Tokenizer decoder makes up class names during inference about open-groundingdino HOT 3 CLOSED

The reason for this situation is that the BERT tokenizer's vocabulary does not contain your label vocabulary, so BERT splits it into smaller subwords. In the official code, if you don't provide the ‘’token_spans‘’ parameter, it will directly match the label with all text tokens and output results in line 112 . You can consider using the ‘’token_spans‘’ parameter or follow our code's post-processing approach to treat the label as a whole and generate pos_maps in line 685.

from open-groundingdino.

Which inference function are you using? The appearance of this question seems to be due to BERT tokenization, which divides your text into smaller segments

from open-groundingdino.

I am following the suggestions in #17 and using the predict function from the official grounding dino implementation.

from open-groundingdino.