You can deploy this model and start earning money today!

basant18/
Smoking-detection-YOLO26s

Name: Smoking-detection-YOLO26s
Availability: InStock

apache-2.0

Views

No views yet

🚬 Smoking Detection — YOLOv8s

A fine-tuned YOLOv8s object detection model trained to detect cigarettes in images and video streams. Designed for real-world deployment with crash-resilient training and automatic checkpoint uploads to Hugging Face.

📊 Model Performance

YOLO Validation Metrics

Metric	Score
mAP@50	0.8796
mAP@50-95	0.5198
Precision	0.9261
Recall	0.8814
F1 Score	0.9032

Image-Level Classification Report (307 validation images)

Class	Precision	Recall	F1-Score	Support
No Cigarette	0.8108	0.9677	0.8824	31
Cigarette	0.9963	0.9746	0.9853	276
Accuracy			0.9739	307
Macro Avg	0.9036	0.9712	0.9339	307
Weighted Avg	0.9776	0.9739	0.9749	307

Model Evaluation Metrics

Confusion Matrix Summary

	Predicted: No Cigarette	Predicted: Cigarette
True: No Cigarette	30 (96.77%)	1 (3.23%)
True: Cigarette	7 (2.54%)	269 (97.46%)

🏗️ Training Setup

Dataset

Source: Roboflow — pro-hiyaw / cigarettes-reality-2-trnm2 (Version 1)
Format: YOLOv8 (yolo26)

Model

Base weights: yolo26s.pt
Architecture: YOLOv8 Small

Hyperparameters

Parameter	Value
Epochs	200
Image size	800
Batch size	16
Device	GPU 0
Patience (early stopping)	30

Data Augmentation

Augmentation	Value
HSV Saturation (`hsv_s`)	0.2
HSV Value / Exposure (`hsv_v`)	0.2
Rotation (`degrees`)	±10°
Horizontal Flip (`fliplr`)	0.5

🔄 Crash-Resilient Training

The training pipeline includes automatic crash recovery:

At the end of every epoch, a training_status.json file is written with the current epoch, path to last.pt, and path to best.pt.
On restart, if a status file is found with "status": "training", training automatically resumes from the last saved weights.
Every 10 epochs, checkpoints are uploaded to Hugging Face:
- weights/epoch_{N}_last.pt — rolling checkpoint
- weights/best.pt — best model so far (overwritten each time)
- training_status.json — current training state

🤗 Hugging Face Integration

Model checkpoints are automatically uploaded to a private Hugging Face repository during training.

Repo: <your-username>/Smoking-detection-YOLO26s
Visibility: Private
Upload frequency: Every 10 epochs

Authentication uses a Hugging Face token stored as a Kaggle secret (HF_TOKEN).

🚀 Quick Start

Install Dependencies

pip install ultralytics roboflow huggingface_hub opencv-python

Run Inference

python

from ultralytics import YOLO

model = YOLO("weights/best.pt")
results = model.predict(source="your_image.jpg", imgsz=800, conf=0.5)
results[0].show()

Resume Training

Simply re-run the training script. If training_status.json exists and points to valid weights, training will resume automatically from the last checkpoint.

📁 Project Structure

.
├── training_status.json        # Auto-generated crash recovery state
├── runs/
│   └── detect/
│       └── train/
│           └── weights/
│               ├── best.pt     # Best checkpoint
│               └── last.pt     # Latest checkpoint
└── <dataset>/
    └── data.yaml               # Dataset config (auto-downloaded from Roboflow)

🔐 Required Secrets (Kaggle)

Secret Name	Description
`HF_TOKEN`	Hugging Face API token
`RF`	Roboflow API key

📄 License

This project is for research and educational purposes. Dataset sourced from Roboflow Universe under its respective license.

basant18/Smoking-detection-YOLO26s