What I learned merging seven public datasets to train a single-class shelf detector
This story is from 2026-09-04. It is preserved in the archive; the latest stories are on the live feed.
The conclusion first: licence filtering matters more than dataset size when you plan to use the model commercially. I merged seven public Roboflow datasets into 11,667 images — all CC BY 4.0 — trained YOLO11n on Apple MPS, and reached mAP50 0.844 on a held-out test set of 277 images and 1,255 insta…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-09-04 10:05 · DEV Community — Machine Learning
What I learned merging seven public datasets to train a single-class shelf detector