GroundingDINO
GroundingDINO copied to clipboard
questions about zero-shot detection
I tried to apply grounded dino on my custom data. However, I am confused about how to input the text or class names? I notice that you take 'dog.stick.' as input in the example in ReadMe. However, if I do not know what object is in the image, should I input all the possible class names as text?