add caption with grounding tasks

#3
by leoxiaobin - opened

Add new combined tasks (caption + phrase grounding)

leoxiaobin changed pull request status to open

Can we create a seperate gr.Tab(label="Florence-2 Combined Tasks") for it? Because the list is going bigger and most people want to click Object Detection directly after captioning.

hi @gokaygokay , thank you for the suggestion. I have made some changes to the code. I added a radio to select the task type (single task or cascaded task).

Thanks, this looks perfect.

gokaygokay changed pull request status to merged
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment