MobileSAM

Install

MobileSAM needs the sam extra: LibreYOLO's own weight download still goes through transformers' Hugging Face snapshot tooling, even though inference runs on a native, non-transformers decoder.

pip install "libreyolo[sam]"

Predict

LibreSAM(...) (or the family-specific LibreMobileSAM(...)) is a separate entry point from LibreYOLO(...): it returns a promptable segmenter rather than a detector, because a forward pass here is meaningless without a spatial prompt. There is no libreyolo predict CLI command for this family; use the Python API.

from libreyolo import LibreSAM, SAMPLE_IMAGE # MobileSAM has a single size, "tiny", so no other alias is needed.model = LibreSAM("mobilesam") # A point prompt: [x, y] in pixel coordinates, label 1 = foreground.result = model.predict(SAMPLE_IMAGE, points=[640, 420], labels=[1])print(result.masks.xy)      # polygon per maskprint(result.boxes.xyxy)    # tight box derived from the mask # A box prompt instead of a point.result = model.predict(SAMPLE_IMAGE, bboxes=[300, 200, 900, 700]) # No prompt at all segments the whole image (a simplified automatic# mask generator, not the exhaustive reference one).result = model.predict(SAMPLE_IMAGE)

from libreyolo import LibreMobileSAM, SAMPLE_IMAGE model = LibreMobileSAM() # The image encoder is the expensive part. set_image() runs it once;# every predict() call after that reuses the cached embedding.model.set_image(SAMPLE_IMAGE)a = model.predict(points=[640, 420], labels=[1])b = model.predict(bboxes=[300, 200, 900, 700])model.reset_image()

A point prompt accepts [x, y] for one object, [[x, y], ...] for several, or numpy arrays; labels marks each point 1 (foreground) or 0 (background) and defaults to all foreground. A box prompt takes [x1, y1, x2, y2] or a list of boxes, one mask per box. Omitting both prompts segments the whole image by prompting a dense grid and keeping the confident, non-overlapping masks; this "segment everything" mode is simplified against the reference automatic mask generator and can under-segment crowded scenes, so a real point or box prompt is the precise path. conf filters by predicted mask quality (IoU), not a detection confidence: pass 0.0 to keep every candidate. multimask=True returns all three of SAM's whole-versus-part ambiguity masks per prompt instead of the single best one. device= moves the model and, if a set_image() session is active, its cached embedding. Every mask carries class id 0, named "object", since a promptable mask has no fixed class set. train(), val(), export() and track() all raise NotImplementedError for this family: MobileSAM is predict-only in LibreYOLO. See prediction for source types.

Variants

One size, tiny, at a fixed 1024 px input: MobileSAM ships a single TinyViT encoder rather than the base/large/huge ladder SAM-1 offers.

Checkpoints

Every published weight file for this family.

Licensing

Citation

@article{mobile_sam,
  title={Faster Segment Anything: Towards Lightweight SAM for Mobile Applications},
  author={Zhang, Chaoning and Han, Dongshen and Qiao, Yu and Kim, Jung Uk and Bae, Sung-Ho and Lee, Seungkyu and Hong, Choong Seon},
  journal={arXiv preprint arXiv:2306.14289},
  year={2023}
}