XetHub hosted fork of EfficientSAM using the GitHub plugin.
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
[Dec.5 2023] We release the torchscript version of EfficientSAM and share the Google colab notebook.
Online demo and examples can be found in the project page.
The model files live in this repo itself:
- EfficientSAM-S:models/efficientsam_s_gpu.jit
- EfficientSAM-Ti: models/efficientsam_ti_gpu.jit
Instructions
-
Install the git-xet extension.
-
Clone the repo:
# Using SSH
git clone git@github.com:xetdata/EfficientSAM.git
cd EfficientSAM/
- Activate your Python virtual environment and install the requirements:
pip install -r requirements.txt
- Start Jupyter Notebook:
# jupyter lab
jupyter lab
# jupyter notebook
jupyter notebook
- You can directly use EfficientSAM:
import torch
efficientsam = torch.jit.load(models/efficientsam_s_gpu.jit)
You can also use this Google Colab notebook
If you're using EfficientSAM in your research or applications, please cite using this BibTeX:
@article{xiong2023efficientsam,
title={EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything},
author={Yunyang Xiong, Bala Varadarajan, Lemeng Wu, Xiaoyu Xiang, Fanyi Xiao, Chenchen Zhu, Xiaoliang Dai, Dilin Wang, Fei Sun, Forrest Iandola, Raghuraman Krishnamoorthi, Vikas Chandra},
journal={arXiv:2312.00863},
year={2023}
}