AdamCodd/YOLOv11n-face-detection

YOLOv11n-Face-Detection

A lightweight face detection model based on YOLO architecture (YOLOv11 nano), trained for 225 epochs on the WIDERFACE dataset.

It achieves the following results on the evaluation set:

==================== Results ====================
Easy   Val AP: 0.9420471677096086
Medium Val AP: 0.9210357271019756
Hard   Val AP: 0.8099848364072022
=================================================

YOLO results:

Confusion matrix:

[[23577 2878]

[16098 0]]

Usage

from huggingface_hub import hf_hub_download
from ultralytics import YOLO

model_path = hf_hub_download(repo_id="AdamCodd/YOLOv11n-face-detection", filename="model.pt")
model = YOLO(model_path)

results = model.predict("/path/to/your/image", save=True) # saves the result in runs/detect/predict

Limitations

• Performance may vary in extreme lighting conditions
• Best suited for frontal and slightly angled faces
• Optimal performance for faces occupying >20 pixels