Felldude/Yolo11_NSFW_Custom_Nano

Full Custom YOLO Detection Model

Model Description

This model is a custom-trained YOLO object detection model for multi-class detection tasks on a specialized dataset.

It is trained for fine-grained object detection using bounding box annotations across multiple visual anatomy classes.

---

Intended Use

• Object detection on custom anatomical datasets
• Bounding box classification for fine-grained region detection

---

Limitations

• Trained on a custom manually annotated dataset across 7 classes
• Performance may degrade on unseen domains or different distributions
• Evaluation is based on a controlled dataset of ~50 images

---

Evaluation Results

Overall Metrics

• Precision: 0.971
• Recall: 0.913
• mAP@50: 0.958
• mAP@50-95: 0.668

---

Per-Class Results

Class	Images	Instances	Precision	Recall	mAP50	mAP50-95
all	50	253	0.971	0.913	0.958	0.668
face	41	49	0.939	0.980	0.979	0.818
nipple	33	64	0.967	0.913	0.957	0.707
mouth	41	50	0.996	1.000	0.995	0.659
eyes	41	49	0.991	0.898	0.985	0.731
navel	28	30	0.943	0.867	0.964	0.567
anus	11	11	0.988	0.818	0.865	0.526

---