B.3: YOLO: image detection architectures: Difference between revisions
From Circular Twain - Reference Implementations Wiki
Jump to navigationJump to search
No edit summary |
No edit summary |
||
| Line 11: | Line 11: | ||
• '''Type''': ML Model | • '''Type''': ML Model | ||
• '''AI Breadth''': | • '''AI Breadth''': Deep Learning, Computer Vision | ||
• '''Learning Ability''': Supervised | • '''Learning Ability''': Supervised Learning | ||
• '''Related technologies''': Pytorch | • '''Related technologies''': Pytorch | ||
| Line 21: | Line 21: | ||
• '''Related to circularity and sustainability''': No | • '''Related to circularity and sustainability''': No | ||
• '''Audience''': | • '''Audience''': Manufacturers | ||
Revision as of 09:27, 27 December 2024
• Short Description: YOLOv5 is a family of compound-scaled object detection models trained on the COCO dataset, and includes simple functionality for Test Time Augmentation (TTA), model ensembling, hyperparameter evolution, and export to ONNX, CoreML and TFLite.
• Reference, URL: https://pytorch.org/hub/datvuthanh_hybridnets/
• Relevant Domain/Industry: WEEE & Battery
• Application in relevant Projects/Initiatives: N.A.
• Type: ML Model
• AI Breadth: Deep Learning, Computer Vision
• Learning Ability: Supervised Learning
• Related technologies: Pytorch
• License Information: MIT license (MIT)
• Related to circularity and sustainability: No
• Audience: Manufacturers
Go back to the AI portfolio of reference implementations
