smoking-detection-finetuned

Fine-tuned from Enos-123/smoking-detection (YOLOv11-Medium) using Ultralytics.

Classes

• cigarette

Dataset

• Source: xu-wei/cigarette-all (version 1)
• Images: 1613 train / 203 valid / 201 test
• Check the dataset page above for its license -- not necessarily the same as this repo's license field, which reflects the base model's license.

Training

Parameter	Value
Base checkpoint	Enos-123/smoking-detection
Epochs	100
Image size	640
Batch size	18
Optimizer	AdamW
Initial LR (lr0)	0.001
Patience (early stop)	20

Results (held-out validation split)

Metric	Value
mAP50	0.8698
mAP50-95	0.5886
Precision	0.9432
Recall	0.7957

Usage

from ultralytics import YOLO

model = YOLO("best.pt")
results = model.predict("image.jpg", conf=0.25)
for r in results:
    for box in r.boxes:
        print(model.names[int(box.cls[0])], float(box.conf[0]))