Segment Anything Python Packages

ultralytics

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

ultralytics-opencv-headless

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

osam

Get up and running with SAM1,2,3, EfficientSAM, YOLO-World, and other promptable vision models locally.

segment-geospatial

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

telekinesis-ai

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

anylabeling

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!

telekinesis-datatypes

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

keras-cv-attention-models

Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam

segment-anything-hq

Segment Anything in High Quality [NeurIPS 2023]

hbb2obb

🔄 Converts horizontal bounding boxes into oriented (rotated) boxes by prompting SAM-family models. Includes model ensembling, confidence scoring, evaluation, format conversion, and hyperparameter tuning.

telekinesis-dataengine

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

telekinesis-medulla

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

micro-sam

Segment Anything for Microscopy

telekinesis-iris

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

annolid

An annotation and instance segmentation-based multi-object tracking and behavior analysis package.

rankseg

Boost segmentation model mIoU/Dice instantly WITHOUT retraining. A plug-and-play, training-free optimization module. Published in NeurIPS & JMLR. Compatible with SAM, DeepLab, SegFormer, and more. 🧩

anylabeling-gpu

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!

telekinesis-applications

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

segment-anything-fast

Fast Segment Anything

garmentiq

Free & Open Source. Precise and flexible garment measurements from images - no tape measures, no delays, just fashion - forward automation.

isat-sam

Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

ultralytics-dev

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

sssegmentation

SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch.