sam-small / README.md
Tony Neel
add test endpoints and make handler work
bf7dfcc
metadata
license: apache-2.0
pipeline_tag: mask-generation
library_name: sam2

Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and videos from FAIR. See the SAM 2 paper for more information.

The official code is publicly release in this repo.

SAM2 Small Inference Endpoint

This repository contains the code for running SAM2 (Segment Anything Model 2) small model as a Hugging Face inference endpoint.

Model Details

  • Model: SAM2 Hiera Small
  • Source: facebook/sam2-hiera-small
  • Type: Segmentation model

Usage

Send a POST request with an image to get segmentation masks:

For image prediction:

import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor

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

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

For video prediction:

import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor

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

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):
        ...

Refer to the demo notebooks for details.

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}
}