The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Apache License 2.0
45.46k
stars
5.37k
forks
source link
[Help] How to restrict the number of predicted labels #404
I'm working on semantic segmentation with a limited number labels. I realize that whenever I use SAM on my data I have multiple labels being generated. Ideally, I would want to restrict the labels to say 3 or 4 labels.
I was wondering if anyone has figured out how to do this?
Hi all,
I'm working on semantic segmentation with a limited number labels. I realize that whenever I use SAM on my data I have multiple labels being generated. Ideally, I would want to restrict the labels to say 3 or 4 labels.
I was wondering if anyone has figured out how to do this?