data

YOLOV1Config

extendsModelConfig

YOLOV1Config(num_classes: int = 80, in_channels: int = 3, split_size: int = 7, num_boxes: int = 2, lambda_coord: float = 5.0, lambda_noobj: float = 0.5, score_thresh: float = 0.5, nms_thresh: float = 0.5, tiny: bool = False)

source edit

Configuration for YOLOv1 (Redmon et al., CVPR 2016).

Parameters

num_classesint= 80

Number of object classes C (COCO default: 80).

in_channelsint= 3

Input image channels.

split_sizeint= 7

Grid cells per side S (default 7 → 7×7 grid).

num_boxesint= 2

Bounding boxes predicted per cell B (default 2).

lambda_coordfloat= 5.0

Up-weighting factor for box coordinate loss.

lambda_noobjfloat= 0.5

Down-weighting factor for no-object confidence loss.

score_threshfloat= 0.5

Minimum class-confidence score at inference.

nms_threshfloat= 0.5

IoU threshold for NMS.

tinybool= False

Use the tiny Darknet backbone instead of the full one.

Used by 1

lucid.models.vision.yolo

Constructors

dunder

init

→None

__init__(num_classes: int = 80, in_channels: int = 3, split_size: int = 7, num_boxes: int = 2, lambda_coord: float = 5.0, lambda_noobj: float = 0.5, score_thresh: float = 0.5, nms_thresh: float = 0.5, tiny: bool = False)

source edit

data

YOLOV1Config

extendsModelConfig

YOLOV1Config(num_classes: int = 80, in_channels: int = 3, split_size: int = 7, num_boxes: int = 2, lambda_coord: float = 5.0, lambda_noobj: float = 0.5, score_thresh: float = 0.5, nms_thresh: float = 0.5, tiny: bool = False)

source edit

Configuration for YOLOv1 (Redmon et al., CVPR 2016).

Parameters

num_classesint= 80

Number of object classes C (COCO default: 80).

in_channelsint= 3

Input image channels.

split_sizeint= 7

Grid cells per side S (default 7 → 7×7 grid).

num_boxesint= 2

Bounding boxes predicted per cell B (default 2).

lambda_coordfloat= 5.0

Up-weighting factor for box coordinate loss.

lambda_noobjfloat= 0.5

Down-weighting factor for no-object confidence loss.

score_threshfloat= 0.5

Minimum class-confidence score at inference.

nms_threshfloat= 0.5

IoU threshold for NMS.

tinybool= False

Use the tiny Darknet backbone instead of the full one.

Used by 1

lucid.models.vision.yolo

Constructors

dunder

init

→None

__init__(num_classes: int = 80, in_channels: int = 3, split_size: int = 7, num_boxes: int = 2, lambda_coord: float = 5.0, lambda_noobj: float = 0.5, score_thresh: float = 0.5, nms_thresh: float = 0.5, tiny: bool = False)

source edit