language:
- en
license: agpl-3.0
library_name: ultralytics
tags:
- ultralytics
- yolo
- yolo26
- object-detection
- face-detection
- widerface
pipeline_tag: object-detection
YOLO26l face detector (WiderFace fine-tune)
Single-class face detector based on Ultralytics YOLO26l, fine-tuned on WIDER FACE.
This repo contains the Ultralytics best.pt checkpoint from a supervised fine-tune of the official YOLO26 large detection model.
Base model: YOLO26 documentation · Ultralytics GitHub
Dataset: WIDER FACE
Files
| File | Description |
|---|---|
best.pt |
Ultralytics YOLO weights (ultralytics.YOLO) |
metrics.txt |
Snapshot of peak validation metrics from this run |
Quick start
pip install ultralytics
huggingface-cli download uralman/yolo26l-widerface best.pt --local-dir .
from ultralytics import YOLO
model = YOLO("best.pt")
results = model.predict("image.jpg", imgsz=1280, conf=0.25)
Recommended inference size: 1280 (same as training).
Training summary
| Item | Value |
|---|---|
| Base weights | Ultralytics yolo26l.pt |
| Task | detect, single class face |
| Dataset | WIDER FACE converted to YOLO format (~12.9k train / ~3.2k val) |
| Image size | 1280 |
| Hardware | 2× NVIDIA H100, DDP |
| Batch | 8, AMP, cache=ram |
| Schedule | up to 200 epochs, patience 50, cosine LR |
| Augmentations | mosaic, multi-scale, Ultralytics detect defaults |
| Stopped at | epoch 73 (early stop; gains near plateau) |
Validation metrics (WIDER FACE val)
Ultralytics built-in box metrics on the YOLO-formatted WIDER FACE validation split used for this run. Peak selected by mAP50-95:
| Metric | Epoch 1 | Best (epoch 71) |
|---|---|---|
| Precision | — | 0.896 |
| Recall | — | 0.725 |
| mAP50 | 0.699 | 0.801 |
| mAP50-95 | 0.331 | 0.455 |
These are COCO-style Ultralytics mAP scores for this training setup — not the official WIDER FACE Easy/Medium/Hard evaluation protocol. Useful for reproducing this run; absolute numbers depend on label conversion, imgsz, and NMS.
Experiment notes (ClearML)
Training was logged in ClearML (project yolo-face). Highlights from the run:
- Val mAP50 rose from ~0.70 → ~0.80 and mAP50-95 from ~0.33 → ~0.455 over ~70 epochs
- Precision / recall at best checkpoint ≈ 0.90 / 0.72
- Stable epoch time ≈ 6.5–7 min on 2×H100 at batch 8 / imgsz 1280
- Train & val box/cls losses plus per-epoch detection metrics were tracked throughout; DDP job with additional train-batch scalars for monitoring
Intended use
- Face detection (boxes) for privacy blur or similar downstream pipelines
- Benchmarking YOLO26-scale face detectors on WIDER FACE-style data
Limitations
- Domain shift is expected outside WIDER FACE-like photos (extreme motion blur, unusual viewpoints, etc.)
- Not a face recognition / re-identification model
- Ultralytics stack is AGPL-3.0 — review license terms before commercial redistribution
Acknowledgements
- Ultralytics YOLO26
- WIDER FACE (Yang et al.)