How do I get the single most accurate foreground mask?

I want to use this script: python scripts/amg.py --checkpoint /home/joonwon/segment-anything/checkpoint/sam_vit_h_4b8939.pth --model-type vit_h
I want to get foreground mask for my 52 images, but when I run the existing code on my ubuntu anaconda, it generates too many masks and it is hard to combine them into one. How can I get the most accurate one mask per image?

Start by reading scripts/amg.py and running the reported command with the supplied checkpoint and vit_h model type on a representative image. Determine whether the requested single-mask behavior is an existing option or requires a defined change; done would mean a documented, reproducible way to produce one foreground mask per image with an accuracy criterion.

Written by the indexing model from the issue text.