Deploy with Roboflow

Segment Anything Model (SAM)

Segment Anything (SAM) is an image segmentation model developed by Meta Research, capable of doing zero-shot segmentation.

Try the Model

Use the widget below to experiment with Segment Anything Model (SAM). You can detect COCO classes such as people, vehicles, animals, household items.

Overview

Segment Anything, released in April 2023 by Meta Research, is an image segmentation computer vision model trained using a new dataset. The model itself is called Segment Anything Model (SAM). Using SAM, you can generate segmentation masks for all of the objects in an image that the model can find, or masks for objects that meet a provided text prompt.

SAM has strong zero-shot capabilities, meaning it can segment unrecognized objects without further training. This provides SAM with a large advantage over other segmentation models which may require fine-tuning for different uses.

The dataset on which SAM was trained contains over one billion image masks and 11 million images.

Segment Anything Model (SAM) License

Segment Anything Model (SAM)

is licensed under a

Apache-2.0

license.

Performance

Deploy a Segment Anything Model (SAM) API

You can use Roboflow Inference to deploy a

Segment Anything Model (SAM)

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with Segment Anything Model (SAM)

You can automatically label a dataset using Segment Anything Model (SAM) with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use Segment Anything Model (SAM) to train a computer vision model.

No items found.