5,337
edits
No edit summary |
(→YOLO) |
||
Line 453: | Line 453: | ||
Some training tricks: They use Lrelu. They predict square root of height and width. They weigh bounding boxes containing objects 10x those which are empty in the loss function. | Some training tricks: They use Lrelu. They predict square root of height and width. They weigh bounding boxes containing objects 10x those which are empty in the loss function. | ||
===TextonBoost=== | |||
Shotton ''et al.'' <ref name="shotton2009texton"></ref> | |||
==Semantic Segmentation== | ==Semantic Segmentation== |