the original creator left the project, although he didn't use a pseudonym...
Responding to the Controversy about YOLOv5
21–26 of 26 posts
Re: Responding to the Controversy about YOLOv5
#22Earlier quoted context omitted.
It seems like the researchers actually working on various versions and updates of this understand and are fine with the naming, the original creator of YOLO doesn’t seem to care, and the only people kicking up a fuss are random opinionated Internet commentators that are nothing to do with it. I don’t see what the problem is with letting the community of people actually contributing to various forms of YOLO work it ou…
What if there are two successors of YOLOv4 that both inherit large parts of YOLOv4, make different sets of changes, achieving different sets of improvements? Do we call them YOLOv5.0 and YOLOv5.1? How do we nomenclate the graph? What if another one inherits from both YOLOv5.0 and YOLOv5.1? Is it YOLOv6 or YOLOv(5.0,5.1).0?
This type of thing does happen in academia. There is a family of algorithms in constraint programming called AC, and there is AC versions 1,2,3,4,5,6,7,3.1,3.2,3.3,2000,3.1* any several other variants.
These algorithms are (mostly) written by different people. People build on each others work in academia all the timr.
Re: Responding to the Controversy about YOLOv5
#23Earlier quoted context omitted.
The article gave me the impression that pjreddie hasn't yet commented on whether he approves v5 or not. Or, did I miss something?
What I mean is that he did not make a public statement that he approves of it. In other words, as far as we know v4 was created with his approval, but v5 was created without his approval.
Annoying characteristic of standard English language is the spread of the negation. “He doesn’t seem to approve” is the same as “He seems to not approve” which is the same as “he seems to disapprove”. Funny that you represented absence of approval and other guy interpreted presence of disapproval. I blame the language. And society. And an uncaring god.
Re: Responding to the Controversy about YOLOv5
#24> Is YOLOv5 the Correct Name? > Candidly, the Roboflow team does not know. It seems like, unless you can say with certainty that you have a legitimate claim to use an existing name, the right and safe thing to do would be to not use it. Just name your project something else. You lose the brand recognition of the existing name, but on the other hand you avoid the risk of your project getting dragged like this. When in…
Roboflow didn't name the project, they just benchmarked it and wrote a blog article (or two, now) about it. So, it's more like this:
> Is YOLOv5 the Correct Name?
> Candidly, the startup that decided to benchmark it and compare it to other stuff that got drawn into this because nobody bothers to pay attention to the details in the blog post they wrote does not know.
Re: Responding to the Controversy about YOLOv5
#25Is this article addressing a strawman? I certainly raised an eyebrow at their use of the name but is there actually a "controversy"? And if so, why not be similarly upset over YOLOv4? That edition confused me just as much as v5, given that neither one came from Reddie.
It's probably referring to https://news.ycombinator.com/item?id=23478151.
Re: Responding to the Controversy about YOLOv5
#26Judging by the many tests, their yolov5 is worse than yolov4, so they should call it yolov3.5