yolo_v2_tiny(pretrained: bool = False, overrides: object = {})YOLOv2-Tiny — lightweight Darknet variant of YOLOv2.
Builds a compact YOLOv2 detector with a slimmer Darknet backbone
(no bottleneck stages); same anchor priors and detection head shape
as yolo_v2. Used as the speed-optimised reference variant
in the YOLO9000 release notes.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently ignored.
**overridesobject= {}Keyword overrides forwarded into
YOLOV2Config.Returns
YOLOV2ForObjectDetectionDetector with the YOLOv2-Tiny configuration applied (or with
overrides merged on top of it).
Notes
Lighter backbone alternative to yolo_v2; head topology is
unchanged.
Examples
>>> import lucid
>>> from lucid.models.vision.yolo._v2 import yolo_v2_tiny
>>> model = yolo_v2_tiny()
>>> x = lucid.randn(1, 3, 416, 416)
>>> out = model(x)
>>> out.logits.shape[0]
1