.

Technology

MMDetection

MMDetection is a PyTorch-based object detection toolbox supporting 300+ network schemas and 2,000+ pretrained models.

Developed by OpenMMLab, this framework streamlines the implementation of state-of-the-art algorithms like Mask R-CNN, YOLOv8, and Swin Transformer. It features a modular design where components (backbones, necks, and heads) are decoupled for rapid experimentation. Engineers leverage high-performance training on COCO and Cityscapes datasets to achieve competitive mAP scores with minimal configuration. The codebase integrates with the MMengine ecosystem to handle distributed training and mixed-precision optimization (FP16).

https://github.com/open-mmlab/mmdetection
1 project · 1 city

Related technologies

Recent Talks & Demos

Showing 1-1 of 1

Members-Only

Sign in to see who built these projects