ciCic/yolo11n-seg-bonnetjes

Yolo11n bonnetjes

A YOLO11n segmentation model trained on receipts dataset.

Model summary

• —Layers: 203 layers
• —Parameters: 2,842,803
• —GFLOPs: 10.4
• —File size: 6 MB

[image]

Requirements

pip install ultralytics

Python

from ultralytics import YOLO

# Load model
model = YOLO("yolo11n-seg-bonnetjes.pt")

# Load image
image = Image.open('image.jpg')

# Inference
results = model.predict(
    image,
    imgsz=640,
    conf=0.60,
)

# Display result
results[0].show()

Dataset

• —Train: 4428
• —Valid: 242
• —Test: 146

Preprocessing (created w/ Roboflow)

• —Auto-Orient: Applied
• —Resize: 640x640

Augmentations (created w/ Roboflow)

• —Outputs per training example: 3
• —Flip: Horizontal
• —90° Rotate: Clockwise, Counter-Clockwise, Upside Down
• —Crop: 0% Minimum Zoom, 20% Maximum Zoom
• —Rotation: Between -15° and +15°
• —Shear: ±10° Horizontal, ±10° Vertical
• —Grayscale: Apply to 15% of images
• —Saturation: Between -27% and +27%
• —Brightness: Between -21% and +21%
• —Exposure: Between -82% and +82%
• —Noise: Up to 0.1% of pixels

Results

[image]