hukaixuan19970627/yolov5_obb

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1947 stars · 427 forks observed · 2026-08-28

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

A PyTorch implementation of YOLOv5 extended for oriented (rotated) object detection using Circular Smooth Label (CSL) angle encoding. It provides training, validation, and inference for rotated bounding box detection, benchmarked on the DOTA aerial imagery dataset.

Use cases

• detect rotated objects in aerial images
• train a yolov5 model for oriented bounding box detection
• run rotated object detection on the DOTA dataset
• detect ships or vehicles at arbitrary angles in satellite imagery
• reproduce OBB mAP results on DOTA v1.0/v1.5/v2.0
• convert a horizontal detection model to rotation-aware detection

When to choose

• you need rotated/oriented bounding box detection built on the familiar YOLOv5 codebase
• you work with aerial or remote-sensing imagery like DOTA
• you want pretrained OBB checkpoints and DOTA evaluation tooling out of the box

When to avoid

• you only need standard axis-aligned object detection (use upstream ultralytics yolov5)
• you need actively maintained code or the latest YOLO versions
• you require a license more permissive than GPL-3.0
• you need production support or frequent updates

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning artificial-intelligence python cross-platform yolov5 oriented-object-detection rotated-bbox circular-smooth-label dota-dataset aerial-imagery object-detection gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hukaixuan19970627/yolov5_obb")