yolov3

Agreed! Crucially, we're tracking "out of the box" performance, e.g., if a developer grabbed X model and used it on a sample task, how could they expect it to perform? Further research and evaluation is recommended! For size, we measured the sizes of our saved weights files for Darknet YOLOv4 versus the PyTorch YOLOv5 implementation. For inference speed, we checked "out of the box" speed using a Colab Notebook equipped with a Tesla P100. We used the same task[1] for both - e.g. see the YOLOv5 Colab notebook[2]. For Darknet YOLOv4 inference speed, we translated the Darknet weights using the Ultralytics YOLOv3 repo (as we've seen many do for deployments)[3]. (To achieve top YOLOv4 inference speed, one should reconfigure Darknet carefully with OpenCV, CUDA, cuDNN, and carefully monitor batch size.) For accuracy, we evaluated the task above w

Yeah, they made the most popular PyTorch implementation of YOLOv3 as well so they're not entering out of the blue, though. https://github.com/ultralytics/yolov3 The author of YOLOv3 quit working on Computer Vision due to ethical concerns. YOLOv4, which built on his work in v3, was released by different authors last month. I'd expect more YOLOvX's from different authors in the future. https://twitter.com/pjreddie/status/1230524770350817280

It's also in Ultralytics' repo which is very frequently updated. https://github.com/ultralytics/yolov3

There is a pytorch port from Ultralytics (https://github.com/ultralytics/yolov3). Nobody seems to have figured out how to achieve the training performance of darknet though, which is entirely uncommented C. The source is all there, but the loss function changed between v2 and v3, and its not documented in the paper. I think it's been fixed in that pytorch port now though. The only frustrating thing is that every commit in the repo is called update... Alternatively... you can train in darknet and then run inference in another framework of choice. Also shameless plug: I wrote an annotation tool which is designed to output darknet formatted labels: https://github.com/jveitchmichaelis/deeplabel