open-mmlab/mmrotate

Health v2 · maintenance only

Adoption not part of the score

2163 stars · 644 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MMRotate is an open-source PyTorch toolbox for rotated object detection, part of the OpenMMLab project. It provides modular components, multiple angle representations, strong baselines, and a model zoo of state-of-the-art rotated detection methods.

Use cases

• train rotated object detection models on aerial imagery
• detect oriented bounding boxes in remote sensing images
• benchmark rotated detection methods like RTMDet
• build custom rotated detection models from modular components
• run inference for oriented text or object detection

When to choose

• you need rotated/oriented bounding box detection with PyTorch
• you want pretrained model zoo baselines for aerial or remote-sensing detection
• you prefer modular OpenMMLab-style configuration for experiments

When to avoid

• you need standard axis-aligned object detection only (use MMDetection)
• you need a lightweight production inference service rather than a research toolbox
• you require active feature development, as the project is in maintenance mode

Facets

library · maturity maintenance

machine-learning computer-vision image-processing computer-vision deep-learning machine-learning python rotated-object-detection pytorch openmmlab object-detection model-zoo benchmark gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="open-mmlab/mmrotate")