Skip to content

Latest commit

 

History

History
60 lines (39 loc) · 1.62 KB

README.md

File metadata and controls

60 lines (39 loc) · 1.62 KB

RASNet: Segmentation for Tracking Surgical Instruments in Surgical Videos Using Refined Attention Segmentation Network (arXiv)

NOTE - Unofficial PyTorch implementation of RASNet

Sample Data

Download from [Dataset Link] and place it inside the repository root and unzip. To train the model, download the Endovis 17/18 dataset from here and set the root directory in main.py

Usage (Training and Validation)

python3 main.py

Dependencies

This code was developed with python3.6

Python (3.6.x)
PyTorch (1.7.x)
CUDA (10.2)
cuDNN (7.6.5)
numpy (1.19.5)

For further details, contact Sai Mitheran via Linkedin, or via email by clicking the icon below.

To cite the original paper

@misc{ni2019rasnet,
      title={RASNet: Segmentation for Tracking Surgical Instruments in Surgical Videos Using Refined Attention Segmentation Network}, 
      author={Zhen-Liang Ni and Gui-Bin Bian and Xiao-Liang Xie and Zeng-Guang Hou and Xiao-Hu Zhou and Yan-Jie Zhou},
      year={2019},
      eprint={1905.08663},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}