rf-sam-2

library1.0.3pypypi✓ verified 82d ago

Roboflow-maintained package for Meta's SAM 2 (Segment Anything Model 2) for image and video segmentation. Currently version 1.0.3, updated March 2025.

ai-ml

pip install rf-sam-2

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · RF-SAM-2

rf-sam-2

ai-mlpythonv1.0.3

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

GlobalHydra

✓ from sam2 import GlobalHydra

✗ from rf_sam_2 import SAM2

initialize_config_module

✓ from sam2 import initialize_config_module

✗ from rf_sam_2 import SAM2

Basic image segmentation with a single point prompt.

import torch from rf_sam_2 import SAM2 # Load model (set environment variable for API key if needed) model = SAM2.from_pretrained("sam2-hiera-large") # Predict with an image import cv2 image = cv2.imread("path/to/image.jpg") image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) with torch.inference_mode(): masks, scores, logits = model.predict(image, point_coords=[[500, 375]], point_labels=[1]) print(masks.shape, scores)

Debug

Known issues

breakingThe import path changed from 'sam2' to 'rf_sam_2' in version 1.0.0.

fix

Use 'from rf_sam_2 import SAM2' instead of 'from sam2 import SAM2'.

affects: >=1.0.0

deprecatedThe old 'segment_anything' API is not supported; use the new SAM2 classes.

fix

Replace 'sam_model_registry' with 'SAM2.from_pretrained()'.

affects: >=1.0.0

gotchaCPU inference requires setting environment variable 'SAM2_DEVICE=cpu' before import.

fix

os.environ['SAM2_DEVICE'] = 'cpu' before importing rf_sam_2.

affects: all

Upgrade

Version history

1.0.3latest on PyPI · released Feb 2, 2026

Audit

Dependencies

torchrequiredPyTorch backend required for model inference

opencv-pythonoptionalImage/video I/O utilities

Agent activity

7 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/roboflow/sam2 ↗

packagehttps://pypi.org/project/rf-sam-2/ ↗

homepagehttps://roboflow.com ↗