IndUSV/Yolov8_SE_2

YOLOv8n Multi-Object Detector (Phone & Suitcase)

A fine-tuned YOLOv8 Nano (YOLOv8n) model capable of detecting mobile phones and suitcases in images. The model has been trained and validated on custom datasets with diverse backgrounds, lighting conditions, and object orientations.

Model Details

• Base Model: YOLOv8n (Nano)
• Task: Object Detection
• Supported Classes:
  • mobile_phone
  • suitcase
• Number of Classes: 2
• Input Resolution: 640 × 640
• Framework: Ultralytics YOLO
• Training Date: 2026-02-06

Capabilities

This model can:

• Detect mobile phones in real-world scenes
• Detect suitcases / luggage in travel and indoor environments
• Handle multiple objects per image
• Perform robustly under varied lighting and viewpoints

Training Details

• Image Size: 640
• Optimizer: Default YOLOv8 optimizer
• Augmentations: YOLOv8 default augmentations
• Device: NVIDIA GPU
• Training Strategy: Transfer learning from YOLOv8n

Dataset Information

The model was trained using curated datasets containing:

• Mobile phone images with bounding-box annotations
• Suitcase / luggage images with bounding-box annotations
• Real-world indoor and outdoor scenes
• Multiple object instances per image

Dataset annotations follow object-detection standards compatible with YOLO training pipelines.

Evaluation & Metrics

• Quantitative evaluation metrics are available in results.csv
• Qualitative predictions can be seen in validation images from the training run

Files in This Repository

• Yolov8_SE_2.pt – Trained YOLOv8 model weights
• args.yaml – Training configuration
• results.csv – Training and validation metrics

License

This model is released under the MIT License.

Acknowledgements

• Ultralytics YOLOv8: https://github.com/ultralytics/ultralytics
• Training datasets sourced and curated for object detection research