Sam2.1 Hiera Tiny

許可協議：Apache-2.0
任務類型：掩碼生成
庫名稱：sam2

SAM 2（Segment Anything in Images and Videos）代碼庫，這是由FAIR研發的面向圖像和視頻可提示視覺分割的基礎模型。更多信息請參閱SAM 2論文。

官方代碼已在此代碼庫中公開發布。

使用方法

圖像預測：

import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor

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

with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
    predictor.set_image(<你的圖像>)
    masks, _, _ = predictor.predict(<輸入提示>)

視頻預測：

import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor

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

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

    # 添加新提示並立即獲取同一幀的輸出
    frame_idx, object_ids, masks = predictor.add_new_points_or_box(state, <你的提示>):

    # 傳播提示以獲取整個視頻中的掩碼片段
    for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
        ...

詳情請參考演示筆記本。

引用

如需引用論文、模型或軟件，請使用以下格式：

@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}
}