Results Are Diffuse or Short – Missing Configuration for Detailed Output?
ClingDing-F opened this issue · 1 comments
I've been trying to use the project to generate answers to a specific prompt on some medical images, but I’ve noticed that the answers always seem to be 'diffuse' or just short descriptions. I would expect the results to be in a format similar to the provided dataset or as shown in the paper. Could the author clarify if there is some configuration I missed?
Dear @ClingDing-F,
I apologize for the delayed response, as I was in Milan attending ECCV over the past few days. Regarding your query, could you confirm if you are using our Captioner model to generate the answers? If so, were you using the prompt provided in our setup? It would be helpful to have a bit more detail to assist you better.
Thank you for reaching out, and I look forward to your reply.