segment-anything

The Segment Anything Model (SAM) produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a dataset of 11 million images and 1.1 billion masks, and has strong zero-shot performance on a variety of segmentation tasks.

More Information

For more information visit the segment-anything website.

Available Versions

These versions of segment-anything are available on the BEAR systems (BlueBEAR and BEAR Cloud VMs). These will be retained in accordance with our Applications Support and Retention Policy.

Version BEAR Apps Version
1.0-foss-2025b-CUDA-12.9.1 2025b