recognize-anything icon indicating copy to clipboard operation
recognize-anything copied to clipboard

Published 20 hours ago • verified publisher icon xinyu1205

Why is the tag and Caption text predicted by Tag2Text different? Why didn't Tag2Text use specific tags given by user?

Open aabbc-cell opened this issue 10 months ago • 0 comments

只输入一张图像，Tag2Text生成的caption并没有用上它生成全部的tags？此外，当Tag2Text的输入是一张图像和几个specific tags的时候，它生成的caption可能也并不包含specific tags？

aabbc-cell avatar Apr 19 '24 11:04 aabbc-cell