Sam2.1 Hiera Large

🚀 SAM 2: Segment Anything in Images and Videos

This repository is for SAM 2, a foundation model developed by FAIR to solve promptable visual segmentation in images and videos. For more information, please refer to the SAM 2 paper.

The official code is publicly released in this repo.

🚀 Quick Start

✨ Features

• Capable of performing promptable visual segmentation in both images and videos.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

Image Prediction

import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor

predictor = SAM2ImagePredictor.from_pretrained("facebook/sam2-hiera-large")

with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
    predictor.set_image(<your_image>)
    masks, _, _ = predictor.predict(<input_prompts>)

Video Prediction

import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor

predictor = SAM2VideoPredictor.from_pretrained("facebook/sam2-hiera-large")

with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
    state = predictor.init_state(<your_video>)

    # add new prompts and instantly get the output on the same frame
    frame_idx, object_ids, masks = predictor.add_new_points_or_box(state, <your_prompts>):

    # propagate the prompts to get masklets throughout the video
    for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
        ...

For more details, refer to the demo notebooks.

📚 Documentation

No detailed documentation other than the usage examples is provided in the original document, so this section is skipped.

🔧 Technical Details

No technical details are provided in the original document, so this section is skipped.

📄 License

The project is licensed under the Apache-2.0 license.

Citation

To cite the paper, model, or software, please use the below:

@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}
}