open-mmlab/mmdetection

Health v2 · maintenance only

Adoption not part of the score

32892 stars · 9819 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

MMDetection is OpenMMLab's PyTorch-based toolbox and benchmark for object detection and instance/panoptic segmentation. It provides a large model zoo (Faster R-CNN, Mask R-CNN, YOLO, DETR, RTMDet, DINO and more), config-driven training, and inference tooling.

Use cases

• train a custom object detection model on my own dataset
• run inference with pretrained Mask R-CNN or YOLO models
• benchmark detection models on COCO
• do instance segmentation in PyTorch
• fine-tune a pretrained detector for my images
• compare Faster R-CNN vs DETR implementations

When to choose

• you need a mature, well-tested detection framework with a huge model zoo and reproducible benchmarks
• you want config-driven training/evaluation with modular customization of models, datasets, and pipelines
• you need state-of-the-art detectors (RTMDet, DINO, Co-DETR) with pretrained weights

When to avoid

• you want a lightweight, minimal detector for edge deployment without heavy dependencies
• you prefer simple single-file training scripts over config-based frameworks
• you need non-PyTorch backends or very new research code not yet ported to MMDetection 3.x

Facets

library · maturity stable

machine-learning computer-vision image-processing benchmarking computer-vision deep-learning machine-learning artificial-intelligence python cross-platform object-detection instance-segmentation pytorch model-zoo mask-rcnn yolo detr panoptic-segmentation openmmlab linux gpu

Member repositories

For agents

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