dimidagd
dimidagd
Can we merge by now? thanks
It is saying so for the product as well, which why I am just trying to correct. Reader might get confused
> @ZeonlungPun hi there, > > Thanks for bringing up the topic of Oriented Bounding Box (OBB) support for YOLOv8. It's great to see such enthusiasm and detailed use cases...
> @Badar-e-Alam Thank you Alam. I am doing continue pretraining on my custom dataset. May I have your Facebook Id, I want to chat with you. Hi @vanpersie32 can we...
> i too am strugling with this. is there any way we can use the pretrained weights without necessarily having to set `global_crop_size: 518` ? You can interpolate the checkpoint...
I have successfully used positional embeddings with linear interpolation and it works fine.On 28 Aug 2024, at 16.17, PMRS-lab ***@***.***> wrote: Same question here. Looks like it is possible to...
Hey, i have tried the approach of Benedikt et. al https://arxiv.org/pdf/2401.04720 I believe its a question of compute and data availability, as well as domain shift. You can probably get...
Second that, its very confusing.
Could you mean that it's not possible, because they did not provide the head **_weights_**?
This feature makes a lot of sense