# yformer/EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Repository: https://github.com/yformer/EfficientSAM
Canonical: https://ross.abutalabs.com/products/efficientsam
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2024-12-24T08:36:39+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1009, "days_push": 617, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2491, forks 163 (observed 2026-08-28T04:06:56.395259+00:00)

## What it is
EfficientSAM is an efficient image segmentation model that leverages masked image pretraining to provide a lightweight alternative to Meta's Segment Anything Model (SAM). It supports point-prompt, box-prompt, and segment-everything modes, with checkpoints, TorchScript, and ONNX exports available.

## Use cases
- segment objects in images with point or box prompts
- run a faster lighter alternative to Segment Anything
- export segmentation model to ONNX for deployment
- integrate AI-assisted segmentation into annotation tools like Labelme
- segment everything in an image automatically
- build grounded segmentation with text prompts

## When to choose
- you need SAM-like promptable segmentation with lower compute cost
- you want ONNX or TorchScript exports for production deployment
- you need a permissively licensed (Apache-2.0) segmentation model

## When to avoid
- you need video object tracking rather than image segmentation (see EfficientTAM)
- you require the absolute highest segmentation accuracy regardless of speed
- you need a turnkey GUI application rather than a model library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: segment-anything, image-segmentation, masked-image-pretraining, onnx, promptable-segmentation, sam, gpu

## Member repositories
- yformer/EfficientSAM (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.395259+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:27:48.124408+00:00, confidence not recorded.
  - readme: https://github.com/yformer/EfficientSAM (fetched 2026-08-28T04:06:56.395259+00:00, sha dfce0e185828)
- Data as of 2026-08-30T08:39:29.467469+00:00.