Open ash80 opened 1 year ago
Hi,
Thanks for your interest. The code now is not supporting it. We have a plan to release such a script later. Or. you can just generate the custom vocabulary with RegionCLIP tools and inplace the text embedding.
Thanks!
--Chuang
Hi,
Do you have this simple script now such that we could test the with our own images?
Does VLDet support a simple script where I supply an image and a vocabulary file (and possibly embeddings) and get the bounding boxes or segmentation mask as the output?