Add model card for YOLO26l WiderFace fine-tune

README.md

@@ -0,0 +1,98 @@
+---
+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.)