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).
1 project
·
1 city
Related technologies
Autoencoder
2
Computer Vision
28
Deep learning
15
Detectron2
1
Gaussian Mixture Model
1
Image Processing
8
Instance segmentation
2
Isolation Forest
1
K-Nearest Neighbors
1
Local Outlier Factor
1
Mask2Former
1
Mask R-CNN
1
MediaPipe
10
One-Class SVM
1
Panoptic FPN
1
Pose tracking
1
Principal Component Analysis
1
PyTorch
264
Recent Talks & Demos
Showing 1-1 of 1