Coreml Sam2.1 Tiny

🚀 SAM 2.1 Tiny Core ML

SAM 2 (Segment Anything in Images and Videos) is a set of foundation models from FAIR, designed to address promptable visual segmentation in images and videos. This Core ML version of SAM 2.1 Tiny is suitable for the SAM2 Studio demo app.

🚀 Quick Start

SAM 2 (Segment Anything in Images and Videos) consists of a series of foundation models developed by FAIR. These models are dedicated to solving the problem of promptable visual segmentation in both images and videos. For more in - depth information, please refer to the SAM 2 paper.

This particular version is the Core ML adaptation of SAM 2.1 Tiny. It is well - suited for use with the SAM2 Studio demo app. The conversion was carried out in float16 precision, utilizing this fork of the original code repository.

📦 Installation

Install huggingface-cli

brew install huggingface-cli

Download the model

huggingface-cli download --local-dir models apple/coreml-sam2.1-tiny

📄 License

This project is licensed under the Apache - 2.0 license.

📚 Documentation

Citation

To cite the paper, model, or software, please use the following BibTeX entry:

@article{ravi2024sam2,
  title={SAM 2: Segment Anything in Images and Videos},
  author={Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan - Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and R{\"a}dle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao - Yuan and Girshick, Ross and Doll{\'a}r, Piotr and Feichtenhofer, Christoph},
  journal={arXiv preprint arXiv:2408.00714},
  url={https://arxiv.org/abs/2408.00714},
  year={2024}
}