Litter Detection Model (YOLOv8)

This model detects plastic litter (bags and bottles) in images using YOLOv8.

Model Description

• Base Model: yolov8n.pt
• Task: Object Detection
• Classes: Litter
• Framework: PyTorch + Ultralytics YOLO

Training Details

Usage

Install Dependencies

pip install ultralytics huggingface_hub

Download and Use Model

from ultralytics import YOLO
from huggingface_hub import hf_hub_download

# Download model
model_path = hf_hub_download(
    repo_id="esapzoi/litter-detection-yolov8", 
    filename="best.pt"
)

# Load model
model = YOLO(model_path)

# Run inference
results = model.predict("path/to/image.jpg", conf=0.25)

# Process results
for result in results:
    boxes = result.boxes
    for box in boxes:
        class_id = int(box.cls[0])
        confidence = float(box.conf[0])
        class_name = model.names[class_id]
        print(f"Detected: {class_name} ({confidence:.2%})")

Batch Processing

# Process multiple images
results = model.predict(["img1.jpg", "img2.jpg", "img3.jpg"])

# Save annotated images
for i, result in enumerate(results):
    result.save(filename=f"result_{i}.jpg")

Classes

Performance

Use this model for litter detection systems, environmental monitoring, and waste management applications.

Citation

If you use this model, please cite:

@misc{litter_detection_yolov8,
  author = {Your Name},
  title = {Litter Detection with YOLOv8},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/esapzoi/litter-detection-yolov8}
}

License

MIT License

Training Data

Model trained on plastic litter detection dataset focusing on bags and bottles.