We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning. MMRotate implements 18 state-of-the-art algorithms and supports the three most frequently used angle definition methods. To facilitate future research and industrial applications of rotated object detection-related problems, we also provide a large number of trained models and detailed benchmarks to give insights into the performance of rotated object detection. MMRotate is publicly released at https://github.com/open-mmlab/mmrotate.
@article{arxiv.2204.13317,
title = {MMRotate: A Rotated Object Detection Benchmark using PyTorch},
author = {Yue Zhou and Xue Yang and Gefan Zhang and Jiabao Wang and Yanyi Liu and Liping Hou and Xue Jiang and Xingzhao Liu and Junchi Yan and Chengqi Lyu and Wenwei Zhang and Kai Chen},
journal= {arXiv preprint arXiv:2204.13317},
year = {2022}
}
Comments
5 pages, 2 tables, MMRotate is accepted by ACM MM 2022 (OS Track). Yue Zhou and Xue Yang provided equal contribution. The code is publicly released at https://github.com/open-mmlab/mmrotate