project

Ultralytics YOLO

Open-source training and inference package for the YOLO family of object detectors, whose optimizer builder groups parameters by type and shares one learning rate across groups.

Known aliases

Ultralytics

Relationships

No evidence-backed relationships are recorded.

Current clusters

build1 publisher

A 20x backbone-to-head learning rate gap only pays when the checkpoint solves a different task

A dev.to write-up gives DEIMv2's DINOv3 backbone 5e-6 and its decoder head 1e-4 while fine-tuning a face detector, then explains why a second detector from the same week kept one global learning rate.

Publishers:dev.to

Reality

Evidence40
Adoption45
Hype gap+12
Incentives20
Confidence55