---
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](https://docs.ultralytics.com/models/yolo26/)**, fine-tuned on **[WIDER FACE](http://shuoyang1213.me/WIDERFACE/)**.

This repo contains the Ultralytics `best.pt` checkpoint from a supervised fine-tune of the official YOLO26 large detection model.

> Base model: [YOLO26 documentation](https://docs.ultralytics.com/models/yolo26/) · [Ultralytics GitHub](https://github.com/ultralytics/ultralytics)  
> Dataset: [WIDER FACE](http://shuoyang1213.me/WIDERFACE/)

## Files

| File | Description |
|------|-------------|
| `best.pt` | Ultralytics YOLO weights (`ultralytics.YOLO`) |
| `metrics.txt` | Snapshot of peak validation metrics from this run |

## Quick start

```bash
pip install ultralytics
huggingface-cli download uralman/yolo26l-widerface best.pt --local-dir .
```

```python
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](https://www.ultralytics.com/license) before commercial redistribution

## Acknowledgements

- [Ultralytics YOLO26](https://docs.ultralytics.com/models/yolo26/)
- [WIDER FACE](http://shuoyang1213.me/WIDERFACE/) (Yang et al.)