Dataset Versions

v7

2024-12-10 1:43pm

Generated on Dec 10, 2024

Dataset Split

Train Set 96%
114Images
Valid Set 3%
3Images
Test Set 2%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1024x1024
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -10° and +10°
Shear: ±15° Horizontal, ±4° Vertical
Saturation: Between -17% and +17%
Brightness: Between -17% and +0%
Exposure: Between -10% and +10%
Blur: Up to 0.6px
Noise: Up to 0.1% of pixels