Semantic-Segment-Anything icon indicating copy to clipboard operation
Semantic-Segment-Anything copied to clipboard

Published 20 hours ago • verified publisher icon fudan-zvg

Apply SSA on a single Image

Open marcomiglionico94 opened this issue 2 years ago • 3 comments

Hi, I was thinking if it is possible to have a single image as input, apply the Segment Anything Model from Meta and the use this tool to get the actual labels for the predicted masks

marcomiglionico94 avatar Apr 10 '23 16:04 marcomiglionico94

Yes, this is exactly the function of SSA. To achieve this, first get the json file of the image masks with SAM, and put the image and image mask json file according to the data folder sturcture shown in the SSA repository, and then run SSA.

Jiaqi-Chen-00 avatar Apr 11 '23 05:04 Jiaqi-Chen-00

Hi, does a single Image work? like, applying this SSA on other datasets if we don't obtain the JSON files?

PoopBear1 avatar Apr 12 '23 06:04 PoopBear1

you can try the demo here https://replicate.com/cjwbw/semantic-segment-anything

chenxwh avatar Apr 14 '23 09:04 chenxwh