Thanks for sharing your wonderful work. I notice that Vary toy supports object detection. Could I give the same object dection promt to Vary and get the detection results?
No, the vision vocabulary of Vary does not train on the object detection dataset. Maybe you can extract the corresponding weights of Vary-toy for Vary to realize it.
Thanks for sharing your wonderful work. I notice that Vary toy supports object detection. Could I give the same object dection promt to Vary and get the detection results?