Connor Ye
Connor Ye
fix by in coco dataset category should follow the same order in the class_name in config file and category_id should start at 0
also add metainfo in train loader dataset and val too.Same issue mentioned.u can check it
Seem to handle REC task via YOLO-World?
Thanks a lot,it work. git checkout 4826695
@sqh85 https://github.com/AILab-CVC/YOLO-World/commit/4826695a84ce370dad7fe4cb555a6c7162f3751d dowanload and use the provided version
@mycfhs hello, may i ask that how to infer after train my own model,just use chat.py according to the guidance?
@mycfhs Thanks for the provided information.And I encounter the problem that "LisaModel" object has no attribute 'text_hidden_fcs' after running the chat.py.Did u have the same problem before?
labelme seems just to open format with itself labelme format,you can just view in text editor or use data_processing.py to see the vis version
@Zhaosoi Yes,u can just design one question for your text-label pair
Hello,have you encouter the val metrics are all 0.00 or nearly 0.00 when finetune groungingdino.I follow the official instruction of cat too,but in infer via image_demo.py it seem no problem.