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]<p>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]<p>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 announcement.[5]<p>[1] <a href="https://github.com/AlexeyAB/darknet/issues/5920" rel="nofollow">https://github.com/AlexeyAB/darknet/issues/5920</a><p>[2] <a href="https://github.com/ultralytics/yolov5/issues/2" rel="nofollow">https://github.com/ultralytics/yolov5/issues/2</a><p>[3] <a href="https://github.com/AlexeyAB/darknet/issues/5920#issuecomment-642812152" rel="nofollow">https://github.com/AlexeyAB/darknet/issues/5920#issuecomment...</a><p>[4] <a href="https://blog.roboflow.ai/yolov4-versus-yolov5/" rel="nofollow">https://blog.roboflow.ai/yolov4-versus-yolov5/</a><p>[5] <a href="https://blog.roboflow.ai/yolov5-is-here/" rel="nofollow">https://blog.roboflow.ai/yolov5-is-here/</a>
As a sidenote, can they get Redmon's name correct? In [1] and [2] they call him Redmond, and in [3] they call him PJ Reddie, which is his username and not his real name. It's not even that hard to be correct here...<p>[1] <a href="https://blog.roboflow.ai/pp-yolo-beats-yolov4-object-detection/" rel="nofollow">https://blog.roboflow.ai/pp-yolo-beats-yolov4-object-detecti...</a><p>[2] <a href="https://blog.roboflow.ai/a-thorough-breakdown-of-yolov4/" rel="nofollow">https://blog.roboflow.ai/a-thorough-breakdown-of-yolov4/</a><p>[3] <a href="https://blog.roboflow.ai/yolov5-is-here/" rel="nofollow">https://blog.roboflow.ai/yolov5-is-here/</a>
Was using "YOLOv5" (hope they merge all the efforts or relabel) yesterday and was amazed on how easy it was (no input image scaling or manipulation) and how fast it was with my model (<1h on RTX2080). Also on how easy it was to use in general (runs, ...) and how easy it was to install (Ubuntu 20.04).<p>To me PyTorch is much more convenient than Darknet.
Suppose someone wanted to train a model to identify which decade a photo was taken in. What would be the current SOTA architecture for that type of task? (Suppose also that you had a few million labeled examples.)<p>I like yolo because it’s a production grade object defector. It seems harder to find a production grade classifier.<p>One amusing but dumb idea would be to use yolo for this: train the model on “photo from 1930,” “photo from 1940,” etc, where the bounding boxes cover the entire photo. But I’m curious what the professional solution might be.
I think at a certain point, FLOP count will be more important than FPS. Like once you're running at real time, there aren't a lot of applications that care about 120 FPS vs 110 FPS. But there are a lot of situations where you care about the total number of operations (regardless of GPU parallelism) because you want to run on an edge device or have power constraints.
Slightly tangential, but has anyone had a chance to use PaddlePaddle? I played around with it for a little bit a few months ago, and found it to be generally a regression in use-ability when compared to Pytorch or Tensorflow V2. I’d be interested to know what someone more experienced with it thinks.
Baidu should be sanctioned. It is one of the companies responsible for what's happening to Uighurs and other minorities.<p><a href="https://www.youtube.com/watch?v=OQ5LnY21Hgc" rel="nofollow">https://www.youtube.com/watch?v=OQ5LnY21Hgc</a><p>Computer vision technology, face recognition, object detection, image segmentation... it's all being weaponized.<p>AI/ML frameworks should have more restrictive licenses that forbid mass surveillance.