Yolo v5

Category: model.detection.2d
Version: 1.0.0
UUID: a7f08e573370cc42366f0bfe25475f455fb6c44c15f186cdb67fdbcde433860c
Execution context: leip_af
Choice Priority: 0.5

Subcomponent Parameters

Name	Synonyms	Allowable Categories
Optimizer	optimization.optimizer	optimization.optimizer.generic
Scheduler	optimization.scheduler	optimization.scheduler.generic

Value Parameters

Name	Synonyms	Type	Values
Input Height	model.input.height	scalar	int, min: 1
Input Width	model.input.width	scalar	int, min: 1
Model Architecture	model.variation, model.backbone, model.architecture	choice	yolov5n (Nano@640) yolov5n6 (Nano@1280) yolov5s (Small@640) yolov5s6 (Small@1280) yolov5m (Medium@640) yolov5m6 (Medium@1280) yolov5l (Large@640) yolov5ts (Transformer-Small@640)
Use Pretrained Backbone	model.use_pretrained, model.backbone.use_pretrained	scalar	bool
Prediction Confidence Threshold	post_processor.confidence, post_processor.confidence_threshold	scalar	float, min: 0.0, max: 1.0, step: 0.05

Constraints

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

This component fits into

Name	UUID	Synonyms
Full Recipe	4511dd...	model