Yolo v8¶

Category: model.detection.2d
Version: 1.1.0
UUID: ad1109b5c42607d3e8e1640a6d84c32c6143fb298c56384355f5e0d3e42c4933
Execution context: leip_af
Choice Priority: 0.7

Subcomponent Parameters¶

Name	Synonyms	Allowable Categories
Optimizer	`optimization.optimizer`	`optimization.optimizer.yolo`

Value Parameters¶

Name	Synonyms	Type	Values
Input Height	`model.input.height`	scalar	int, min: 1
Input Width	`model.input.width`	scalar	int, min: 1
Prediction Confidence Threshold	`post_processor.confidence`, `post_processor.confidence_threshold`	scalar	float, min: 0.0, max: 1.0, step: 0.05
Freeze Backbone	`model.backbone.freeze`	scalar	bool
IoU Threshold for NMS	`post_processor.iou_threshold`	scalar	float, min: 0.0, max: 1.0
Final learning rate	`optimization.scheduler.final_learning_rate`	scalar	float
Model Architecture	`model.variation`, `model.backbone`, `model.architecture`	choice	`yolov8n` (Nano) `yolov8s` (Small) `yolov8m` (Medium) `yolov8l` (Large) `yolov8x` (Extra Large) `yolov8x6` (Extra Large (with additional P6 output layer))
Use Pretrained Backbone	`model.use_pretrained`, `model.backbone.use_pretrained`	scalar	bool
Include decoding in Graph	`model.include_decoding`, `export.include_decoding`	scalar	bool

Constraints¶

Data for Yolo models should be normalized with 'yolo' (data.normalization == 'yolo')
Export can only be done by using traced model: export \(\in\) export.tracer

This component fits into¶

Name	UUID	Synonyms
Full Recipe	`4511dd...`	`model`