yolo_v1_tiny(pretrained: bool = False, overrides: object = {})YOLOv1-Tiny with reduced Darknet backbone (Redmon et al., CVPR 2016).
Builds the lightweight variant explicitly described in the YOLOv1 paper alongside the full model: 9-layer Darknet-Tiny backbone with the same 7x7 grid and 2 boxes per cell. Approximately 45M parameters and 52.7% mAP on VOC 2007 at 155 fps (paper Table 1) — trades accuracy for speed.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently ignored.
**overridesobject= {}Keyword overrides forwarded into
YOLOV1Config.Returns
YOLOV1ForObjectDetectionDetector with the YOLOv1-Tiny configuration applied (or with
overrides merged on top of it).
Notes
See Redmon et al., "You Only Look Once: Unified, Real-Time Object Detection", CVPR 2016 (arXiv:1506.02640). The tiny variant uses fewer / shallower conv stages but keeps the same FC head topology.
Examples
>>> import lucid
>>> from lucid.models.vision.yolo._v1 import yolo_v1_tiny
>>> model = yolo_v1_tiny()
>>> x = lucid.randn(1, 3, 448, 448)
>>> out = model(x)
>>> out.logits.shape[0]
1