LibreSAM Promptable Segmentation
Collection
Promptable segmentation (LibreSAM tier): point and box prompts, encode once and prompt many. Image inference; video is out of scope in v1. • 7 items • Updated
LibreMobileSAM
LibreMobileSAM is the MobileSAM TinyViT checkpoint converted to LibreYOLO's
native checkpoint schema for the LibreSAM promptable segmentation tier.
Files
LibreMobileSAM.pt: LibreYOLO schema-wrapped PyTorch checkpoint.LICENSE: Apache-2.0 license text.NOTICE: upstream MobileSAM and TinyViT attribution.
Usage
from libreyolo import LibreMobileSAM
model = LibreMobileSAM()
results = model("image.jpg", points=[[[500, 375]]], labels=[[1]])
Metadata
- Model family:
mobilesam - Size:
tiny - Task:
segment - Input size:
1024 - Checkpoint schema: LibreYOLO v1.0
This checkpoint is intended for LibreYOLO's promptable segmentation API. It is
not loaded through the LibreYOLO() detector factory.