Rafael Padilla

It would be very useful for all community if the training code is provided. We all appreciate that.

I am using the same model (`r50-FPN-1x_classsampling_TSD.py` and `r50-FPN-1x_classsampling_TSD.pth`) and having the same error: "TypeError: __init__() got an unexpected keyword argument 'bbox_roi_extractor'" Any suggestion?

Yep, we intend to integrate to `evaluate` library. Meanwhile you can use from here https://huggingface.co/spaces/rafaelpadilla/detection_metrics **Update**: the code with the `evaluate` AP metric and its variations was transferred to https://huggingface.co/spaces/hf-vision/detection_metrics

Hi @EduardoPach , Are you referring to `groundingdino_swinb_cogcoor.pth` and `groundingdino_swint_ogc.pth`, placed [here](https://huggingface.co/ShilongLiu/GroundingDINO/tree/main), right? In this case, let's consult @ArthurZucker and @younesbelkada.

> > Hi @EduardoPach , > > Are you referring to `groundingdino_swinb_cogcoor.pth` and `groundingdino_swint_ogc.pth`, placed [here](https://huggingface.co/ShilongLiu/GroundingDINO/tree/main), right? > > In this case, let's consult @ArthurZucker and @younesbelkada. > > Precisely,...

Hi @EduardoPach , If your `ImageProcessor` is an exact copy from another model you must include the `#Copied from`. If somehow your `ImageProcessor` uses parts of other code, it would...

Investigating this issue and the proposed example, I found that the resulting image produced by HF is shifted up in 1 pixel in comparison to the transformation used by OpenAI...

Hi @UmarIgan Thank you for bringing this to our attention! I've tested your code and indeed, I've encountered the same error. I'm on it and will work towards a solution.