CPU compatible fork of the official SAMv2 implementation.

Features 🚀

• CPU compatible
• ships with config files
• Run image and video inference on CPUs
• Example notebooks showcasing inference using weights and biases.

Installation

You can download it from pypi using pip as follows:

pip install samv2

or from the repository:

pip install git+https://github.com/SauravMaheshkar/samv2.git

Usage

After downloading the official weights, you can use the load_model() helper method to instantiate a model.

from sam2 import load_model

model = load_model(
    variant="tiny",
    ckpt_path="artifacts/sam2_hiera_tiny.pt",
    device="cpu"
)

• Example Notebook to run prompted segmentation on images logging predictions as W&B Tables.
• Example Notebook to run automatic segmentation on images logging predictions as W&B Tables.

Citation

@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},
  year={2024}
}