darknet

> The YOLO series is developed and maintained by Ultralytics. All YOLO code and weights are released under the AGPL-3.0 license.The YOLO series is developed and maintained by Ultralytics. All YOLO code and weights are released under the AGPL-3.0 license. The original author of YOLO and the Darknet framework [1] issued the code under pretty much every license you wish to use [2]. My preferred fork by AlexeyAB is under an equally permissive license [3]. Ultralytics then created their own model under the AGPL-3.0 license [4], which probably would never stand up in a court as they have the model from the likes of YOLOv3 in their source [5]. This entire article is flawed anyway, because they don't state which YOLOv11 model they are using or compare the accuracy. They appear to have just taken the pre-trained models and assumed it's apples-to-a

Hi, Almost All models are based on the Darknet[0] configurations which would come under this License[1]. We further trained/finetuned those architectures on additional datasets collected by us. Whole framework actual used for final products is completely written in Nim. [0] https://github.com/AlexeyAB/darknet [1] https://github.com/AlexeyAB/darknet/blob/master/LICENSE

BTW, this sounded surprising to me, so I went to check it out. According to YOLOv4 GitHub, i7-7700 can only do 4 FPS of detection. For comparison, tuned version on Jetson Xavier (NVidia dev board) does 40FPS. https://github.com/AlexeyAB/darknet https://github.com/indra4837/yolov4_trt_ros

This is mostly in the realm of computer vision, but I would recommend checking out AlexeyAB's fork of Darknet: https://github.com/AlexeyAB/darknet It's got decent CUDA acceleration, I personally run a GTX 960M for training.

If you can position the camera so that only the "counter" is visible from it, a much easier option is to use the pre-trained yolov4. https://gist.github.com/YashasSamaga/e2b19a6807a13046e399f4b... (download links for yolov4.weights is at https://github.com/AlexeyAB/darknet) Using this, you will be able to detect if a cat is present in your image.

This isn't directly relevant to PP-YOLO, but I'm surprised roboflow is still promoting "YOLOv5" - despite that model not having an associated paper and it not being made by the authors of the previous YOLO's.[1] The ML community has been asking the authors of that model to rename their project[2] because they are basically stealing publicity by making it seem like the next version of YOLO, despite its performance being worse than that of YOLOv4.[3] Roboflow has deflected this in the past by claiming they don't know if "YOLOv5" is the correct name[4], but by continuing to promote it, they are directly supporting it. In fact, I wouldn't be surprised that their claim of not being affiliated with Ultralytics to be either false or a half truth, given that all the top pages about "YOLOv5" were done by roboflow, including the first official anno

Not that I really care, but the original GitHub issue[1] has multiple researchers "kicking up a fuss", why are you just reducing their opinion to "random opinionated commentators"? Also, the original creator did not say he does not care ("doesn't matter what I think"), he said another maintainer of darknet/yolo should have more say. [2] [1] https://github.com/ultralytics/yolov5/issues/2 [2] https://github.com/AlexeyAB/darknet/issues/5920

Thanks for your followup thoughts. Pleased the conversation has evolved to focus on architecture and performance rather than naming alone. re: GitHub comment deletion - We determined we should engage when we have easier to reproduce results, so we moved quickly to share them. That's what this post and diligence is, and I've re-engaged on the issues thread in question [1] with fuller remarks + reproducible Colab notebooks. [1] https://github.com/AlexeyAB/darknet/issues/5920#issuecomment...

This post is in response to the discussion[1] on Hacker News this week on the post "YOLOv5: State-of-the-art object detection at 140 FPS" and the objections raised by AlexeyAB on Github[2]. The controversy surrounded around two points: • Should the model truly be named YOLOv5? • Are the initial benchmarks Roboflow published accurate and reproducible? We have published more details surrounding our methodology, clear steps and notebooks for reproducing our results, a correction of an unfair comparison we made (re relative inference speed and batch sizes), how we think about the naming controversy and a request for the community to weigh in. [1] https://news.ycombinator.com/item?id=23478151 [2] https://github.com/AlexeyAB/darknet/issues/5920#issuecomment...

AlexeyAB is the primary author on YOLOv4, and the darknet maintainer, so yes. This is pretty much the official word on the matter: https://github.com/AlexeyAB/darknet/issues/5920#issuecomment... Despite that, there was still a lot of controversy over the decision to call it v4. See that thread for the discussion on v5 and you can make your own judgement.

AlexeyAB seems to have gotten endorsement from pjreddie: https://github.com/AlexeyAB/darknet/issues/5920#issuecomment...

> Edit: Although as yeldarb explains in a comment here[3], > it's probably a bit more complicated than that. Legally speaking I'm not sure anything wrong was really done here. Morally speaking, it seems quite unethical. AlexeyAB has really been carrying the torch of the Darknet framework and the YOLO neural network for quite some time (with pjreddie effectively handing it over to him). AlexeyAB has been providing support on pjreddie's abandoned repository (e.g. [1]) and actively working on improvements in a fork [2]. If you look at the contributors graphs, he really has been keeping the project alive [3] (vs Darknet by pjreddie [4]). Probably the worse part in my opinion is that they have also seemingly bypassed the open source nature of the project. This is quite damning. [1] https://github.com/pjreddie/darknet/issues/1900 [2] https://gi

I'm just going to call this out as bullshit. This isn't YOLOv5. I doubt they even did a proper comparison between their model and YOLOv4. Someone asked it to not be called YOLOv5 and their response was just awful [1]. They also blew off a request to publish a blog/paper detailing the network [2]. I filed a ticket to get to the bottom of this with the creators of YOLOv4: https://github.com/AlexeyAB/darknet/issues/5920 [1] https://github.com/ultralytics/yolov5/issues/2 [2] https://github.com/ultralytics/yolov5/issues/4

Great points, and hoping Glenn releases a paper to complement performance. We are also planning more rigorous benchmarking nonetheless. re: PyTorch being a confounding factor for speed - we recompiled YOLOv4 to PyTorch to achieve 50 FPS. Darknet would likely top out around 10 FPS on the same hardware. EDIT: Alexey, author of YOLOv4, provided benchmarks of YOLOv4 hitting much higher FPS here: https://github.com/AlexeyAB/darknet/issues/5920#issuecomment...

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...