Official implementation of our the paper:
Sparse Label Assignment for Oriented Object Detection in Aerial Images .
The code is very simple, just modify the parameters of the relevant shell files and then run it.
conda create -n sla python=3.6 -y source activate sla conda install pytorch=1.5 torchvision cudatoolkit=10.1 -c pytorch pip install -r requirement.txt sh compile.sh sh demo.sh - Put the dataset to the
datadirectory. - Prepare dateset via:
sh prepare.sh - Start training:
sh train.sh Conduct evaluation via:
sh test.sh If you find our work or code useful in your research, please consider citing:
@article{ming2021sparse, title={Sparse Label Assignment for Oriented Object Detection in Aerial Images}, author={Ming, Qi and Miao, Lingjuan and Zhou, Zhiqiang and Song, Junjie and Yang, Xue}, journal={Remote Sensing}, volume={13}, number={14}, pages={2664}, year={2021}, publisher={Multidisciplinary Digital Publishing Institute} }