MMRotate: A Rotated Object Detection Benchmark using PyTorch

TL;DR

MMRotate is an open-source PyTorch toolbox that standardizes training, inference, and evaluation for rotated object detection, supporting multiple algorithms and angle definitions, with extensive benchmarks and pretrained models.

Contribution

It introduces a comprehensive framework for rotated object detection, integrating 18 algorithms and supporting various angle definitions, facilitating research and industrial applications.

Findings

Supports 18 state-of-the-art algorithms

Provides extensive benchmarks and pretrained models

Facilitates research in rotated object detection

Abstract

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.