Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick
[Paper] [Project] [Demo] [Dataset] [Blog] [BibTeX]
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.
The code requires python>=3.8, as well as pytorch>=1.7 and torchvision>=0.8. Please follow the instructions here to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.
Install Segment Anything:
pip install git+https://github.com/facebookresearch/segment-anything.git
or clone the repository locally and install with
git clone git@github.com:facebookresearch/segment-anything.git
cd segment-anything; pip install -e .
The following optional dependencies are necessary for mask post-processing, saving masks in COCO format, the example notebooks, and exporting the model in ONNX format. jupyter is also required to run the example notebooks.
pip install opencv-python pycocotools matplotlib onnxruntime onnx
First download a model checkpoint. Then the model can be used in just a few lines to get masks from a given prompt:
from segment_anything import build_sam, SamPredictor
predictor = SamPredictor(build_sam(checkpoint="</path/to/model.pth>"))
predictor.set_image(<your_image>)
masks, _, _ = predictor.predict(<input_prompts>)
or generate masks for an entire image:
from segment_anything import build_sam, SamAutomaticMaskGenerator
mask_generator = SamAutomaticMaskGenerator(build_sam(checkpoint="</path/to/model.pth>"))
masks = mask_generator.generate(<your_image>)
Additionally, masks can be generated for images from the command line:
python scripts/amg.py --checkpoint <path/to/sam/checkpoint> --input <image_or_folder> --output <output_directory>
See the examples notebooks on using SAM with prompts and automatically generating masks for more details.
SAM's lightweight mask decoder can be exported to ONNX format so that it can be run in any environment that supports ONNX runtime, such as in-browser as showcased in the demo. Export the model with
python scripts/export_onnx_model.py --checkpoint <path/to/checkpoint> --output <path/to/output>
See the example notebook for details on how to combine image preprocessing via SAM's backbone with mask prediction using the ONNX model. It is recommended to use the latest stable version of PyTorch for ONNX export.
Three model versions of the model are available with different backbone sizes. These models can be instantiated by running
from segment_anything import sam_model_registry
sam = sam_model_registry["<name>"](checkpoint="<path/to/checkpoint>")
Click the links below to download the checkpoint for the corresponding model name. The default model in bold can also be instantiated with build_sam, as in the examples in Getting Started.
defaultorvit_h: ViT-H SAM model.vit_l: ViT-L SAM model.vit_b: ViT-B SAM model.
The model is licensed under the Apache 2.0 license.
See contributing and the code of conduct.
The Segment Anything project was made possible with the help of many contributors (alphabetical):
Aaron Adcock, Vaibhav Aggarwal, Morteza Behrooz, Cheng-Yang Fu, Ashley Gabriel, Ahuva Goldstand, Allen Goodman, Sumanth Gurram, Jiabo Hu, Somya Jain, Devansh Kukreja, Robert Kuo, Joshua Lane, Yanghao Li, Lilian Luong, Jitendra Malik, Mallika Malhotra, William Ngan, Omkar Parkhi, Nikhil Raina, Dirk Rowe, Neil Sejoor, Vanessa Stark, Bala Varadarajan, Bram Wasti, Zachary Winstrom
If you use SAM or SA-1B in your research, please use the following BibTeX entry.
@article{kirillov2023segany,
title={Segment Anything},
author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
journal={arXiv:2304.02643},
year={2023}
}