Matthias
Matthias
@jartantupjar Thanks for your ideas. I will give that a try - but frankly, an automated solution would still be great ;-)
@iamarchisha Well, maybe it would, but I don't know - how can one integrate that with the `model_main_tf2.py` script?
@glenn-jocher Thanks your response. So in my case, if I would use the `rect` parameter, would that also mean I should provide both width and height for the `imgsz` parameter?
Hi, thanks for your feedback. Unfortunately we don't use GDScript any more, so at the moment there are no plans to update it here. But please feel free to make...
Not yet I wanted to ask first. Will drop you a line when I have tested it!
Frankly I haven't tested in yet - I have originally asked here because I didn't want to invest time only to find out that TF2 is not supported, so I...
> For anyone else following this discussion, here’s a quick recap: You can train a classification model by directly specifying the path to your dataset directory, as shown in the...
@glenn-jocher Unfortunately, that doesn't work either, as `nc` is not a valid argument to `train()`: ``` $ python yolo_trainer.py Traceback (most recent call last): File "/data/python/cvserver/training/9d27af44-fd16-3df6-e4fd-fabc9d8aa387/yolo_trainer.py", line 4, in model.train(...
@glenn-jocher Thanks, but I don't have such a yaml file for my model. I simply use `model = YOLO("yolov8n-cls.pt")`, as shown above. Do I have to use a `model.yaml` file,...
@glenn-jocher Thanks for your resoponse. But how can I select the `yolo*-cls` model that should be used for training that way?