Sergiy

1) Everything worked fine 2-3 days ago and I did not made any changes to the images or annotations 2) I went thought all images with a Python script to...

> Hi, try to not pass a **--hyp** at all, let it default to whatever it wants. This might help you as I've seen all sorts of issues with it...

To cite the work of YOLO if you use it in your academic work

> There is a error when I run segment/train with 1280 or 1600 imgsz in DDP mode, It happenes around 20% of the first epoch. I am confused, because **it...

Still crashes for me with any batch size and without --sync-bn, see https://github.com/ultralytics/yolov5/issues/10716

I saw no difference in training time with --cache or without when using a SSD, interesting. Also using a smaller image size (e.g. 160 with batch size of 960) was...

drift detection? Drift of a car? Inference data distribution drift?

> @wvalcke hi! can you try `--config-name default.yaml` and let me know if the issue still exisists? Thanks! For me it ignores my custom "default.yaml" and loads your default settings....

@AyushExel I renamed my custom config to "custom.yaml", it now shows a different error message: ``` (oneformer) jupyter@yolact-eu-for-object-detection-1:~/yolov8$ yolo task=detect mode=train --config-name=home/jupyter/yolov8/custom.yaml Cannot find primary config 'home/jupyter/yolov8/custom.yaml'. Check that it's...

Is there a way to train YOLO8 same way we trained YOLO5 with: `python segment/train.py --weights 'yolov5l-seg.pt' --cfg yolov5l-seg.yaml --img 600 --epochs 200 --data data/sagemaker.yaml --hyp hyp.scratch-high.yaml --batch 48 --project...