Welcome to the official implementation of ``SFCNet: Automated Non-Invasive Analysis of Motile Sperms Using Sperm Feature-Correlated Network''. This repository offers a robust toolkit designed for advanced tasks in deep learning and computer vision, specifically tailored for semantic segmentation and object detection. It supports features such as training progress visualization, logging, and calculation of standard metrics.
To install the SFCNet implementation, please follow the detailed instructions in INSTALL.md.
Please refer to DATA.md for guidelines on preparing the datasets for benchmarking and training.
Execute the training and evaluation processes using the configuration settings for segmentation in segmentation.sh and for detection in detection.sh script.
If you use this implementation in your research, please consider citing our paper as follows:
@ARTICLE{10542677,
author={Dai, Wei and Wu, Zixuan and Liu, Rui and Wu, Tianyi and Wang, Min and Zhou, Junxian and Zhang, Zhuoran and Liu, Jun},
journal={IEEE Transactions on Automation Science and Engineering},
title={Automated Non-Invasive Analysis of Motile Sperms Using Sperm Feature-Correlated Network},
year={2024},
volume={},
number={},
pages={1-11},
doi={10.1109/TASE.2024.3404488}
}