MattLiutt

> @rishabh-akridata I use the COCO dataset instead of LVIS dataset may I know if you tried training/finetuning based on your own dataset?

I also got the same issue but different jaxlib version

No, I searched a lot still no idea

Hi, may I know that if it's possible to run with onnxruntime instead of using optimum and obtaining model processor using HF pipeline? Also, I tried to export with Cuda...

Hi, thanks for the work! I also change a bit on load_model script, and it turns out ```TypeError: Owlv2ForObjectDetection.forward() got an unexpected keyword argument 'images'```. I managed to solved the...

Hi @VlSomers, I've checked both KPR and bpbreid and the [demo script](https://github.com/VlSomers/keypoint_promptable_reidentification/blob/main/demo.py). If let say I wanna have feature extraction, do I simply put random image for inference with bpbreid?...

@VlSomers Thanks for the reply! Does it mean that I only have to call the bpbreid model and then use [feature extraction function](https://github.com/VlSomers/bpbreid/blob/82c6f2a6f1f4be34d8612e2372cafde9b03bcaef/torchreid/models/bpbreid.py#L129) for getting the embedding? I simply refactor...

Thanks! I'm not working with @vipingautam1906, I just search related topics in the issue and trying to see if similar issues are solved. I'm trying to see how good the...

OK, so as long as the `external_parts_masks=None`, it should work right?

@VlSomers sorry to bother you again, as I've tried, is it always return `True` for visibility score if `external_parts_masks=None`? Like what you mentioned [here](https://github.com/VlSomers/bpbreid/issues/27#issuecomment-1766528026). I run the script to get...